Files

8354 lines
1.3 MiB
Plaintext
Raw Permalink Normal View History

[2026-04-22 17:08:48,040] [DEBUG] [axolotl.utils.config.resolve_dtype:74] [PID:1024775] bf16 support detected, enabling for this configuration.
[2026-04-22 17:08:48,597] [DEBUG] [axolotl.utils.config.log_gpu_memory_usage:127] [PID:1024775] baseline 0.000GB ()
[2026-04-22 17:08:48,598] [INFO] [axolotl.cli.config.load_cfg:341] [PID:1024775] config:
{
"activation_offloading": true,
"adam_beta1": 0.9,
"adam_beta2": 0.95,
"axolotl_config_path": "/e/scratch/jureap59/feuer1/code/axolotl_configs/qwen3_8b_sera_v3_1000.yaml",
"base_model": "Qwen/Qwen3-8B",
"base_model_config": "Qwen/Qwen3-8B",
"batch_size": 32,
"bf16": true,
"capabilities": {
"bf16": true,
"compute_capability": "sm_90",
"fp8": true,
"n_gpu": 4,
"n_node": 1,
"tf32": true
},
"chat_template": "chatml",
"context_parallel_size": 1,
"dataloader_num_workers": 4,
"dataloader_pin_memory": true,
"dataloader_prefetch_factor": 256,
"dataset_num_proc": 288,
"dataset_prepared_path": "/e/data1/datasets/playground/ot-baf/axolotl_dataset_cache/sera-v3-1000",
"datasets": [
{
"chat_template": "tokenizer_default",
"data_files": [
"sera-4.5a-full-t1_v3_1000.jsonl"
],
"ds_type": "json",
"field_messages": "messages",
"message_field_training": "train",
"message_property_mappings": {
"content": "content",
"role": "role"
},
"path": "laion/Sera-4.5A-Full-T1-v3-1000",
"trust_remote_code": false,
"type": "chat_template"
}
],
"ddp": true,
"deepspeed": {
"bf16": {
"enabled": true
},
"gradient_accumulation_steps": "auto",
"gradient_clipping": "auto",
"train_batch_size": "auto",
"train_micro_batch_size_per_gpu": "auto",
"wall_clock_breakdown": false,
"zero_optimization": {
"contiguous_gradients": true,
"gather_16bit_weights_on_model_save": true,
"max_live_parameters": 0,
"max_reuse_distance": 0,
"overlap_comm": true,
"reduce_bucket_size": "auto",
"stage": 3,
"stage3_param_persistence_threshold": "auto",
"stage3_prefetch_bucket_size": "auto",
"sub_group_size": 0
}
},
"device": "cuda:0",
"device_map": {
"": 0
},
"dion_rank_fraction": 1.0,
"dion_rank_multiple_of": 1,
"eaft_alpha": 1.0,
"eaft_k": 20,
"env_capabilities": {
"torch_version": "2.9.1"
},
"eval_batch_size": 1,
"eval_causal_lm_metrics": [
"sacrebleu",
"comet",
"ter",
"chrf"
],
"eval_max_new_tokens": 128,
"eval_table_size": 0,
"evals_per_epoch": 0,
"experimental_skip_move_to_device": true,
"flash_attention": true,
"fp16": false,
"generate_samples": false,
"generation_do_sample": true,
"generation_max_new_tokens": 50,
"generation_prompt_ratio": 0.5,
"generation_temperature": 0.7,
"gradient_accumulation_steps": 8,
"gradient_checkpointing": true,
"gradient_checkpointing_kwargs": {
"use_reentrant": true
},
"include_tkps": true,
"layer_offloading": false,
"learning_rate": 1e-05,
"lisa_layers_attribute": "model.layers",
"load_best_model_at_end": false,
"load_in_4bit": false,
"load_in_8bit": false,
"local_rank": 0,
"logging_steps": 1,
"lora_dropout": 0.0,
"loraplus_lr_embedding": 1e-06,
"loss_watchdog_patience": 3,
"loss_watchdog_threshold": 5.0,
"lr_scheduler": "cosine",
"max_grad_norm": 1.0,
"mean_resizing_embeddings": false,
"merge_method": "memory_efficient",
"micro_batch_size": 1,
"model_config_type": "qwen3",
"num_epochs": 3.0,
"num_generation_samples": 3,
"optimizer": "adamw_torch",
"otel_metrics_host": "localhost",
"otel_metrics_port": 8000,
"output_dir": "/e/data1/datasets/playground/ot-baf/checkpoints/sera-v3-1000-axolotl__Qwen3-8B",
"pretrain_multipack_attn": true,
"profiler_steps_start": 0,
"qlora_sharded_model_loading": false,
"quantize_moe_experts": false,
"ray_num_workers": 1,
"resources_per_worker": {
"GPU": 1
},
"sample_packing_bin_size": 200,
"sample_packing_group_size": 100000,
"save_only_model": false,
"save_safetensors": true,
"save_strategy": "epoch",
"sequence_len": 32768,
"shuffle_before_merging_datasets": false,
"shuffle_merged_datasets": true,
"skip_prepare_dataset": false,
"streaming_multipack_buffer_size": 10000,
"strict": false,
"tensor_parallel_size": 1,
"tf32": false,
"tiled_mlp_use_original_mlp": true,
"tokenizer_config": "Qwen/Qwen3-8B",
"tokenizer_save_jinja_files": true,
"torch_dtype": "torch.bfloat16",
"train_on_inputs": false,
"trl": {
"async_prefetch": false,
"log_completions": false,
"mask_truncated_completions": false,
"ref_model_mixup_alpha": 0.9,
"ref_model_sync_steps": 64,
"replay_buffer_size": 0,
"replay_recompute_logps": true,
"reroll_max_groups": 1,
"reroll_start_fraction": 1.0,
"reward_num_workers": 1,
"scale_rewards": true,
"skip_zero_advantage_batches": true,
"sync_ref_model": false,
"use_data_producer": false,
"use_vllm": false,
"vllm_lora_sync": false,
"vllm_server_host": "0.0.0.0",
"vllm_server_port": 8000
},
"use_otel_metrics": false,
"use_ray": false,
"val_set_size": 0.0,
"vllm": {
"device": "auto",
"dtype": "auto",
"gpu_memory_utilization": 0.9,
"host": "0.0.0.0",
"port": 8000
},
"wandb_name": "sera-v3-1000-axolotl__Qwen3-8B",
"warmup_ratio": 0.1875,
"weight_decay": 0.01,
"world_size": 4
}
[2026-04-22 17:08:48,619] [INFO] [axolotl.cli.checks.check_user_token:37] [PID:1024775] Skipping HuggingFace token verification because HF_HUB_OFFLINE is set to True. Only local files will be used.
[2026-04-22 17:08:49,088] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:307] [PID:1024775] EOS: 151645 / <|im_end|>
[2026-04-22 17:08:49,088] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:308] [PID:1024775] BOS: None / None
[2026-04-22 17:08:49,088] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:309] [PID:1024775] PAD: 151643 / <|endoftext|>
[2026-04-22 17:08:49,088] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:310] [PID:1024775] UNK: None / None
[2026-04-22 17:08:49,200] [INFO] [axolotl.utils.data.shared.load_preprocessed_dataset:475] [PID:1024775] Loading prepared dataset from disk at /e/data1/datasets/playground/ot-baf/axolotl_dataset_cache/sera-v3-1000/0b7c53810080c53afa3bb49c397dff74...
[2026-04-22 17:08:49,676] [DEBUG] [axolotl.utils.trainer.calculate_total_num_steps:420] [PID:1024775] total_num_tokens: 8_072_292
[2026-04-22 17:08:50,363] [DEBUG] [axolotl.utils.trainer.calculate_total_num_steps:438] [PID:1024775] `total_supervised_tokens: 1_547_775`
[2026-04-22 17:08:50,363] [DEBUG] [axolotl.utils.trainer.calculate_total_num_steps:521] [PID:1024775] total_num_steps: 29
[2026-04-22 17:08:50,363] [INFO] [axolotl.utils.data.sft._prepare_standard_dataset:121] [PID:1024775] Maximum number of steps set at 29
[2026-04-22 17:08:50,400] [DEBUG] [axolotl.train.setup_model_and_tokenizer:70] [PID:1024775] loading tokenizer... Qwen/Qwen3-8B
[2026-04-22 17:08:50,662] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:307] [PID:1024775] EOS: 151645 / <|im_end|>
[2026-04-22 17:08:50,662] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:308] [PID:1024775] BOS: None / None
[2026-04-22 17:08:50,662] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:309] [PID:1024775] PAD: 151643 / <|endoftext|>
[2026-04-22 17:08:50,662] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:310] [PID:1024775] UNK: None / None
[2026-04-22 17:08:50,662] [DEBUG] [axolotl.train.setup_model_and_tokenizer:81] [PID:1024775] Loading model
[2026-04-22 17:08:50,708] [DEBUG] [axolotl.monkeypatch.transformers.trainer_loss_calc.patch_evaluation_loop:94] [PID:1024775] Patched Trainer.evaluation_loop with nanmean loss calculation
[2026-04-22 17:08:50,709] [DEBUG] [axolotl.monkeypatch.transformers.trainer_loss_calc.patch_maybe_log_save_evaluate:148] [PID:1024775] Patched Trainer._maybe_log_save_evaluate with nanmean loss calculation
[2026-04-22 17:08:50,856] [INFO] [axolotl.monkeypatch.attention.flash_attn_4.patch_flash_attn_4:52] [PID:1024775] Flash Attention 4 is available for your GPU and offers faster training speeds. To enable: pip install flash-attn-4
[2026-04-22 17:08:50,858] [INFO] [axolotl.monkeypatch.deepspeed_utils.patch_checkpoint_wrapper_setattr:52] [PID:1024775] CheckpointWrapper patched to forward DeepSpeed attributes
[2026-04-22 17:09:02,275] [INFO] [axolotl.loaders.model._configure_embedding_dtypes:361] [PID:1024775] Converting modules to torch.bfloat16
[2026-04-22 17:09:02,279] [DEBUG] [axolotl.loaders.model.log_gpu_memory_usage:127] [PID:1024775] Memory usage after model load 4.973GB (+4.973GB allocated, +5.080GB reserved)
[2026-04-22 17:09:08,636] [INFO] [axolotl.train.save_initial_configs:421] [PID:1024775] Pre-saving tokenizer to /e/data1/datasets/playground/ot-baf/checkpoints/sera-v3-1000-axolotl__Qwen3-8B...
[2026-04-22 17:09:08,757] [INFO] [axolotl.train.save_initial_configs:426] [PID:1024775] Pre-saving model config to /e/data1/datasets/playground/ot-baf/checkpoints/sera-v3-1000-axolotl__Qwen3-8B...
[2026-04-22 17:09:08,760] [INFO] [axolotl.train.execute_training:222] [PID:1024775] Starting trainer...
[2026-04-22 17:09:09,099] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:09,100] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:09,100] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:09,100] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:09,100] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:09,101] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:09,101] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:09,101] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:09,101] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:09,101] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:09,102] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:09,102] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:09,102] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:09,102] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:09,102] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:09,102] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:09,103] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:09,103] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:09,103] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:09,103] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:09,104] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:09,104] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:09,104] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:09,104] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:09,104] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:09,105] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:09,105] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:09,105] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:09,105] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:09,105] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:09,105] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:09,106] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:09,106] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:09,106] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:09,106] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:09,106] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:09,110] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_id to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:09,112] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_id to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:09,114] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_id to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:09,115] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_id to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:09,117] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_id to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:09,118] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_id to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:09,119] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_id to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:09,121] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_id to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:09,123] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_id to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:09,124] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_id to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:09,125] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_id to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:09,127] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_id to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:09,128] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_id to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:09,130] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_id to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:09,131] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_id to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:09,132] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_id to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:09,133] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_id to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:09,134] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_id to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:09,136] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_id to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:09,137] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_id to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:09,139] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_id to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:09,140] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_id to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:09,141] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_id to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:09,142] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_id to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:09,144] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_id to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:09,145] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_id to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:09,146] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_id to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:09,147] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_id to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:09,149] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_id to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:09,150] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_id to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:09,151] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_id to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:09,153] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_id to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:09,154] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_id to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:09,155] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_id to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:09,157] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_id to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:09,158] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_id to wrapped module Qwen3DecoderLayer
0%| | 0/29 [00:00<?, ?it/s][2026-04-22 17:09:11,551] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:11,772] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:11,823] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:11,881] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:11,941] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:11,998] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:12,060] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:12,123] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:12,184] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:12,245] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:12,307] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:12,368] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:12,434] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:12,491] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:12,557] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:12,614] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:12,675] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:12,737] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:12,798] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:12,861] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:12,924] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:12,986] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:13,047] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:13,109] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:13,170] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:13,232] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:13,293] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:13,355] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:13,416] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:13,477] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:13,538] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:13,601] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:13,665] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:13,727] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:13,790] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:13,852] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:18,009] [WARNING] [trl.models.activation_offloading.verify_sufficient_virtual_memory:178] [PID:1024775] [RANK 0] curr_pct=68.0% > self.virtual_memory_safe_pct=60% of virtual memory used
[2026-04-22 17:09:26,374] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:26,433] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:26,490] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:26,553] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:26,618] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:26,686] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:26,752] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:26,819] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:26,886] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:26,949] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:27,014] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:27,079] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:27,142] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:27,206] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:27,270] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:27,335] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:27,398] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:27,462] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:27,525] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:27,589] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:27,652] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:27,716] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:27,780] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:27,843] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:27,907] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:27,971] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:28,036] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:28,099] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:28,163] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:28,228] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:28,294] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:28,362] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:28,428] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:28,502] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:28,561] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:28,627] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:40,377] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:40,395] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:40,447] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:40,504] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:40,559] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:40,616] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:40,671] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:40,726] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:40,782] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:40,838] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:40,893] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:40,948] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:41,004] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:41,061] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:41,117] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:41,172] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:41,228] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:41,283] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:41,339] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:41,394] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:41,449] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:41,505] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:41,561] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:41,617] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:41,672] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:41,727] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:41,783] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:41,838] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:41,893] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:41,949] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:42,005] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:42,061] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:42,116] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:42,174] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:42,230] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:42,285] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:50,802] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:50,822] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:50,874] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:50,931] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:50,989] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:51,045] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:51,102] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:51,160] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:51,217] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:51,274] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:51,330] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:51,386] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:51,443] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:51,499] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:51,556] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:51,612] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:51,669] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:51,726] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:51,782] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:51,838] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:51,895] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:51,951] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:52,009] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:52,066] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:52,122] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:52,177] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:52,235] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:52,292] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:52,350] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:52,407] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:52,464] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:52,521] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:52,577] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:52,634] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:52,691] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:09:52,747] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:00,151] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:00,171] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:00,212] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:00,256] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:00,300] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:00,345] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:00,393] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:00,440] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:00,489] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:00,537] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:00,581] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:00,628] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:00,675] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:00,722] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:00,766] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:00,813] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:00,860] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:00,916] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:00,976] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:01,035] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:01,094] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:01,154] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:01,213] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:01,273] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:01,332] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:01,392] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:01,452] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:01,513] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:01,572] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:01,631] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:01,690] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:01,751] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:01,812] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:01,871] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:01,929] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:01,989] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:11,153] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:11,173] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:11,230] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:11,293] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:11,355] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:11,418] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:11,479] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:11,541] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:11,603] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:11,666] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:11,731] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:11,795] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:11,861] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:11,926] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:11,991] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:12,056] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:12,120] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:12,184] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:12,249] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:12,314] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:12,378] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:12,442] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:12,506] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:12,570] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:12,632] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:12,696] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:12,760] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:12,824] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:12,887] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:12,952] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:13,016] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:13,080] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:13,143] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:13,207] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:13,271] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:13,332] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:21,630] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:21,650] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:21,686] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:21,726] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:21,765] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:21,808] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:21,848] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:21,888] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:21,930] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:21,970] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:22,010] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:22,054] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:22,129] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:22,180] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:22,241] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:22,303] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:22,364] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:22,439] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:22,489] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:22,549] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:22,611] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:22,673] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:22,736] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:22,798] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:22,860] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:22,922] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:22,983] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:23,045] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:23,107] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:23,168] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:23,230] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:23,292] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:23,354] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:23,417] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:23,479] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:23,542] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:32,035] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:32,054] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:32,109] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:32,169] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:32,231] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:32,291] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:32,351] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:32,412] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:32,474] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:32,536] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:32,598] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:32,660] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:32,722] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:32,784] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:32,846] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:32,908] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:32,970] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:33,033] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:33,094] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:33,155] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:33,218] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:33,280] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:33,342] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:33,404] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:33,466] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:33,529] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:33,591] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:33,654] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:33,715] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:33,775] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:33,837] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:33,898] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:34,408] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:34,466] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:34,527] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:34,584] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
3%|▎ | 1/29 [01:32<43:18, 92.80s/it] {'loss': '1.086', 'grad_norm': '18.57', 'learning_rate': '0', 'ppl': '2.961', 'memory/max_active (GiB)': '76.08', 'memory/max_allocated (GiB)': '74.92', 'memory/device_reserved (GiB)': '88.51', 'tokens/train_per_sec_per_gpu': '63.71', 'tokens/total': 866752, 'tokens/trainable': 161897, 'epoch': '0.1067'}
3%|▎ | 1/29 [01:32<43:18, 92.80s/it][2026-04-22 17:10:43,085] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:43,122] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:43,180] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:43,242] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:43,304] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:43,367] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:43,430] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:43,493] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:43,555] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:43,618] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:43,680] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:43,743] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:43,804] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:43,868] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:43,931] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:43,993] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:44,056] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:44,118] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:44,180] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:44,243] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:44,306] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:44,370] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:44,433] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:44,495] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:44,558] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:44,620] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:44,682] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:44,746] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:44,809] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:44,873] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:44,936] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:44,999] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:45,061] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:45,124] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:45,187] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:45,252] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:54,725] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:54,748] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:54,790] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:54,836] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:54,882] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:54,930] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:54,979] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:55,024] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:55,071] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:55,119] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:55,168] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:55,214] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:55,263] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:55,320] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:55,386] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:55,452] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:55,520] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:55,587] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:55,653] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:55,720] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:55,788] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:55,854] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:55,921] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:55,988] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:56,055] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:56,123] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:56,189] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:56,256] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:56,323] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:56,390] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:56,457] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:56,525] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:56,590] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:56,683] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:56,724] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:10:56,792] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:06,736] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:06,755] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:06,787] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:06,821] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:06,856] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:06,890] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:06,926] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:06,962] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:06,998] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:07,047] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:07,127] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:07,231] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:07,303] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:07,361] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:07,394] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:07,457] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:07,520] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:07,587] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:07,688] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:07,753] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:07,794] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:07,856] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:07,908] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:07,968] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:08,032] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:08,096] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:08,161] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:08,225] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:08,289] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:08,357] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:08,417] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:08,482] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:08,547] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:08,628] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:08,686] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:08,750] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:19,215] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:19,235] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:19,281] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:19,333] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:19,385] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:19,438] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:19,490] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:19,543] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:19,596] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:19,647] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:19,700] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:19,753] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:19,807] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:19,861] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:19,913] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:19,966] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:20,019] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:20,073] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:20,126] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:20,179] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:20,234] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:20,288] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:20,342] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:20,397] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:20,449] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:20,503] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:20,559] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:20,614] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:20,667] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:20,721] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:20,774] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:20,826] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:20,880] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:20,934] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:20,988] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:21,040] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:29,223] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:29,242] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:29,277] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:29,313] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:29,350] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:29,389] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:29,427] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:29,465] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:29,502] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:29,541] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:29,581] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:29,618] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:29,655] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:29,698] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:29,751] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:29,805] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:29,857] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:29,909] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:29,963] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:30,015] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:30,068] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:30,120] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:30,173] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:30,227] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:30,295] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:30,348] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:30,400] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:30,455] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:30,508] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:30,561] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:30,621] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:30,674] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:30,724] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:30,779] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:30,831] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:30,886] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:38,522] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:38,542] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:38,592] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:38,647] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:38,704] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:38,763] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:38,821] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:38,878] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:38,933] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:38,990] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:39,048] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:39,109] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:39,169] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:39,228] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:39,289] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:39,351] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:39,411] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:39,472] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:39,532] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:39,592] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:39,652] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:39,711] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:39,769] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:39,826] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:39,883] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:39,940] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:39,998] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:40,058] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:40,117] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:40,176] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:40,238] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:40,299] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:40,360] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:40,421] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:40,479] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:40,540] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:50,726] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:50,746] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:50,782] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:50,820] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:50,859] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:50,900] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:50,938] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:50,977] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:51,018] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:51,056] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:51,106] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:51,188] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:51,254] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:51,316] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:51,378] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:51,440] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:51,502] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:51,565] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:51,628] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:51,692] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:51,756] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:51,822] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:51,886] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:51,956] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:52,020] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:52,081] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:52,145] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:52,207] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:52,277] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:52,339] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:52,403] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:52,471] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:52,535] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:52,598] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:52,662] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:11:52,728] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:03,606] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:03,625] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:03,673] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:03,725] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:03,778] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:03,833] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:03,886] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:03,940] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:03,993] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:04,048] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:04,105] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:04,164] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:04,221] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:04,277] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:04,334] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:04,391] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:04,448] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:04,507] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:04,565] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:04,622] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:04,676] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:04,731] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:04,785] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:04,840] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:04,896] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:04,953] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:05,010] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:05,068] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:05,126] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:05,184] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:05,242] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:05,300] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:05,358] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:05,416] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:05,472] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:05,527] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:15,382] [WARNING] [stage3.py:2497:step] 6 pytorch allocator cache flushes since last step. this happens when there is high memory pressure and is detrimental to performance. if this is happening frequently consider adjusting settings to reduce memory consumption. If you are unable to make the cache flushes go away consider adding get_accelerator().empty_cache() calls in your training loop to ensure that all ranks flush their caches at the same time
7%|▋ | 2/29 [03:05<41:38, 92.52s/it] {'loss': '1.114', 'grad_norm': '19.11', 'learning_rate': '2e-06', 'ppl': '3.046', 'memory/max_active (GiB)': '84.51', 'memory/max_allocated (GiB)': '84.51', 'memory/device_reserved (GiB)': '92.83', 'tokens/train_per_sec_per_gpu': '62.7', 'tokens/total': 1715584, 'tokens/trainable': 330311, 'epoch': '0.2133'}
7%|▋ | 2/29 [03:05<41:38, 92.52s/it][2026-04-22 17:12:15,410] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:15,444] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:15,502] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:15,561] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:15,620] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:15,680] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:15,740] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:15,801] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:15,862] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:15,923] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:15,983] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:16,043] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:16,103] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:16,164] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:16,659] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:16,718] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:16,778] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:16,837] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:16,897] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:16,956] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:17,014] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:17,074] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:17,133] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:17,195] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:17,256] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:17,679] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:17,734] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:17,794] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:17,854] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:17,912] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:17,972] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:18,032] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:18,092] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:18,153] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:18,215] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:18,277] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:28,513] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:28,537] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:28,579] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:28,627] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:28,675] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:28,724] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:28,775] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:28,822] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:28,871] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:28,921] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:28,971] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:29,019] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:29,068] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:29,121] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:29,180] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:29,247] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:29,317] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:29,392] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:29,458] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:29,516] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:29,583] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:29,650] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:29,717] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:29,783] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:29,851] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:29,918] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:29,985] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:30,052] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:30,119] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:30,186] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:30,255] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:30,321] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:30,388] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:30,471] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:30,522] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:30,589] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:40,300] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:40,320] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:40,362] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:40,409] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:40,456] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:40,502] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:40,551] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:40,599] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:40,644] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:40,694] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:40,741] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:40,789] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:40,837] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:40,885] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:40,954] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:41,014] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:41,070] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:41,134] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:41,198] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:41,262] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:41,326] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:41,391] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:41,455] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:41,518] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:41,582] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:41,647] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:41,712] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:41,776] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:41,839] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:41,903] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:41,969] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:42,032] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:42,096] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:42,160] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:42,223] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:42,287] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:51,698] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:51,720] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:51,775] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:51,834] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:51,893] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:51,951] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:52,012] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:52,071] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:52,130] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:52,190] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:52,251] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:52,311] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:52,371] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:52,430] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:52,489] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:52,549] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:52,609] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:52,669] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:52,728] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:52,788] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:52,848] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:52,909] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:52,968] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:53,027] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:53,087] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:53,146] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:53,206] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:53,267] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:53,326] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:53,386] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:53,446] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:53,505] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:53,565] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:53,625] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:53,685] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:12:53,744] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:02,012] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:02,031] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:02,088] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:02,149] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:02,209] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:02,268] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:02,330] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:02,390] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:02,449] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:02,508] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:02,568] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:02,629] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:02,689] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:02,748] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:02,808] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:02,868] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:02,928] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:02,987] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:03,047] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:03,107] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:03,167] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:03,228] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:03,287] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:03,346] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:03,407] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:03,467] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:03,526] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:03,586] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:03,646] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:03,706] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:03,767] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:03,826] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:03,886] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:03,948] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:04,008] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:04,067] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:12,143] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:12,163] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:12,218] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:12,278] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:12,338] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:12,398] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:12,456] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:12,515] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:12,574] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:12,633] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:12,693] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:12,753] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:12,814] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:12,873] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:12,933] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:12,992] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:13,052] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:13,112] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:13,172] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:13,232] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:13,292] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:13,352] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:13,412] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:13,472] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:13,532] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:13,592] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:13,652] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:13,713] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:13,772] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:13,833] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:13,893] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:13,953] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:14,013] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:14,074] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:14,134] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:14,192] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:23,228] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:23,247] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:23,307] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:23,371] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:23,434] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:23,499] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:23,562] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:23,626] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:23,690] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:23,753] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:23,817] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:23,881] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:23,947] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:24,010] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:24,073] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:24,137] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:24,200] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:24,264] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:24,328] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:24,392] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:24,458] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:24,525] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:24,590] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:24,656] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:24,723] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:24,789] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:24,855] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:24,921] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:24,987] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:25,054] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:25,121] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:25,185] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:25,252] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:25,318] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:25,383] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:25,447] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:35,521] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:35,541] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:35,598] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:35,658] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:35,716] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:35,775] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:35,835] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:35,894] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:35,955] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:36,016] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:36,075] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:36,136] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:36,197] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:36,257] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:36,318] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:36,379] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:36,440] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:36,500] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:36,562] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:36,623] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:36,684] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:36,746] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:36,807] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:36,869] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:36,930] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:36,991] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:37,052] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:37,114] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:37,176] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:37,238] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:37,302] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:37,365] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:37,427] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:37,491] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:37,552] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:37,613] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:47,164] [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
10%|█ | 3/29 [04:36<39:56, 92.18s/it] {'loss': '1.083', 'grad_norm': '17.84', 'learning_rate': '4e-06', 'ppl': '2.953', 'memory/max_active (GiB)': '90.17', 'memory/max_allocated (GiB)': '90.17', 'memory/device_reserved (GiB)': '92.83', 'tokens/train_per_sec_per_gpu': '51.34', 'tokens/total': 2569408, 'tokens/trainable': 495726, 'epoch': '0.32'}
10%|█ | 3/29 [04:36<39:56, 92.18s/it][2026-04-22 17:13:47,190] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:47,224] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:47,287] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:47,349] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:47,412] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:47,473] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:47,534] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:47,597] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:47,658] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:47,721] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:47,782] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:47,845] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:47,907] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:47,969] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:48,030] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:48,093] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:48,156] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:48,218] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:48,280] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:48,342] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:48,404] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:48,466] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:48,528] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:48,590] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:48,653] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:48,716] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:48,778] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:48,840] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:48,903] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:48,965] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:49,027] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:49,089] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:49,151] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:49,215] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:49,278] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:49,340] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:58,547] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:58,569] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:58,631] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:58,699] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:58,770] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:58,838] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:58,907] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:58,976] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:59,044] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:59,114] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:59,182] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:59,251] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:59,319] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:59,386] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:59,455] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:59,523] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:59,592] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:59,664] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:59,734] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:59,805] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:59,876] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:13:59,945] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:14:00,016] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:14:00,085] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:14:00,155] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:14:00,226] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:14:00,295] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:14:00,366] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:14:00,438] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:14:00,508] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:14:00,580] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:14:00,652] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:14:00,721] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:14:00,788] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:14:00,855] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:14:00,920] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:14:11,700] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:14:11,720] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:14:11,752] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:14:11,785] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:14:11,820] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:14:11,855] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:14:11,890] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:14:11,925] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:14:11,961] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:14:12,010] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:14:12,077] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:14:12,134] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:14:12,195] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:14:12,258] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:14:12,321] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:14:12,385] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:14:12,448] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:14:12,510] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:14:12,573] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:14:12,636] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:14:12,697] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:14:12,760] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:14:12,823] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:14:12,886] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:14:12,950] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:14:13,012] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:14:13,075] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:14:13,137] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:14:13,200] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:14:13,263] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:14:13,329] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:14:13,392] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:14:13,455] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:14:13,517] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:14:13,577] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:14:13,640] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:14:23,363] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:14:23,383] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:14:23,442] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:14:23,506] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:14:23,572] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:14:23,637] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:14:23,702] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:14:23,769] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:14:23,834] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:14:23,899] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:14:23,966] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:14:24,032] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:14:24,097] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:14:24,162] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:14:24,227] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:14:24,294] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:14:24,361] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:14:24,428] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:14:24,493] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:14:24,560] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:14:24,624] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:14:24,689] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:14:24,753] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:14:24,817] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:14:24,881] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:14:24,946] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:14:25,011] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:14:25,075] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:14:25,139] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:14:25,204] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:14:25,269] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:14:25,333] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:14:25,397] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:14:25,464] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:14:25,528] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:14:25,590] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:14:36,340] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:14:36,361] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:14:36,412] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:14:36,465] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:14:36,522] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:14:36,579] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:14:36,637] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:14:36,693] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:14:36,749] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:14:36,808] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:14:36,867] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:14:36,927] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:14:36,987] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:14:37,042] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:14:37,100] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:14:37,157] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:14:37,213] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:14:37,269] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:14:37,327] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:14:37,386] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:14:37,446] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:14:37,506] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:14:37,566] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:14:37,626] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:14:37,686] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:14:37,746] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:14:37,802] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:14:37,858] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:14:37,915] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:14:37,971] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:14:38,029] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:14:38,088] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:14:38,148] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:14:38,209] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:14:38,269] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:14:38,328] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:14:48,871] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:14:48,892] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:14:48,943] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:14:49,000] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:14:49,056] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:14:49,111] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:14:49,167] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:14:49,223] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:14:49,282] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:14:49,341] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:14:49,401] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:14:49,462] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:14:49,523] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:14:49,578] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:14:49,636] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:14:49,693] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:14:49,752] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:14:49,811] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:14:49,871] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:14:49,930] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:14:49,990] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:14:50,050] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:14:50,106] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:14:50,163] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:14:50,220] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:14:50,279] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:14:50,338] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:14:50,399] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:14:50,459] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:14:50,523] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:14:50,589] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:14:50,654] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:14:50,722] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:14:50,788] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:14:50,853] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:14:50,920] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:00,940] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:00,960] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:00,992] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:01,025] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:01,060] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:01,097] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:01,132] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:01,167] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:01,202] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:01,237] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:01,298] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:01,350] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:01,405] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:01,464] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:01,521] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:01,580] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:01,639] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:01,699] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:01,756] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:01,813] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:01,871] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:01,929] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:01,987] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:02,060] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:02,120] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:02,172] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:02,230] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:02,285] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:02,343] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:02,403] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:02,462] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:02,519] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:02,577] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:02,639] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:02,695] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:02,768] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:11,144] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:11,164] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:11,218] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:11,276] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:11,335] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:11,394] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:11,455] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:11,515] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:11,574] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:11,633] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:11,695] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:11,756] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:11,816] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:11,878] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:11,938] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:12,001] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:12,065] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:12,127] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:12,190] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:12,253] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:12,316] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:12,377] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:12,441] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:12,505] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:12,569] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:12,632] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:12,695] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:12,758] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:12,822] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:12,886] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:12,950] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:13,014] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:13,077] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:13,141] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:13,204] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:13,268] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:23,959] [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
14%|█▍ | 4/29 [06:13<39:10, 94.00s/it] {'loss': '0.9875', 'grad_norm': '10.35', 'learning_rate': '6e-06', 'ppl': '2.685', 'memory/max_active (GiB)': '91.35', 'memory/max_allocated (GiB)': '91.35', 'memory/device_reserved (GiB)': '92.9', 'tokens/train_per_sec_per_gpu': '65.19', 'tokens/total': 3453504, 'tokens/trainable': 670131, 'epoch': '0.4267'}
14%|█▍ | 4/29 [06:13<39:10, 94.00s/it][2026-04-22 17:15:23,987] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:24,020] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:24,080] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:24,140] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:24,200] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:24,261] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:24,321] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:24,381] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:24,443] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:24,501] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:24,563] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:24,624] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:24,685] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:24,744] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:24,805] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:24,867] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:24,927] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:24,987] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:25,047] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:25,108] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:25,169] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:25,229] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:25,290] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:25,351] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:25,413] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:25,474] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:25,534] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:25,594] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:25,655] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:25,717] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:25,777] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:25,840] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:25,901] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:25,963] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:26,025] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:26,086] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:36,365] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:36,387] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:36,443] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:36,505] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:36,567] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:36,627] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:36,688] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:36,749] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:36,811] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:36,871] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:36,932] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:36,993] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:37,054] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:37,116] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:37,176] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:37,238] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:37,300] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:37,361] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:37,423] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:37,484] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:37,546] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:37,608] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:37,669] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:38,114] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:38,170] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:38,229] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:38,289] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:38,349] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:38,409] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:38,469] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:38,530] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:38,591] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:38,651] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:38,727] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:38,774] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:38,835] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:47,389] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:47,410] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:47,446] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:47,484] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:47,523] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:47,564] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:47,602] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:47,643] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:47,684] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:47,721] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:47,781] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:47,842] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:47,900] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:47,959] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:48,021] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:48,086] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:48,150] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:48,214] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:48,277] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:48,342] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:48,408] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:48,470] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:48,533] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:48,599] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:48,662] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:48,741] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:48,807] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:48,867] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:48,927] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:48,988] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:49,051] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:49,111] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:49,174] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:49,238] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:49,302] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:49,366] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:59,014] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:59,036] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:59,081] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:59,130] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:59,179] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:59,230] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:59,280] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:59,330] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:59,380] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:59,430] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:59,480] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:59,531] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:59,582] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:59,635] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:59,688] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:59,740] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:59,793] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:59,846] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:59,899] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:15:59,951] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:00,004] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:00,058] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:00,111] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:00,164] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:00,217] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:00,270] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:00,322] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:00,375] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:00,430] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:00,484] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:00,538] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:00,592] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:00,646] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:00,701] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:00,755] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:00,808] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:08,846] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:08,866] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:08,916] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:08,969] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:09,024] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:09,078] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:09,133] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:09,187] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:09,242] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:09,300] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:09,356] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:09,415] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:09,473] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:09,532] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:09,591] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:09,650] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:09,708] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:09,766] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:09,825] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:09,884] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:09,943] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:09,998] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:10,053] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:10,108] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:10,164] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:10,222] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:10,280] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:10,338] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:10,397] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:10,456] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:10,515] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:10,573] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:10,632] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:10,692] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:10,749] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:10,808] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:19,878] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:19,899] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:19,960] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:20,027] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:20,095] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:20,165] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:20,231] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:20,299] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:20,368] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:20,437] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:20,506] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:20,574] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:20,643] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:20,712] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:20,779] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:20,846] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:20,914] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:20,981] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:21,048] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:21,116] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:21,182] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:21,250] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:21,317] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:21,384] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:21,452] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:21,518] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:21,586] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:21,653] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:21,720] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:21,788] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:21,855] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:21,922] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:21,990] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:22,057] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:22,125] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:22,190] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:32,971] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:32,991] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:33,042] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:33,099] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:33,156] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:33,213] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:33,269] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:33,323] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:33,381] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:33,441] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:33,501] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:33,558] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:33,618] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:33,676] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:33,732] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:33,789] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:33,845] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:33,903] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:33,963] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:34,022] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:34,082] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:34,143] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:34,204] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:34,263] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:34,319] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:34,373] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:34,431] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:34,489] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:34,548] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:34,608] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:34,669] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:34,735] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:34,800] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:34,867] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:34,932] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:34,997] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:44,684] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:44,704] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:44,747] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:44,792] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:44,837] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:44,887] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:44,934] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:44,985] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:45,030] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:45,078] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:45,126] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:45,172] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:45,217] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:45,268] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:45,330] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:45,390] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:45,452] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:45,513] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:45,576] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:45,640] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:45,705] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:45,770] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:45,833] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:45,896] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:45,960] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:46,024] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:46,088] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:46,153] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:46,217] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:46,281] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:46,345] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:46,410] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:46,475] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:46,540] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:46,603] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:46,682] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:56,991] [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
17%|█▋ | 5/29 [07:46<37:27, 93.65s/it] {'loss': '0.8417', 'grad_norm': '5.001', 'learning_rate': '8e-06', 'ppl': '2.32', 'memory/max_active (GiB)': '92.18', 'memory/max_allocated (GiB)': '92.18', 'memory/device_reserved (GiB)': '92.88', 'tokens/train_per_sec_per_gpu': '48.5', 'tokens/total': 4297856, 'tokens/trainable': 832861, 'epoch': '0.5333'}
17%|█▋ | 5/29 [07:46<37:27, 93.65s/it][2026-04-22 17:16:57,020] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:57,054] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:57,112] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:57,172] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:57,233] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:57,295] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:57,356] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:57,418] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:57,478] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:57,540] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:57,603] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:57,663] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:57,725] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:57,787] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:57,849] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:57,911] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:57,972] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:58,034] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:58,095] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:58,158] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:58,220] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:58,281] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:58,343] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:58,405] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:58,468] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:58,529] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:58,591] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:58,653] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:58,716] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:58,777] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:58,840] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:58,902] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:58,965] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:59,027] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:59,089] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:16:59,152] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:08,219] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:08,241] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:08,294] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:08,353] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:08,412] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:08,471] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:08,530] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:08,589] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:08,648] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:08,708] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:08,767] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:08,828] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:08,887] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:08,947] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:09,009] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:09,069] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:09,130] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:09,192] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:09,254] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:09,316] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:09,377] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:09,439] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:09,501] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:09,564] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:09,625] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:09,687] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:09,749] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:09,811] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:09,872] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:09,933] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:09,995] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:10,058] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:10,120] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:10,189] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:10,245] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:10,307] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:20,944] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:20,966] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:21,022] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:21,082] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:21,145] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:21,209] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:21,670] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:21,725] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:21,783] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:21,844] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:21,906] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:21,968] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:22,030] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:22,091] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:22,153] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:22,212] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:22,274] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:22,336] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:22,401] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:22,468] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:22,532] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:22,594] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:22,661] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:22,726] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:22,787] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:22,849] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:22,909] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:22,972] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:23,038] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:23,104] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:23,179] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:23,244] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:23,310] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:23,377] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:23,443] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:23,511] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:34,272] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:34,292] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:34,348] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:34,408] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:34,469] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:34,531] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:34,593] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:34,655] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:34,716] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:34,776] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:34,839] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:34,901] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:34,964] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:35,026] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:35,089] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:35,151] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:35,213] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:35,273] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:35,335] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:35,398] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:35,460] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:35,522] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:35,583] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:35,645] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:35,707] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:35,770] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:35,832] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:35,896] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:35,959] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:36,022] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:36,085] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:36,149] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:36,213] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:36,276] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:36,340] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:36,403] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:46,543] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:46,564] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:46,623] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:46,686] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:46,750] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:46,812] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:46,875] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:46,940] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:47,003] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:47,068] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:47,131] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:47,197] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:47,262] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:47,330] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:47,395] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:47,461] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:47,526] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:47,590] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:47,653] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:47,717] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:47,780] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:47,844] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:47,909] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:47,972] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:48,034] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:48,099] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:48,163] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:48,227] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:48,291] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:48,357] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:48,421] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:48,485] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:48,549] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:48,612] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:48,677] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:48,739] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:58,771] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:58,791] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:58,852] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:58,918] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:58,985] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:59,050] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:59,116] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:59,181] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:59,249] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:59,315] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:59,382] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:59,449] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:59,515] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:59,580] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:59,646] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:59,712] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:59,780] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:59,848] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:59,914] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:17:59,979] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:00,045] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:00,111] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:00,175] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:00,241] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:00,307] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:00,372] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:00,438] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:00,503] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:00,569] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:00,633] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:00,699] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:00,765] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:00,830] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:00,898] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:00,963] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:01,026] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:11,150] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:11,172] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:11,217] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:11,267] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:11,316] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:11,365] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:11,414] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:11,464] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:11,515] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:11,567] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:11,617] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:11,668] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:11,718] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:11,769] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:11,820] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:11,871] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:11,922] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:11,973] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:12,025] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:12,076] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:12,128] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:12,179] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:12,231] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:12,281] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:12,332] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:12,384] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:12,436] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:12,489] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:12,541] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:12,594] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:12,647] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:12,699] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:12,752] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:12,806] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:12,855] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:12,906] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:20,606] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:20,626] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:20,659] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:20,695] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:20,732] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:20,769] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:20,807] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:20,842] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:20,880] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:20,916] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:20,954] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:20,993] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:21,030] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:21,068] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:21,104] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:21,142] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:21,187] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:21,235] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:21,293] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:21,343] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:21,390] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:21,432] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:21,481] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:21,528] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:21,578] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:21,626] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:21,674] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:21,723] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:21,781] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:21,826] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:21,874] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:21,920] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:21,969] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:22,018] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:22,065] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:22,114] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:29,392] [WARNING] [stage3.py:2497:step] 13 pytorch allocator cache flushes since last step. this happens when there is high memory pressure and is detrimental to performance. if this is happening frequently consider adjusting settings to reduce memory consumption. If you are unable to make the cache flushes go away consider adding get_accelerator().empty_cache() calls in your training loop to ensure that all ranks flush their caches at the same time
21%|██ | 6/29 [09:19<35:44, 93.23s/it] {'loss': '0.8376', 'grad_norm': '6.239', 'learning_rate': '1e-05', 'ppl': '2.311', 'memory/max_active (GiB)': '91.23', 'memory/max_allocated (GiB)': '91.23', 'memory/device_reserved (GiB)': '92.61', 'tokens/train_per_sec_per_gpu': '48.17', 'tokens/total': 5179136, 'tokens/trainable': 1009902, 'epoch': '0.64'}
21%|██ | 6/29 [09:19<35:44, 93.23s/it][2026-04-22 17:18:29,419] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:29,453] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:29,512] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:29,572] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:29,632] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:29,690] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:29,749] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:29,809] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:29,868] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:29,928] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:29,987] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:30,047] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:30,107] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:30,167] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:30,227] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:30,286] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:30,346] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:30,405] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:30,465] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:30,525] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:30,585] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:30,645] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:30,706] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:30,764] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:30,824] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:30,884] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:30,943] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:31,003] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:31,063] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:31,123] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:31,183] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:31,243] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:31,303] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:31,363] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:31,424] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:31,485] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:41,230] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:41,253] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:41,293] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:41,341] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:41,388] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:41,434] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:41,484] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:41,532] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:41,580] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:41,627] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:41,674] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:41,725] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:41,774] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:41,823] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:41,870] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:41,919] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:41,994] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:42,048] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:42,104] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:42,156] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:42,215] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:42,276] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:42,338] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:42,414] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:42,471] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:42,532] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:42,587] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:42,645] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:42,707] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:42,769] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:42,831] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:42,892] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:42,953] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:43,032] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:43,076] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:43,137] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:52,565] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:52,584] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:52,613] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:52,642] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:52,673] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:52,703] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:52,734] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:52,765] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:52,819] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:52,887] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:52,946] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:53,002] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:53,062] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:53,118] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:53,176] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:53,235] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:53,296] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:53,359] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:53,419] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:53,480] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:53,541] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:53,602] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:53,676] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:54,214] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:54,242] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:54,270] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:54,330] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:54,385] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:54,437] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:54,497] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:54,560] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:54,621] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:54,682] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:54,742] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:54,800] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:18:54,867] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:04,334] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:04,353] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:04,409] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:04,468] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:04,528] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:04,588] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:04,650] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:04,711] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:04,772] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:04,833] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:04,898] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:04,964] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:05,087] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:05,145] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:05,204] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:05,275] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:05,334] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:05,396] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:05,459] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:05,523] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:05,588] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:05,650] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:05,712] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:05,775] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:05,840] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:05,904] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:05,967] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:06,029] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:06,091] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:06,155] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:06,218] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:06,283] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:06,348] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:06,412] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:06,476] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:06,543] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:17,588] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:17,608] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:17,649] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:17,692] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:17,737] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:17,782] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:17,826] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:17,870] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:17,913] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:17,957] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:18,001] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:18,048] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:18,113] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:18,184] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:18,258] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:18,324] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:18,384] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:18,445] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:18,510] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:18,577] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:18,641] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:18,707] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:18,772] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:18,854] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:18,911] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:18,970] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:19,035] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:19,100] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:19,166] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:19,232] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:19,297] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:19,363] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:19,429] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:19,494] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:19,559] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:19,625] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:29,431] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:29,450] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:29,495] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:29,545] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:29,594] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:29,644] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:29,694] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:29,746] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:29,796] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:29,849] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:29,901] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:29,953] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:30,004] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:30,054] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:30,106] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:30,158] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:30,211] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:30,263] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:30,314] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:30,364] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:30,414] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:30,466] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:30,519] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:30,573] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:30,633] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:30,693] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:30,752] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:30,813] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:30,873] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:30,932] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:30,992] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:31,052] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:31,112] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:31,172] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:31,231] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:31,291] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:39,847] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:39,867] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:39,915] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:39,967] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:40,019] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:40,071] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:40,123] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:40,177] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:40,230] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:40,285] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:40,339] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:40,394] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:40,449] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:40,502] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:40,556] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:40,610] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:40,663] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:40,716] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:40,770] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:40,823] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:40,876] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:40,930] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:40,983] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:41,036] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:41,090] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:41,143] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:41,196] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:41,249] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:41,302] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:41,355] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:41,408] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:41,461] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:41,513] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:41,566] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:41,619] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:41,670] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:49,140] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:49,160] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:49,210] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:49,263] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:49,317] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:49,372] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:49,428] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:49,483] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:49,538] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:49,594] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:49,649] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:49,704] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:49,758] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:49,812] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:49,866] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:49,920] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:49,974] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:50,028] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:50,083] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:50,137] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:50,191] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:50,247] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:50,302] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:50,357] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:50,412] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:50,466] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:50,520] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:50,575] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:50,629] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:50,684] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:50,738] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:50,793] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:50,848] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:50,903] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:50,957] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:51,011] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:58,970] [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
24%|██▍ | 7/29 [10:48<33:44, 92.03s/it] {'loss': '0.776', 'grad_norm': '4.316', 'learning_rate': '9.957e-06', 'ppl': '2.173', 'memory/max_active (GiB)': '86.63', 'memory/max_allocated (GiB)': '86.63', 'memory/device_reserved (GiB)': '92.88', 'tokens/train_per_sec_per_gpu': '39.64', 'tokens/total': 6040320, 'tokens/trainable': 1171791, 'epoch': '0.7467'}
24%|██▍ | 7/29 [10:48<33:44, 92.03s/it][2026-04-22 17:19:58,996] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:59,029] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:59,087] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:59,147] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:59,207] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:59,268] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:59,327] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:59,388] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:59,448] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:59,509] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:59,569] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:59,629] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:59,690] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:59,750] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:59,811] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:59,872] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:59,932] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:19:59,992] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:00,053] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:00,113] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:00,173] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:00,234] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:00,294] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:00,354] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:00,415] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:00,476] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:00,536] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:00,597] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:00,657] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:00,718] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:00,779] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:00,840] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:00,901] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:00,962] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:01,023] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:01,084] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:10,354] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:10,377] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:10,409] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:10,445] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:10,481] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:10,519] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:10,557] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:10,594] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:10,634] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:10,674] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:10,712] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:10,750] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:10,796] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:10,850] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:10,914] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:10,981] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:11,034] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:11,091] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:11,145] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:11,203] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:11,262] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:11,314] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:11,368] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:11,425] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:11,481] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:11,533] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:11,588] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:11,644] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:11,699] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:11,756] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:11,812] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:11,868] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:11,924] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:11,987] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:12,035] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:12,091] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:20,367] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:20,386] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:20,437] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:20,493] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:20,548] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:20,604] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:20,661] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:20,716] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:20,772] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:20,830] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:20,887] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:20,945] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:21,003] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:21,060] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:21,117] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:21,174] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:21,232] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:21,290] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:21,349] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:21,407] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:21,466] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:21,525] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:21,585] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:21,644] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:21,704] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:21,762] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:21,822] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:21,882] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:21,942] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:22,001] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:22,060] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:22,120] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:22,179] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:22,239] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:22,299] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:22,358] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:31,810] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:31,830] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:31,881] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:31,937] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:31,994] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:32,440] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:32,491] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:32,547] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:32,602] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:32,658] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:32,714] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:32,771] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:32,829] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:32,888] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:32,945] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:33,004] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:33,065] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:33,124] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:33,182] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:33,306] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:33,360] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:33,417] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:33,472] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:33,528] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:33,585] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:33,640] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:33,697] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:33,754] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:33,814] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:34,000] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:34,055] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:34,115] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:34,175] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:34,233] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:34,290] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:34,346] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:43,824] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:43,844] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:43,888] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:43,938] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:43,986] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:44,034] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:44,084] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:44,134] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:44,186] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:44,237] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:44,289] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:44,338] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:44,388] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:44,438] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:44,491] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:44,544] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:44,595] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:44,648] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:44,697] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:44,747] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:44,796] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:44,849] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:44,909] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:44,961] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:45,020] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:45,072] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:45,129] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:45,187] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:45,247] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:45,306] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:45,366] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:45,425] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:45,484] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:45,545] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:45,603] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:45,663] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:54,283] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:54,303] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:54,351] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:54,405] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:54,456] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:54,508] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:54,562] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:54,616] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:54,672] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:54,725] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:54,777] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:54,832] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:54,889] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:54,945] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:54,998] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:55,051] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:55,105] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:55,160] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:55,216] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:55,282] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:55,349] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:55,417] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:55,482] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:55,548] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:55,616] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:55,682] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:55,749] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:55,816] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:55,883] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:55,950] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:56,019] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:56,084] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:56,151] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:56,218] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:56,284] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:20:56,350] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:07,273] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:07,293] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:07,336] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:07,383] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:07,430] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:07,478] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:07,526] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:07,573] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:07,622] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:07,671] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:07,719] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:07,767] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:07,816] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:07,864] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:07,914] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:07,963] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:08,013] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:08,064] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:08,115] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:08,163] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:08,211] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:08,266] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:08,314] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:08,362] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:08,424] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:08,478] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:08,533] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:08,593] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:08,648] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:08,710] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:08,766] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:08,823] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:08,877] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:08,933] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:08,989] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:09,046] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:17,838] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:17,857] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:17,911] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:17,970] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:18,029] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:18,089] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:18,148] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:18,208] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:18,266] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:18,326] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:18,386] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:18,447] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:18,511] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:18,571] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:18,632] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:18,694] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:18,755] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:18,816] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:18,877] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:18,940] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:19,001] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:19,063] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:19,124] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:19,184] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:19,245] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:19,306] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:19,366] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:19,427] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:19,488] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:19,549] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:19,611] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:19,671] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:19,732] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:19,793] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:19,855] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:19,913] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:29,406] [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
28%|██▊ | 8/29 [12:19<32:02, 91.53s/it] {'loss': '0.7641', 'grad_norm': '3.037', 'learning_rate': '9.83e-06', 'ppl': '2.147', 'memory/max_active (GiB)': '86.87', 'memory/max_allocated (GiB)': '86.87', 'memory/device_reserved (GiB)': '92.9', 'tokens/train_per_sec_per_gpu': '48.91', 'tokens/total': 6914432, 'tokens/trainable': 1319202, 'epoch': '0.8533'}
28%|██▊ | 8/29 [12:19<32:02, 91.53s/it][2026-04-22 17:21:29,434] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:29,463] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:29,517] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:29,570] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:29,622] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:29,676] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:29,728] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:29,781] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:29,835] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:29,888] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:29,942] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:29,997] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:30,052] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:30,105] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:30,160] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:30,215] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:30,269] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:30,322] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:30,376] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:30,429] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:30,483] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:30,537] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:30,591] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:30,644] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:30,698] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:30,753] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:30,807] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:30,860] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:30,915] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:30,969] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:31,023] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:31,077] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:31,131] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:31,185] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:31,239] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:31,295] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:38,792] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:38,814] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:38,863] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:38,919] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:38,976] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:39,033] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:39,090] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:39,147] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:39,206] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:39,261] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:39,318] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:39,378] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:39,437] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:39,498] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:39,558] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:39,618] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:39,678] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:39,739] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:39,800] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:39,859] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:39,919] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:39,979] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:40,039] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:40,100] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:40,160] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:40,219] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:40,275] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:40,333] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:40,390] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:40,447] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:40,505] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:40,563] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:40,622] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:41,119] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:41,144] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:41,188] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:50,905] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:50,925] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:50,987] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:51,054] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:51,123] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:51,189] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:51,256] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:51,323] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:51,391] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:51,460] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:51,529] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:51,597] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:51,665] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:51,732] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:51,801] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:51,869] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:51,938] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:52,006] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:52,073] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:52,140] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:52,207] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:52,274] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:52,341] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:52,409] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:52,476] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:52,543] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:52,610] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:52,677] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:52,744] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:52,811] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:52,878] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:52,945] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:53,013] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:53,080] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:53,147] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:21:53,213] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:04,042] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:04,063] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:04,116] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:04,174] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:04,233] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:04,293] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:04,352] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:04,411] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:04,469] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:04,528] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:04,588] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:04,649] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:04,711] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:04,774] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:04,837] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:04,900] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:05,009] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:05,063] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:05,121] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:05,181] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:05,242] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:05,300] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:05,359] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:05,774] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:05,825] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:05,880] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:05,937] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:05,995] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:06,052] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:06,108] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:06,163] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:06,221] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:06,276] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:06,336] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:06,396] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:06,452] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:16,449] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:16,469] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:16,497] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:16,526] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:16,557] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:16,587] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:16,617] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:16,651] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:16,710] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:16,778] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:16,845] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:16,922] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:17,308] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:17,374] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:17,440] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:17,506] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:17,572] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:17,639] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:17,706] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:17,772] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:17,840] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:17,907] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:17,974] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:18,042] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:18,108] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:18,176] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:18,243] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:18,309] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:18,377] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:18,444] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:18,511] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:18,579] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:18,646] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:18,712] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:18,780] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:18,847] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:28,634] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:28,654] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:28,686] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:28,719] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:28,754] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:28,787] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:28,823] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:28,857] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:28,898] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:28,967] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:29,033] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:29,140] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:29,246] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:29,318] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:29,387] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:29,452] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:29,513] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:29,577] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:29,643] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:29,714] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:29,767] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:29,832] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:29,923] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:29,955] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:30,030] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:30,094] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:30,165] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:30,232] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:30,300] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:30,368] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:30,435] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:30,503] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:30,573] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:30,644] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:30,713] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:30,782] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:42,221] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:42,242] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:42,279] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:42,317] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:42,357] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:42,396] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:42,434] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:42,476] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:42,515] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:42,556] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:42,612] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:42,680] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:42,744] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:42,808] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:42,874] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:42,940] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:43,006] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:43,092] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:43,156] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:43,223] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:43,287] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:43,358] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:43,423] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:43,487] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:43,551] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:43,620] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:43,682] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:43,747] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:43,814] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:43,879] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:43,942] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:44,008] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:44,074] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:44,143] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:44,206] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:44,272] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:54,547] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:54,566] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:54,618] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:54,673] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:54,731] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:54,788] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:54,845] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:54,900] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:54,959] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:55,018] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:55,076] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:55,137] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:55,198] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:55,258] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:55,314] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:55,370] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:55,427] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:55,485] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:55,545] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:55,604] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:55,662] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:55,721] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:55,781] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:55,836] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:55,893] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:55,950] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:56,009] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:56,068] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:56,129] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:56,188] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:56,250] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:56,314] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:56,379] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:56,444] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:56,510] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:22:56,576] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:23:06,768] [WARNING] [stage3.py:2497:step] 9 pytorch allocator cache flushes since last step. this happens when there is high memory pressure and is detrimental to performance. if this is happening frequently consider adjusting settings to reduce memory consumption. If you are unable to make the cache flushes go away consider adding get_accelerator().empty_cache() calls in your training loop to ensure that all ranks flush their caches at the same time
31%|███ | 9/29 [13:56<31:07, 93.35s/it] {'loss': '0.6519', 'grad_norm': '1.971', 'learning_rate': '9.619e-06', 'ppl': '1.919', 'memory/max_active (GiB)': '91.6', 'memory/max_allocated (GiB)': '91.6', 'memory/device_reserved (GiB)': '92.9', 'tokens/train_per_sec_per_gpu': '53.16', 'tokens/total': 7778432, 'tokens/trainable': 1487467, 'epoch': '0.96'}
31%|███ | 9/29 [13:56<31:07, 93.35s/it][2026-04-22 17:23:06,812] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:23:06,845] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:23:06,906] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:23:06,965] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:23:07,023] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:23:07,084] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:23:07,144] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:23:07,204] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:23:07,264] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:23:07,323] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:23:07,383] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:23:07,443] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:23:07,504] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:23:07,563] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:23:07,622] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:23:07,682] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:23:07,743] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:23:07,804] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:23:07,863] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:23:07,922] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:23:07,982] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:23:08,043] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:23:08,104] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:23:08,164] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:23:08,223] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:23:08,283] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:23:08,344] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:23:08,404] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:23:08,464] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:23:08,524] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:23:08,584] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:23:08,644] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:23:08,705] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:23:08,765] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:23:08,824] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:23:08,885] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:23:17,449] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:23:17,471] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:23:17,534] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:23:17,600] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:23:17,662] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:23:17,726] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:23:17,790] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:23:17,852] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:23:17,915] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:23:17,977] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:23:18,041] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:23:18,104] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:23:18,167] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:23:18,232] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:23:18,295] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:23:18,361] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:23:18,422] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:23:18,485] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:23:18,547] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:23:18,610] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:23:18,673] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:23:18,737] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:23:18,801] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:23:18,865] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:23:18,930] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:23:18,992] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:23:19,057] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:23:19,120] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:23:19,182] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:23:19,245] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:23:19,308] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:23:19,372] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:23:19,435] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:23:19,502] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:23:19,564] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:23:19,626] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:23:28,878] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:23:28,899] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:23:28,947] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:23:28,999] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:23:29,051] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:23:29,103] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:23:29,157] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:23:29,212] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:23:29,266] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:23:29,322] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:23:29,374] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:23:29,426] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:23:29,481] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:23:29,535] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:23:29,588] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:23:29,642] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:23:29,693] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:23:29,747] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:23:29,803] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:23:29,860] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:23:29,937] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:23:30,000] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:23:30,058] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:23:30,120] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:23:30,186] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:23:30,250] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:23:30,314] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:23:30,380] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:23:30,445] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:23:30,510] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:23:30,576] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:23:30,642] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:23:30,707] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:23:30,774] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:23:30,837] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:23:30,903] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:23:41,039] [WARNING] [stage3.py:2497:step] 3 pytorch allocator cache flushes since last step. this happens when there is high memory pressure and is detrimental to performance. if this is happening frequently consider adjusting settings to reduce memory consumption. If you are unable to make the cache flushes go away consider adding get_accelerator().empty_cache() calls in your training loop to ensure that all ranks flush their caches at the same time
34%|███▍ | 10/29 [14:30<23:47, 75.11s/it] {'loss': '0.6358', 'grad_norm': '1.466', 'learning_rate': '9.33e-06', 'ppl': '1.889', 'memory/max_active (GiB)': '89.82', 'memory/max_allocated (GiB)': '89.82', 'memory/device_reserved (GiB)': '91.57', 'tokens/train_per_sec_per_gpu': '158.1', 'tokens/total': 8081344, 'tokens/trainable': 1547775, 'epoch': '1'}
34%|███▍ | 10/29 [14:30<23:47, 75.11s/it][2026-04-22 17:23:43,393] [INFO] [axolotl.core.trainers.base._save:741] [PID:1024775] Saving model checkpoint to /e/data1/datasets/playground/ot-baf/checkpoints/sera-v3-1000-axolotl__Qwen3-8B/checkpoint-10
Writing model shards: 0%| | 0/1 [00:00<?, ?it/s]
Writing model shards: 100%|██████████| 1/1 [00:06<00:00, 6.92s/it] Writing model shards: 100%|██████████| 1/1 [00:06<00:00, 6.92s/it]
[2026-04-22 17:24:14,592] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:24:14,644] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:24:14,705] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:24:14,766] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:24:14,831] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:24:14,896] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:24:14,960] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:24:15,024] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:24:15,110] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:24:15,212] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:24:15,357] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:24:15,406] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:24:15,493] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:24:15,556] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:24:15,619] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:24:15,751] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:24:15,834] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:24:15,923] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:24:15,987] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:24:16,051] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:24:16,116] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:24:16,614] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:24:16,675] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:24:16,737] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:24:16,800] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:24:16,864] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:24:16,928] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:24:16,992] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:24:17,057] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:24:17,121] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:24:17,185] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:24:17,251] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:24:17,317] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:24:17,382] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:24:17,888] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:24:17,941] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:24:27,187] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:24:27,206] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:24:27,257] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:24:27,312] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:24:27,365] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:24:27,423] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:24:27,477] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:24:27,534] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:24:27,594] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:24:27,654] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:24:27,714] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:24:27,771] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:24:27,829] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:24:27,884] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:24:27,943] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:24:28,002] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:24:28,060] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:24:28,120] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:24:28,177] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:24:28,623] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:24:28,686] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:24:28,752] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:24:28,818] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:24:28,883] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:24:28,949] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:24:29,014] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:24:29,332] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:24:29,385] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:24:29,440] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:24:29,495] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:24:29,549] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:24:29,607] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:24:29,664] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:24:29,723] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:24:29,781] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:24:29,840] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:24:40,700] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:24:40,720] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:24:40,773] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:24:40,831] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:24:40,890] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:24:40,950] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:24:41,009] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:24:41,068] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:24:41,127] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:24:41,186] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:24:41,245] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:24:41,305] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:24:41,364] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:24:41,425] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:24:41,487] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:24:41,550] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:24:41,613] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:24:41,675] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:24:41,738] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:24:41,801] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:24:41,862] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:24:41,924] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:24:41,987] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:24:42,051] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:24:42,114] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:24:42,176] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:24:42,239] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:24:42,302] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:24:42,363] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:24:42,426] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:24:42,489] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:24:42,553] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:24:42,617] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:24:42,680] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:24:42,741] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:24:42,806] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:24:53,200] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:24:53,221] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:24:53,256] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:24:53,294] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:24:53,334] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:24:53,374] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:24:53,413] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:24:53,453] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:24:53,494] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:24:53,535] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:24:53,573] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:24:53,614] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:24:53,673] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:24:53,732] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:24:53,792] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:24:53,851] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:24:53,911] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:24:53,973] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:24:54,031] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:24:54,090] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:24:54,150] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:24:54,210] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:24:54,272] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:24:54,331] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:24:54,390] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:24:54,450] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:24:54,510] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:24:54,570] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:24:54,630] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:24:54,690] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:24:54,750] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:24:54,811] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:24:54,873] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:24:54,931] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:24:54,990] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:24:55,052] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:04,222] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:04,242] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:04,298] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:04,359] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:04,419] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:04,479] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:04,540] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:04,601] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:04,661] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:04,723] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:04,783] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:04,845] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:04,907] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:04,968] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:05,032] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:05,096] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:05,158] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:05,222] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:05,285] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:05,349] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:05,412] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:05,477] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:05,540] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:05,605] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:05,668] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:05,733] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:05,798] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:05,864] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:05,928] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:05,992] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:06,058] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:06,121] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:06,185] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:06,250] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:06,315] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:06,378] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:16,396] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:16,420] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:16,458] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:16,498] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:16,539] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:16,580] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:16,622] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:16,665] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:16,706] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:16,747] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:16,791] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:16,859] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:16,924] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:16,992] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:17,074] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:17,132] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:17,194] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:17,260] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:17,328] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:17,394] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:17,477] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:17,543] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:17,602] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:17,663] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:17,730] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:17,798] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:17,865] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:17,933] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:18,000] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:18,066] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:18,133] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:18,201] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:18,267] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:18,335] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:18,402] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:18,468] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:28,585] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:28,605] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:28,665] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:28,726] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:28,790] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:28,854] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:28,918] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:28,979] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:29,041] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:29,105] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:29,167] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:29,231] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:29,295] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:29,358] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:29,420] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:29,483] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:29,548] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:29,611] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:29,677] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:29,739] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:29,802] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:29,864] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:29,928] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:29,992] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:30,055] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:30,118] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:30,180] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:30,244] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:30,308] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:30,371] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:30,436] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:30,500] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:30,563] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:30,627] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:30,692] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:30,754] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:40,128] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:40,149] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:40,192] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:40,239] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:40,285] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:40,334] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:40,382] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:40,429] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:40,477] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:40,525] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:40,574] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:40,623] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:40,671] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:40,718] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:40,771] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:40,835] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:40,892] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:40,951] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:41,016] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:41,078] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:41,141] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:41,206] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:41,282] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:41,347] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:41,402] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:41,460] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:41,524] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:41,589] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:41,651] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:41,714] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:41,778] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:41,841] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:41,905] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:41,968] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:42,031] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:42,095] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:51,662] [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
38%|███▊ | 11/29 [16:41<27:37, 92.10s/it] {'loss': '0.5897', 'grad_norm': '1.307', 'learning_rate': '8.967e-06', 'ppl': '1.803', 'memory/max_active (GiB)': '89.7', 'memory/max_allocated (GiB)': '89.7', 'memory/device_reserved (GiB)': '92.88', 'tokens/train_per_sec_per_gpu': '59.97', 'tokens/total': 8941440, 'tokens/trainable': 1714754, 'epoch': '1.107'}
38%|███▊ | 11/29 [16:41<27:37, 92.10s/it][2026-04-22 17:25:51,697] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:51,747] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:51,807] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:51,867] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:51,929] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:51,991] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:52,054] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:52,116] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:52,179] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:52,241] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:52,304] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:52,368] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:52,429] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:52,491] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:52,554] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:52,616] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:52,679] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:52,741] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:52,803] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:52,866] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:52,929] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:52,991] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:53,054] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:53,116] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:53,179] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:53,242] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:53,305] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:53,368] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:53,431] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:53,493] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:53,556] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:53,619] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:53,681] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:53,745] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:53,811] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:25:53,873] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:02,846] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:02,868] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:02,918] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:02,973] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:03,028] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:03,081] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:03,135] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:03,193] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:03,251] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:03,310] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:03,367] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:03,423] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:03,477] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:03,534] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:03,593] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:03,652] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:03,710] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:03,767] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:03,823] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:04,312] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:04,360] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:04,412] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:04,467] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:04,521] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:04,574] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:04,629] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:04,683] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:04,738] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:04,793] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:04,847] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:04,904] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:04,958] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:05,012] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:05,067] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:05,123] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:05,178] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:15,998] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:16,020] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:16,065] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:16,115] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:16,164] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:16,215] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:16,268] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:16,320] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:16,562] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:16,609] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:16,658] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:16,705] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:16,755] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:16,804] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:16,853] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:16,902] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:16,949] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:17,001] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:17,052] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:17,105] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:17,158] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:17,208] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:17,258] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:17,310] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:17,363] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:17,420] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:17,482] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:17,543] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:17,605] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:17,667] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:17,730] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:17,791] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:17,854] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:17,916] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:17,978] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:18,040] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:27,041] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:27,062] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:27,117] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:27,177] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:27,238] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:27,298] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:27,359] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:27,420] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:27,481] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:27,542] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:27,604] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:27,667] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:27,732] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:27,794] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:27,857] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:27,920] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:27,982] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:28,044] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:28,106] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:28,167] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:28,229] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:28,291] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:28,354] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:28,417] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:28,478] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:28,540] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:28,602] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:28,664] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:28,726] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:28,789] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:28,852] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:28,914] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:28,976] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:29,039] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:29,100] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:29,161] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:38,712] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:38,733] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:38,779] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:38,827] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:38,878] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:38,926] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:38,976] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:39,025] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:39,076] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:39,125] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:39,176] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:39,226] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:39,278] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:39,329] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:39,381] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:39,433] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:39,484] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:39,536] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:39,587] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:39,638] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:39,689] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:39,741] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:39,791] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:39,842] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:39,893] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:39,943] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:39,995] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:40,045] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:40,096] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:40,147] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:40,198] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:40,249] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:40,300] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:40,351] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:40,402] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:40,450] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:47,859] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:47,880] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:47,935] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:47,996] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:48,056] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:48,116] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:48,176] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:48,236] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:48,297] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:48,359] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:48,421] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:48,484] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:48,549] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:48,612] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:48,675] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:48,737] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:48,800] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:48,861] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:48,924] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:48,986] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:49,050] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:49,115] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:49,178] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:49,241] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:49,304] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:49,366] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:49,428] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:49,491] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:49,554] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:49,616] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:49,678] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:49,739] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:49,803] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:49,864] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:49,925] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:26:49,986] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:00,123] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:00,145] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:00,200] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:00,259] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:00,319] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:00,379] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:00,440] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:00,499] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:00,559] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:00,621] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:00,686] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:00,751] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:00,815] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:00,878] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:00,940] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:01,003] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:01,065] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:01,128] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:01,191] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:01,253] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:01,317] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:01,381] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:01,444] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:01,509] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:01,571] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:01,634] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:01,698] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:01,761] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:01,824] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:01,888] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:01,951] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:02,017] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:02,080] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:02,147] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:02,208] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:02,272] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:12,886] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:12,908] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:12,965] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:13,026] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:13,088] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:13,150] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:13,212] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:13,272] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:13,335] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:13,396] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:13,457] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:13,519] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:13,580] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:13,643] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:13,705] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:13,765] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:13,827] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:13,889] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:13,952] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:14,013] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:14,074] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:14,135] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:14,197] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:14,258] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:14,319] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:14,381] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:14,443] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:14,504] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:14,566] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:14,628] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:14,690] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:14,752] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:14,814] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:14,876] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:14,938] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:14,998] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:23,668] [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
41%|████▏ | 12/29 [18:13<26:05, 92.07s/it] {'loss': '0.5733', 'grad_norm': '1.021', 'learning_rate': '8.536e-06', 'ppl': '1.774', 'memory/max_active (GiB)': '88.64', 'memory/max_allocated (GiB)': '88.64', 'memory/device_reserved (GiB)': '92.89', 'tokens/train_per_sec_per_gpu': '40.95', 'tokens/total': 9790080, 'tokens/trainable': 1883691, 'epoch': '1.213'}
41%|████▏ | 12/29 [18:13<26:05, 92.07s/it][2026-04-22 17:27:23,700] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:23,735] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:23,797] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:23,860] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:23,922] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:23,985] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:24,047] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:24,108] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:24,171] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:24,235] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:24,299] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:24,363] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:24,426] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:24,488] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:24,551] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:24,613] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:24,677] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:24,741] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:24,804] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:24,867] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:24,930] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:24,994] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:25,058] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:25,120] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:25,183] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:25,246] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:25,309] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:25,372] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:25,436] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:25,500] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:25,564] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:25,627] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:25,690] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:25,753] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:25,817] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:25,881] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:35,468] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:35,488] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:35,534] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:35,585] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:35,637] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:35,685] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:35,739] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:35,792] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:35,846] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:35,900] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:35,949] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:36,000] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:36,054] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:36,106] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:36,160] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:36,215] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:36,266] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:36,319] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:36,373] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:36,428] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:36,486] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:36,551] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:36,614] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:36,677] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:36,742] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:36,805] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:37,082] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:37,131] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:37,182] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:37,234] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:37,285] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:37,341] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:37,392] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:37,444] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:37,493] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:37,546] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:46,646] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:46,666] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:46,714] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:46,767] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:46,821] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:46,875] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:46,928] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:46,982] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:47,039] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:47,096] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:47,152] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:47,209] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:47,264] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:47,321] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:47,377] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:47,436] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:47,792] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:47,851] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:47,915] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:47,975] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:48,036] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:48,097] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:48,376] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:48,427] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:48,486] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:48,550] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:48,602] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:48,658] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:48,712] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:48,767] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:48,824] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:48,880] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:48,940] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:48,996] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:49,053] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:49,108] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:59,478] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:59,498] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:59,555] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:59,614] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:59,676] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:59,737] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:59,799] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:59,860] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:59,921] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:27:59,982] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:00,047] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:00,111] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:00,174] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:00,237] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:00,299] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:00,362] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:00,425] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:00,490] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:00,554] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:00,618] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:00,681] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:00,745] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:00,808] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:00,872] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:00,935] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:00,998] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:01,060] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:01,123] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:01,186] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:01,250] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:01,313] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:01,376] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:01,439] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:01,502] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:01,565] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:01,626] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:11,449] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:11,470] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:11,533] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:11,603] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:11,671] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:11,740] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:11,807] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:11,875] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:11,942] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:12,011] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:12,080] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:12,147] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:12,215] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:12,282] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:12,350] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:12,418] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:12,486] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:12,554] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:12,621] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:12,689] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:12,757] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:12,824] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:12,892] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:12,959] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:13,026] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:13,096] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:13,165] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:13,233] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:13,302] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:13,370] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:13,438] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:13,505] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:13,573] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:13,641] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:13,710] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:13,775] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:24,489] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:24,511] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:24,559] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:24,611] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:24,663] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:24,716] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:24,769] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:24,823] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:24,878] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:24,933] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:24,988] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:25,041] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:25,093] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:25,146] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:25,201] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:25,253] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:25,305] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:25,362] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:25,462] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:25,528] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:25,590] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:25,649] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:25,700] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:25,775] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:25,825] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:25,902] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:25,965] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:26,024] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:26,086] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:26,152] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:26,211] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:26,274] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:26,341] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:26,395] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:26,469] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:26,521] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:37,136] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:37,157] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:37,219] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:37,284] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:37,350] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:37,417] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:37,484] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:37,553] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:37,621] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:37,690] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:37,759] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:37,827] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:37,896] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:37,963] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:38,030] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:38,098] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:38,164] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:38,232] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:38,299] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:38,365] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:38,432] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:38,499] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:38,566] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:38,635] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:38,702] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:38,769] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:38,836] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:38,902] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:38,968] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:39,036] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:39,102] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:39,169] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:39,236] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:39,304] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:39,371] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:39,435] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:49,928] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:49,950] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:50,012] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:50,078] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:50,143] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:50,209] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:50,277] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:50,345] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:50,414] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:50,482] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:50,550] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:50,619] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:50,686] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:50,754] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:50,821] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:50,888] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:50,956] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:51,023] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:51,090] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:51,157] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:51,224] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:51,291] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:51,358] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:51,425] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:51,493] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:51,559] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:51,626] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:51,693] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:51,759] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:51,826] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:51,894] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:51,961] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:52,028] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:52,117] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:52,163] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:28:52,227] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:03,057] [WARNING] [stage3.py:2497:step] 14 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
45%|████▍ | 13/29 [19:52<25:08, 94.29s/it] {'loss': '0.5483', 'grad_norm': '0.8327', 'learning_rate': '8.044e-06', 'ppl': '1.73', 'memory/max_active (GiB)': '91.95', 'memory/max_allocated (GiB)': '91.95', 'memory/device_reserved (GiB)': '92.87', 'tokens/train_per_sec_per_gpu': '51.91', 'tokens/total': 10687872, 'tokens/trainable': 2060672, 'epoch': '1.32'}
45%|████▍ | 13/29 [19:52<25:08, 94.29s/it][2026-04-22 17:29:03,091] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:03,128] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:03,197] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:03,264] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:03,330] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:03,398] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:03,465] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:03,533] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:03,601] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:03,668] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:03,737] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:03,805] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:03,873] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:03,940] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:04,009] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:04,077] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:04,145] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:04,214] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:04,281] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:04,350] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:04,418] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:04,486] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:04,555] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:04,622] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:04,689] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:04,757] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:04,824] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:04,893] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:04,961] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:05,029] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:05,098] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:05,166] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:05,234] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:05,302] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:05,370] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:05,439] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:15,783] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:15,807] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:15,851] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:15,901] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:15,951] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:16,002] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:16,055] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:16,109] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:16,159] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:16,211] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:16,262] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:16,316] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:16,371] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:16,426] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:16,477] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:16,528] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:16,587] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:16,645] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:16,704] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:16,765] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:16,829] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:16,894] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:16,961] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:17,026] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:17,091] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:17,156] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:17,240] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:17,299] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:17,358] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:17,422] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:17,487] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:17,552] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:17,619] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:18,054] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:18,090] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:18,121] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:28,383] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:28,405] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:28,439] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:28,476] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:28,513] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:28,550] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:28,588] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:28,627] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:28,666] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:28,987] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:29,023] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:29,061] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:29,098] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:29,136] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:29,183] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:29,219] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:29,255] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:29,292] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:29,329] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:29,365] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:29,404] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:29,978] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:30,012] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:30,049] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:30,086] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:30,122] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:30,160] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:30,199] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:30,247] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:30,298] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:30,349] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:30,400] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:30,452] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:30,505] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:30,553] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:30,607] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:37,987] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:38,008] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:38,064] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:38,128] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:38,190] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:38,253] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:38,314] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:38,375] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:38,438] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:38,501] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:38,563] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:38,627] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:38,691] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:38,755] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:38,818] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:38,882] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:38,946] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:39,009] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:39,073] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:39,138] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:39,202] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:39,267] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:39,331] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:39,396] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:39,461] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:39,528] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:39,594] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:39,659] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:39,725] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:39,792] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:39,858] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:39,924] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:39,990] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:40,056] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:40,122] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:40,187] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:50,179] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:50,201] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:50,240] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:50,284] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:50,327] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:50,371] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:50,416] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:50,460] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:50,504] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:50,550] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:50,594] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:50,637] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:50,681] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:50,727] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:50,788] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:50,849] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:50,913] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:50,973] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:51,034] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:51,097] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:51,159] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:51,221] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:51,300] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:51,361] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:51,440] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:51,543] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:51,648] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:51,750] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:51,839] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:51,880] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:51,926] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:51,988] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:52,066] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:52,155] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:52,195] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:29:52,238] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:02,076] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:02,096] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:02,141] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:02,189] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:02,237] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:02,285] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:02,336] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:02,386] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:02,433] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:02,481] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:02,532] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:02,582] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:02,634] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:02,682] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:02,732] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:02,783] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:02,843] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:02,908] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:02,972] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:03,035] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:03,098] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:03,162] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:03,226] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:03,290] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:03,354] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:03,417] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:03,481] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:03,545] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:03,610] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:03,674] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:03,738] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:03,802] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:03,867] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:03,931] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:03,994] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:04,057] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:13,113] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:13,134] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:13,171] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:13,209] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:13,249] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:13,290] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:13,332] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:13,371] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:13,411] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:13,452] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:13,492] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:13,532] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:13,582] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:13,655] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:13,712] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:13,811] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:13,906] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:13,943] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:13,985] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:14,033] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:14,074] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:14,142] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:14,202] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:14,246] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:14,319] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:14,381] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:14,439] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:14,499] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:14,557] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:14,616] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:14,681] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:14,740] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:14,799] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:14,861] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:14,920] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:14,978] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:24,707] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:24,728] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:24,769] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:24,813] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:24,856] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:24,904] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:24,951] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:24,995] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:25,040] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:25,087] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:25,132] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:25,177] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:25,239] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:25,305] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:25,369] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:25,432] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:25,497] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:25,558] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:25,621] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:25,685] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:25,748] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:25,814] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:25,894] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:25,957] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:26,024] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:26,085] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:26,144] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:26,205] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:26,270] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:26,335] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:26,400] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:26,466] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:26,531] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:26,595] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:26,660] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:26,725] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:37,635] [WARNING] [stage3.py:2497:step] 5 pytorch allocator cache flushes since last step. this happens when there is high memory pressure and is detrimental to performance. if this is happening frequently consider adjusting settings to reduce memory consumption. If you are unable to make the cache flushes go away consider adding get_accelerator().empty_cache() calls in your training loop to ensure that all ranks flush their caches at the same time
48%|████▊ | 14/29 [21:27<23:35, 94.38s/it] {'loss': '0.5367', 'grad_norm': '0.749', 'learning_rate': '7.5e-06', 'ppl': '1.71', 'memory/max_active (GiB)': '90.19', 'memory/max_allocated (GiB)': '90.19', 'memory/device_reserved (GiB)': '92.75', 'tokens/train_per_sec_per_gpu': '58.28', 'tokens/total': 11546496, 'tokens/trainable': 2229334, 'epoch': '1.427'}
48%|████▊ | 14/29 [21:27<23:35, 94.38s/it][2026-04-22 17:30:37,668] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:37,705] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:37,770] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:37,835] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:37,900] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:37,965] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:38,028] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:38,091] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:38,155] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:38,220] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:38,284] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:38,350] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:38,415] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:38,479] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:38,544] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:38,610] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:38,675] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:38,739] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:38,805] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:38,871] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:38,936] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:39,000] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:39,066] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:39,131] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:39,196] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:39,262] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:39,328] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:39,393] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:39,459] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:39,524] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:39,589] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:39,654] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:39,719] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:39,785] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:39,850] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:39,916] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:49,900] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:49,926] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:49,965] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:50,011] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:50,058] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:50,106] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:50,154] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:50,202] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:50,253] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:50,300] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:50,349] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:50,396] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:50,446] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:50,496] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:50,543] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:50,593] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:50,639] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:50,690] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:50,741] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:50,798] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:50,856] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:50,914] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:50,971] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:51,031] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:51,090] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:51,150] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:51,210] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:51,269] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:51,329] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:51,389] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:51,449] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:51,508] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:51,568] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:51,633] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:51,685] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:30:51,745] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:01,806] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:01,828] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:01,855] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:01,884] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:01,914] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:01,942] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:01,972] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:02,004] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:02,060] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:02,114] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:02,176] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:02,238] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:02,299] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:02,362] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:02,440] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:02,493] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:02,552] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:02,614] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:02,676] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:02,738] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:02,800] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:02,878] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:02,932] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:02,989] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:03,052] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:03,114] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:03,177] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:03,467] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:03,513] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:03,577] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:03,634] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:03,667] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:03,715] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:03,776] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:04,092] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:04,133] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:13,394] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:13,415] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:13,447] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:13,481] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:13,517] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:13,553] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:13,588] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:13,624] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:13,659] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:13,710] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:13,791] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:13,852] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:13,910] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:13,973] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:14,032] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:14,348] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:14,394] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:14,456] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:14,521] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:14,580] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:14,623] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:14,677] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:14,731] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:14,764] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:14,813] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:14,847] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:14,881] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:14,924] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:14,989] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:15,060] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:15,121] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:15,201] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:15,265] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:15,324] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:15,384] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:15,457] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:25,658] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:25,677] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:25,725] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:25,777] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:25,829] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:25,879] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:25,933] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:25,986] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:26,039] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:26,093] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:26,145] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:26,196] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:26,248] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:26,300] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:26,352] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:26,405] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:26,457] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:26,510] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:26,564] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:26,617] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:26,671] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:26,725] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:26,777] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:26,830] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:26,882] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:26,935] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:26,987] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:27,039] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:27,091] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:27,143] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:27,195] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:27,247] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:27,299] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:27,350] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:27,403] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:27,453] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:35,154] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:35,175] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:35,225] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:35,277] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:35,330] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:35,383] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:35,436] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:35,488] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:35,542] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:35,597] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:35,652] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:35,709] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:35,766] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:35,823] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:35,881] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:35,935] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:35,988] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:36,040] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:36,095] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:36,150] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:36,205] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:36,261] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:36,317] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:36,374] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:36,431] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:36,486] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:36,539] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:36,592] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:36,645] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:36,700] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:36,755] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:36,812] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:36,868] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:36,926] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:36,982] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:37,044] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:46,096] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:46,117] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:46,172] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:46,231] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:46,290] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:46,349] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:46,408] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:46,468] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:46,528] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:46,588] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:46,648] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:46,709] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:46,769] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:46,829] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:46,889] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:46,949] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:47,009] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:47,069] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:47,129] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:47,189] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:47,249] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:47,309] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:47,369] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:47,429] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:47,489] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:47,549] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:47,609] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:47,669] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:47,729] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:47,789] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:47,849] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:47,910] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:47,970] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:48,030] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:48,091] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:48,149] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:56,464] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:56,485] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:56,534] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:56,587] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:56,640] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:56,694] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:56,748] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:56,801] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:56,854] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:56,909] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:56,964] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:57,022] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:57,080] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:57,139] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:57,197] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:57,252] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:57,309] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:57,365] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:57,420] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:57,475] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:57,529] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:57,584] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:57,641] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:57,697] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:57,756] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:57,812] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:57,869] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:57,926] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:57,987] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:58,039] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:58,093] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:58,147] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:58,202] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:58,259] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:58,316] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:31:58,374] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:08,578] [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
52%|█████▏ | 15/29 [22:58<21:46, 93.34s/it] {'loss': '0.5115', 'grad_norm': '0.6997', 'learning_rate': '6.913e-06', 'ppl': '1.668', 'memory/max_active (GiB)': '86.75', 'memory/max_allocated (GiB)': '86.75', 'memory/device_reserved (GiB)': '92.75', 'tokens/train_per_sec_per_gpu': '61.9', 'tokens/total': 12386176, 'tokens/trainable': 2392568, 'epoch': '1.533'}
52%|█████▏ | 15/29 [22:58<21:46, 93.34s/it][2026-04-22 17:32:08,611] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:08,648] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:08,707] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:08,772] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:08,835] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:08,900] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:08,965] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:09,029] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:09,092] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:09,157] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:09,222] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:09,287] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:09,353] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:09,417] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:09,482] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:09,548] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:09,613] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:09,678] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:09,743] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:09,808] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:09,873] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:09,938] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:10,003] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:10,068] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:10,133] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:10,198] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:10,263] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:10,328] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:10,393] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:10,458] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:10,522] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:10,588] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:10,654] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:10,718] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:10,783] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:10,850] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:20,400] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:20,424] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:20,478] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:20,542] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:20,600] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:20,662] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:20,723] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:20,783] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:20,844] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:20,904] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:20,964] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:21,024] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:21,087] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:21,148] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:21,208] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:21,268] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:21,328] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:21,388] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:21,448] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:21,508] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:21,568] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:21,628] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:21,689] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:21,750] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:21,809] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:21,869] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:21,929] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:21,989] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:22,049] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:22,109] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:22,170] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:22,229] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:22,290] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:22,595] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:22,622] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:22,671] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:31,044] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:31,066] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:31,108] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:31,153] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:31,198] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:31,245] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:31,293] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:31,338] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:31,384] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:31,432] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:31,479] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:31,529] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:31,577] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:31,623] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:31,673] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:31,733] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:31,794] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:31,848] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:31,907] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:31,969] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:32,031] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:32,092] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:32,155] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:32,227] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:32,287] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:32,343] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:32,401] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:32,463] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:32,525] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:32,588] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:32,650] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:32,712] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:32,775] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:32,837] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:32,898] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:32,960] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:42,034] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:42,055] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:42,103] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:42,155] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:42,209] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:42,265] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:42,320] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:42,673] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:42,724] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:42,776] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:42,841] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:42,894] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:42,955] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:43,024] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:43,082] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:43,142] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:43,215] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:43,272] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:43,333] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:43,396] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:43,460] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:43,981] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:44,003] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:44,051] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:44,103] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:44,156] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:44,208] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:44,260] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:44,313] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:44,366] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:44,422] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:44,477] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:44,638] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:44,691] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:44,750] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:44,814] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:54,798] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:54,819] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:54,872] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:54,929] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:54,987] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:55,047] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:55,105] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:55,164] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:55,223] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:55,284] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:55,345] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:55,404] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:55,464] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:55,525] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:55,586] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:55,647] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:55,709] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:55,771] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:55,831] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:55,889] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:55,948] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:56,007] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:56,067] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:56,128] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:56,191] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:56,251] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:56,311] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:56,370] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:56,430] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:56,490] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:56,571] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:56,629] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:56,706] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:56,763] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:56,824] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:32:56,883] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:07,632] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:07,652] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:07,702] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:07,756] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:07,812] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:07,866] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:07,921] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:07,977] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:08,035] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:08,094] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:08,151] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:08,208] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:08,266] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:08,324] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:08,382] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:08,442] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:08,498] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:08,554] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:08,612] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:08,671] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:08,731] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:08,789] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:08,844] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:08,900] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:08,956] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:09,012] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:09,069] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:09,127] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:09,187] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:09,247] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:09,306] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:09,369] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:09,432] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:09,495] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:09,559] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:09,624] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:20,192] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:20,213] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:20,265] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:20,320] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:20,375] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:20,432] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:20,489] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:20,544] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:20,598] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:20,653] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:20,710] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:20,766] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:20,822] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:20,879] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:20,936] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:20,992] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:21,048] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:21,105] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:21,163] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:21,222] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:21,280] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:21,338] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:21,395] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:21,452] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:21,510] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:21,568] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:21,627] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:21,684] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:21,742] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:21,800] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:21,857] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:21,915] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:21,972] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:22,030] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:22,087] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:22,142] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:31,165] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:31,186] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:31,215] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:31,244] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:31,275] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:31,306] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:31,337] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:31,368] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:31,414] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:31,477] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:31,540] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:31,603] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:31,684] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:31,787] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:31,871] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:31,956] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:32,019] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:32,078] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:32,118] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:32,177] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:32,215] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:32,278] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:32,336] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:32,398] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:32,462] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:32,525] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:32,588] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:32,651] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:32,715] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:32,778] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:32,842] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:32,906] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:32,970] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:33,032] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:33,096] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:33,160] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:44,075] [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
55%|█████▌ | 16/29 [24:33<20:21, 93.99s/it] {'loss': '0.5235', 'grad_norm': '0.7286', 'learning_rate': '6.294e-06', 'ppl': '1.688', 'memory/max_active (GiB)': '89.84', 'memory/max_allocated (GiB)': '89.84', 'memory/device_reserved (GiB)': '92.88', 'tokens/train_per_sec_per_gpu': '61.4', 'tokens/total': 13263744, 'tokens/trainable': 2553565, 'epoch': '1.64'}
55%|█████▌ | 16/29 [24:33<20:21, 93.99s/it][2026-04-22 17:33:44,109] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:44,137] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:44,182] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:44,229] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:44,277] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:44,325] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:44,373] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:44,420] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:44,467] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:44,515] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:44,563] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:44,612] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:44,659] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:44,706] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:44,755] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:44,802] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:44,850] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:44,899] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:44,946] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:44,995] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:45,043] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:45,091] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:45,140] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:45,187] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:45,235] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:45,283] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:45,332] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:45,380] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:45,428] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:45,476] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:45,525] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:45,573] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:45,622] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:45,670] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:45,719] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:45,767] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:52,062] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:52,082] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:52,127] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:52,176] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:52,226] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:52,275] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:52,326] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:52,378] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:52,431] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:52,482] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:52,531] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:52,583] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:52,633] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:52,686] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:52,738] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:52,791] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:52,842] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:52,895] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:52,944] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:52,993] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:53,045] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:53,097] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:53,149] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:53,209] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:53,268] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:53,328] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:53,388] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:53,447] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:53,507] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:53,568] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:53,628] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:53,687] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:53,747] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:53,807] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:53,867] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:33:53,928] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:02,652] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:02,673] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:02,723] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:02,777] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:02,832] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:02,887] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:02,942] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:02,996] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:03,050] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:03,105] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:03,161] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:03,218] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:03,276] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:03,335] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:03,394] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:03,452] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:03,510] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:03,565] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:03,620] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:03,676] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:03,732] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:03,788] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:03,844] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:03,899] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:03,956] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:04,014] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:04,072] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:04,129] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:04,188] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:04,246] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:04,305] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:04,363] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:04,423] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:04,482] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:04,541] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:04,601] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:14,162] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:14,184] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:14,224] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:14,267] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:14,310] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:14,354] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:14,401] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:14,445] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:14,490] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:14,535] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:14,579] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:14,629] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:14,699] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:14,760] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:15,071] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:15,117] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:15,180] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:15,242] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:15,305] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:15,347] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:15,391] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:15,460] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:15,533] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:15,586] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:15,628] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:15,670] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:15,715] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:15,761] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:16,119] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:16,171] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:16,231] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:16,298] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:16,364] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:16,424] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:16,464] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:16,520] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:26,851] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:26,872] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:26,907] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:26,944] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:26,982] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:27,449] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:27,482] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:27,518] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:27,558] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:27,595] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:27,632] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:27,667] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:27,704] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:27,743] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:27,779] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:27,816] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:27,856] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:27,894] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:27,933] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:27,974] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:28,014] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:28,053] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:28,094] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:28,133] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:28,172] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:28,214] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:28,266] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:28,323] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:28,380] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:28,437] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:28,496] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:28,553] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:28,609] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:28,667] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:28,723] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:28,780] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:37,489] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:37,510] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:37,556] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:37,607] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:37,657] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:37,708] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:37,758] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:37,811] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:37,865] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:37,917] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:37,966] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:38,016] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:38,070] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:38,122] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:38,175] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:38,231] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:38,285] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:38,339] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:38,393] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:38,443] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:38,494] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:38,575] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:38,623] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:38,674] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:38,728] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:38,782] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:38,844] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:38,901] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:38,959] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:39,018] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:39,079] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:39,138] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:39,198] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:39,259] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:39,319] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:39,381] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:48,979] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:49,000] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:49,043] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:49,087] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:49,130] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:49,176] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:49,222] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:49,267] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:49,313] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:49,361] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:49,407] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:49,453] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:49,501] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:49,547] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:49,594] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:49,642] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:49,688] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:49,734] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:49,782] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:49,830] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:49,877] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:49,926] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:49,972] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:50,019] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:50,067] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:50,113] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:50,160] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:50,208] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:50,255] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:50,303] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:50,351] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:50,398] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:50,445] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:50,493] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:50,541] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:50,588] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:57,131] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:57,151] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:57,184] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:57,218] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:57,254] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:57,289] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:57,325] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:57,361] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:57,397] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:57,432] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:57,477] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:57,543] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:57,601] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:57,647] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:57,703] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:57,760] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:57,818] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:57,890] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:57,936] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:57,994] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:58,051] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:58,110] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:58,165] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:58,222] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:58,280] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:58,338] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:58,395] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:58,453] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:58,511] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:58,569] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:58,627] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:58,683] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:58,741] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:58,798] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:58,856] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:34:58,914] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:07,695] [WARNING] [stage3.py:2497:step] 3 pytorch allocator cache flushes since last step. this happens when there is high memory pressure and is detrimental to performance. if this is happening frequently consider adjusting settings to reduce memory consumption. If you are unable to make the cache flushes go away consider adding get_accelerator().empty_cache() calls in your training loop to ensure that all ranks flush their caches at the same time
59%|█████▊ | 17/29 [25:57<18:10, 90.87s/it] {'loss': '0.5074', 'grad_norm': '0.7482', 'learning_rate': '5.653e-06', 'ppl': '1.661', 'memory/max_active (GiB)': '82.97', 'memory/max_allocated (GiB)': '82.97', 'memory/device_reserved (GiB)': '92.89', 'tokens/train_per_sec_per_gpu': '50.03', 'tokens/total': 14077952, 'tokens/trainable': 2706756, 'epoch': '1.747'}
59%|█████▊ | 17/29 [25:57<18:10, 90.87s/it][2026-04-22 17:35:07,728] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:07,764] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:07,828] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:07,894] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:07,959] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:08,024] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:08,090] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:08,156] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:08,222] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:08,289] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:08,356] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:08,421] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:08,488] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:08,554] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:08,620] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:08,688] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:08,753] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:08,819] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:08,887] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:08,953] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:09,019] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:09,085] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:09,152] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:09,217] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:09,285] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:09,350] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:09,416] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:09,483] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:09,548] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:09,614] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:09,682] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:09,748] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:09,814] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:09,880] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:09,947] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:10,014] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:19,762] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:19,782] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:19,834] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:19,890] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:19,947] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:20,002] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:20,059] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:20,119] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:20,176] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:20,234] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:20,293] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:20,352] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:20,412] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:20,473] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:20,535] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:20,596] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:20,657] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:20,719] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:20,781] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:20,842] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:20,902] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:20,963] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:21,024] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:21,085] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:21,146] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:21,206] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:21,262] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:21,320] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:21,378] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:21,436] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:21,494] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:21,554] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:21,613] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:21,673] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:21,734] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:21,795] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:31,948] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:31,970] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:31,999] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:32,028] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:32,058] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:32,090] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:32,120] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:32,151] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:32,184] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:32,214] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:32,251] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:32,313] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:32,364] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:32,415] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:32,461] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:32,511] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:32,561] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:32,609] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:32,658] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:32,709] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:32,760] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:32,811] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:32,861] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:32,911] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:32,963] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:33,016] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:33,063] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:33,114] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:33,164] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:33,216] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:33,266] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:33,317] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:33,368] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:33,418] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:33,468] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:33,518] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:41,050] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:41,070] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:41,098] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:41,127] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:41,156] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:41,188] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:41,219] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:41,249] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:41,278] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:41,309] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:41,341] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:41,371] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:41,402] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:41,440] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:41,478] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:41,517] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:41,554] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:41,596] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:41,645] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:41,682] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:41,724] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:41,771] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:41,812] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:42,153] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:42,183] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:42,223] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:42,252] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:42,282] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:42,317] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:42,353] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:42,390] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:42,420] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:42,450] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:42,489] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:42,519] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:42,550] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:48,280] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:48,300] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:48,349] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:48,403] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:48,456] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:48,510] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:48,564] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:48,619] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:48,673] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:48,728] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:48,781] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:48,838] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:48,896] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:48,954] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:49,013] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:49,070] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:49,329] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:49,381] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:49,435] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:49,555] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:49,616] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:49,668] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:49,724] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:50,235] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:50,282] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:50,333] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:50,385] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:50,437] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:50,491] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:50,544] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:50,597] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:50,652] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:50,706] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:50,762] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:50,818] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:35:50,868] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:00,264] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:00,286] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:00,335] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:00,388] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:00,441] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:00,496] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:00,550] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:00,604] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:00,658] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:00,713] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:00,770] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:00,827] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:00,885] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:00,941] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:00,996] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:01,051] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:01,108] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:01,164] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:01,219] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:01,277] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:01,335] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:01,390] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:01,445] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:01,501] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:01,558] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:01,616] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:01,673] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:01,732] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:01,790] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:01,846] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:01,904] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:01,962] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:02,020] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:02,079] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:02,137] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:02,196] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:11,669] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:11,691] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:11,741] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:11,795] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:11,848] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:11,903] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:11,958] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:12,014] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:12,069] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:12,124] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:12,180] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:12,238] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:12,295] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:12,351] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:12,410] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:12,468] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:12,526] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:12,584] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:12,642] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:12,701] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:12,759] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:12,818] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:12,879] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:12,939] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:12,998] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:13,056] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:13,115] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:13,174] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:13,234] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:13,293] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:13,350] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:13,410] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:13,468] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:13,527] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:13,586] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:13,644] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:23,355] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:23,376] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:23,424] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:23,473] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:23,525] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:23,576] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:23,631] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:23,681] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:23,731] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:23,783] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:23,836] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:23,890] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:23,944] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:23,994] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:24,046] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:24,100] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:24,188] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:24,253] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:24,318] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:24,372] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:24,433] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:24,496] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:24,563] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:24,630] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:24,696] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:24,792] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:24,883] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:24,931] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:24,984] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:25,043] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:25,105] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:25,169] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:25,235] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:25,304] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:25,368] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:25,435] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:36,716] [WARNING] [stage3.py:2497:step] 6 pytorch allocator cache flushes since last step. this happens when there is high memory pressure and is detrimental to performance. if this is happening frequently consider adjusting settings to reduce memory consumption. If you are unable to make the cache flushes go away consider adding get_accelerator().empty_cache() calls in your training loop to ensure that all ranks flush their caches at the same time
62%|██████▏ | 18/29 [27:26<16:33, 90.32s/it] {'loss': '0.4908', 'grad_norm': '0.6239', 'learning_rate': '5e-06', 'ppl': '1.634', 'memory/max_active (GiB)': '84.96', 'memory/max_allocated (GiB)': '84.96', 'memory/device_reserved (GiB)': '92.49', 'tokens/train_per_sec_per_gpu': '65.83', 'tokens/total': 14928896, 'tokens/trainable': 2869000, 'epoch': '1.853'}
62%|██████▏ | 18/29 [27:26<16:33, 90.32s/it][2026-04-22 17:36:36,749] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:36,785] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:36,848] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:36,911] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:36,974] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:37,038] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:37,103] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:37,164] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:37,225] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:37,289] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:37,353] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:37,416] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:37,480] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:37,545] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:37,608] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:37,672] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:37,736] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:37,800] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:37,865] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:37,929] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:37,993] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:38,057] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:38,121] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:38,184] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:38,248] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:38,312] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:38,376] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:38,440] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:38,505] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:38,569] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:38,633] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:38,698] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:38,762] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:38,827] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:38,891] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:38,956] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:49,303] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:49,327] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:49,373] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:49,428] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:49,481] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:49,536] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:49,590] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:49,644] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:49,700] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:49,757] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:49,815] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:49,873] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:49,928] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:49,982] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:50,039] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:50,096] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:50,164] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:50,220] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:50,276] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:50,331] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:50,385] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:50,441] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:50,506] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:50,568] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:50,633] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:50,691] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:50,752] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:50,817] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:50,882] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:50,947] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:51,014] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:51,079] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:51,145] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:51,230] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:51,276] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:36:51,341] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:02,035] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:02,056] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:02,113] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:02,177] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:02,239] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:02,302] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:02,364] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:02,427] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:02,491] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:02,553] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:02,619] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:02,683] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:02,749] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:02,813] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:02,878] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:02,944] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:03,009] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:03,075] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:03,139] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:03,207] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:03,274] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:03,342] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:03,409] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:03,477] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:03,546] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:03,612] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:03,680] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:03,747] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:03,814] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:03,882] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:03,949] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:04,016] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:04,084] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:04,151] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:04,218] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:04,285] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:15,306] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:15,327] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:15,374] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:15,425] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:15,476] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:15,528] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:15,581] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:15,633] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:15,686] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:15,739] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:15,792] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:15,846] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:15,899] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:15,951] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:16,003] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:16,056] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:16,111] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:16,166] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:16,221] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:16,274] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:16,326] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:16,378] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:16,429] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:16,482] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:16,536] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:16,590] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:16,644] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:16,704] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:16,764] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:16,824] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:16,885] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:16,946] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:17,007] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:17,068] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:17,127] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:17,189] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:26,556] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:26,577] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:26,638] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:26,703] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:26,769] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:26,836] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:26,903] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:26,969] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:27,035] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:27,103] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:27,169] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:27,236] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:27,302] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:27,368] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:27,434] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:27,499] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:27,566] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:27,633] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:27,700] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:27,764] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:27,828] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:27,894] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:27,959] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:28,025] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:28,091] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:28,156] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:28,222] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:28,288] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:28,353] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:28,419] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:28,485] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:28,550] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:28,619] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:28,690] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:28,757] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:28,874] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:40,386] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:40,407] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:40,466] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:40,528] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:40,591] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:40,653] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:40,718] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:40,782] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:40,845] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:40,907] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:40,971] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:41,033] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:41,098] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:41,161] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:41,622] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:41,678] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:41,740] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:41,800] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:41,862] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:41,924] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:41,986] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:42,047] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:42,110] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:42,171] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:42,236] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:42,299] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:42,362] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:42,425] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:42,489] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:42,551] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:42,615] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:42,679] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:42,742] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:42,832] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:42,870] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:42,932] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:51,729] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:51,751] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:51,810] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:51,872] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:51,936] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:51,999] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:52,062] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:52,124] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:52,188] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:52,249] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:52,312] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:52,375] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:52,439] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:52,503] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:52,566] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:52,629] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:52,692] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:52,755] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:52,818] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:52,881] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:52,944] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:53,007] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:53,068] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:53,131] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:53,194] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:53,258] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:53,321] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:53,384] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:53,447] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:53,510] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:53,574] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:53,636] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:53,700] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:53,762] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:53,826] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:37:53,886] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:38:03,156] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:38:03,177] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:38:03,220] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:38:03,267] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:38:03,316] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:38:03,365] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:38:03,416] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:38:03,464] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:38:03,510] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:38:03,559] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:38:03,608] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:38:03,655] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:38:03,704] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:38:03,752] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:38:03,810] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:38:03,876] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:38:03,954] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:38:04,010] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:38:04,077] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:38:04,144] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:38:04,210] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:38:04,278] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:38:04,343] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:38:04,409] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:38:04,475] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:38:04,543] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:38:04,609] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:38:04,674] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:38:04,742] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:38:04,808] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:38:04,875] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:38:04,942] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:38:05,009] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:38:05,074] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:38:05,141] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:38:05,208] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:38:15,538] [WARNING] [stage3.py:2497:step] 11 pytorch allocator cache flushes since last step. this happens when there is high memory pressure and is detrimental to performance. if this is happening frequently consider adjusting settings to reduce memory consumption. If you are unable to make the cache flushes go away consider adding get_accelerator().empty_cache() calls in your training loop to ensure that all ranks flush their caches at the same time
66%|██████▌ | 19/29 [29:05<15:28, 92.87s/it] {'loss': '0.4916', 'grad_norm': '0.603', 'learning_rate': '4.347e-06', 'ppl': '1.635', 'memory/max_active (GiB)': '90.64', 'memory/max_allocated (GiB)': '90.64', 'memory/device_reserved (GiB)': '92.89', 'tokens/train_per_sec_per_gpu': '50.06', 'tokens/total': 15832832, 'tokens/trainable': 3035124, 'epoch': '1.96'}
66%|██████▌ | 19/29 [29:05<15:28, 92.87s/it][2026-04-22 17:38:15,595] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:38:15,632] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:38:15,695] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:38:15,761] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:38:15,827] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:38:15,893] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:38:15,959] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:38:16,027] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:38:16,095] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:38:16,164] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:38:16,231] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:38:16,298] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:38:16,366] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:38:16,434] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:38:16,502] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:38:16,570] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:38:16,638] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:38:16,706] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:38:16,772] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:38:16,842] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:38:16,909] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:38:16,979] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:38:17,047] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:38:17,115] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:38:17,182] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:38:17,249] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:38:17,317] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:38:17,384] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:38:17,451] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:38:17,519] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:38:17,586] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:38:17,653] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:38:17,722] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:38:17,789] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:38:17,856] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:38:17,926] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:38:28,412] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:38:28,433] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:38:28,482] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:38:28,536] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:38:28,590] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:38:28,643] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:38:28,697] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:38:28,754] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:38:28,812] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:38:28,870] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:38:28,925] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:38:28,980] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:38:29,036] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:38:29,091] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:38:29,146] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:38:29,205] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:38:29,262] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:38:29,320] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:38:29,379] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:38:29,437] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:38:29,491] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:38:29,546] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:38:29,603] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:38:29,661] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:38:29,719] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:38:29,780] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:38:29,841] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:38:29,907] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:38:29,971] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:38:30,035] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:38:30,100] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:38:30,164] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:38:30,228] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:38:30,293] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:38:30,357] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:38:30,423] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:38:40,645] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:38:40,667] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:38:40,723] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:38:40,783] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:38:40,842] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:38:40,902] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:38:40,961] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:38:41,020] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:38:41,082] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:38:41,140] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:38:41,202] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:38:41,263] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:38:41,325] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:38:41,386] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:38:41,447] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:38:41,508] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:38:41,569] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:38:41,629] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:38:41,689] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:38:41,748] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:38:41,808] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:38:41,867] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:38:41,928] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:38:41,987] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:38:42,047] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:38:42,108] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:38:42,168] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:38:42,229] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:38:42,289] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:38:42,349] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:38:42,410] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:38:42,471] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:38:42,531] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:38:42,592] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:38:42,653] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:38:42,712] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:38:52,115] [WARNING] [stage3.py:2497:step] 3 pytorch allocator cache flushes since last step. this happens when there is high memory pressure and is detrimental to performance. if this is happening frequently consider adjusting settings to reduce memory consumption. If you are unable to make the cache flushes go away consider adding get_accelerator().empty_cache() calls in your training loop to ensure that all ranks flush their caches at the same time
69%|██████▉ | 20/29 [29:41<11:23, 75.97s/it] {'loss': '0.4799', 'grad_norm': '0.8088', 'learning_rate': '3.706e-06', 'ppl': '1.616', 'memory/max_active (GiB)': '86.98', 'memory/max_allocated (GiB)': '86.98', 'memory/device_reserved (GiB)': '92.3', 'tokens/train_per_sec_per_gpu': '127.1', 'tokens/total': 16162688, 'tokens/trainable': 3095550, 'epoch': '2'}
69%|██████▉ | 20/29 [29:41<11:23, 75.97s/it][2026-04-22 17:38:54,535] [INFO] [axolotl.core.trainers.base._save:741] [PID:1024775] Saving model checkpoint to /e/data1/datasets/playground/ot-baf/checkpoints/sera-v3-1000-axolotl__Qwen3-8B/checkpoint-20
Writing model shards: 0%| | 0/1 [00:00<?, ?it/s]
Writing model shards: 100%|██████████| 1/1 [00:06<00:00, 6.89s/it] Writing model shards: 100%|██████████| 1/1 [00:06<00:00, 6.90s/it]
[2026-04-22 17:39:20,489] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:39:20,540] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:39:20,600] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:39:20,662] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:39:20,725] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:39:20,789] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:39:20,851] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:39:20,913] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:39:20,974] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:39:21,038] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:39:21,100] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:39:21,164] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:39:21,228] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:39:21,291] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:39:21,354] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:39:21,417] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:39:21,480] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:39:21,542] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:39:21,605] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:39:21,668] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:39:21,731] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:39:21,793] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:39:21,857] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:39:21,921] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:39:21,985] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:39:22,049] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:39:22,112] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:39:22,175] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:39:22,237] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:39:22,300] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:39:22,365] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:39:22,428] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:39:22,491] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:39:22,556] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:39:22,619] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:39:22,685] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:39:32,972] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:39:32,991] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:39:33,044] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:39:33,101] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:39:33,158] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:39:33,216] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:39:33,274] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:39:33,333] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:39:33,392] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:39:33,451] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:39:33,514] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:39:33,577] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:39:33,641] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:39:33,701] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:39:34,027] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:39:34,087] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:39:34,146] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:39:34,210] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:39:34,276] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:39:34,342] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:39:34,399] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:39:34,460] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:39:34,520] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:39:34,579] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:39:34,641] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:39:34,702] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:39:34,763] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:39:34,824] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:39:34,884] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:39:34,944] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:39:35,005] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:39:35,067] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:39:35,129] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:39:35,191] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:39:35,250] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:39:35,312] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:39:45,780] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:39:45,801] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:39:45,850] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:39:45,906] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:39:45,961] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:39:46,015] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:39:46,070] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:39:46,126] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:39:46,183] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:39:46,239] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:39:46,296] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:39:46,354] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:39:46,413] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:39:46,470] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:39:46,526] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:39:46,583] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:39:46,919] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:39:46,970] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:39:47,027] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:39:47,092] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:39:47,146] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:39:47,201] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:39:47,256] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:39:47,310] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:39:47,922] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:39:47,943] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:39:47,992] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:39:48,047] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:39:48,102] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:39:48,156] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:39:48,209] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:39:48,264] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:39:48,317] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:39:48,370] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:39:48,423] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:39:48,473] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:39:58,917] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:39:58,937] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:39:58,988] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:39:59,043] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:39:59,098] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:39:59,153] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:39:59,210] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:39:59,265] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:39:59,322] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:39:59,379] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:39:59,436] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:39:59,493] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:39:59,550] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:39:59,609] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:39:59,666] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:39:59,725] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:39:59,783] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:39:59,841] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:39:59,900] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:39:59,958] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:00,017] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:00,076] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:00,136] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:00,194] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:00,253] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:00,312] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:00,372] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:00,432] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:00,490] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:00,548] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:00,608] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:00,667] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:00,726] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:00,785] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:00,842] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:00,900] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:10,008] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:10,027] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:10,080] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:10,136] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:10,192] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:10,249] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:10,308] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:10,366] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:10,423] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:10,483] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:10,541] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:10,602] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:10,663] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:10,725] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:10,786] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:10,843] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:10,901] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:10,958] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:11,017] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:11,075] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:11,134] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:11,193] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:11,253] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:11,314] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:11,376] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:11,437] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:11,498] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:11,559] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:11,619] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:11,680] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:11,740] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:11,801] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:11,858] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:11,917] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:11,974] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:12,033] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:21,860] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:21,880] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:21,929] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:21,984] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:22,037] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:22,091] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:22,145] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:22,199] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:22,253] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:22,310] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:22,365] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:22,423] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:22,480] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:22,538] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:22,596] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:22,655] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:22,714] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:22,774] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:22,832] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:22,889] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:22,947] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:23,002] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:23,056] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:23,111] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:23,166] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:23,221] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:23,278] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:23,335] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:23,392] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:23,450] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:23,510] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:23,569] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:23,627] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:23,687] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:23,742] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:23,800] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:33,318] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:33,339] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:33,381] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:33,425] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:33,471] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:33,519] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:33,565] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:33,611] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:33,660] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:33,707] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:33,756] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:33,804] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:33,854] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:33,904] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:33,951] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:33,998] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:34,045] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:34,094] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:34,143] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:34,193] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:34,242] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:34,291] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:34,340] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:34,385] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:34,432] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:34,480] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:34,528] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:34,578] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:34,626] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:34,679] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:34,733] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:34,786] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:34,841] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:34,896] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:34,950] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:35,004] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:42,998] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:43,018] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:43,077] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:43,140] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:43,199] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:43,261] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:43,323] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:43,384] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:43,446] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:43,509] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:43,573] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:43,637] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:43,700] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:43,763] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:43,826] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:43,890] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:43,952] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:44,016] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:44,080] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:44,142] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:44,205] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:44,269] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:44,333] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:44,396] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:44,459] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:44,522] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:44,585] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:44,649] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:44,713] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:44,777] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:44,840] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:44,903] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:44,967] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:45,031] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:45,094] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:45,156] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:54,999] [WARNING] [stage3.py:2497:step] 9 pytorch allocator cache flushes since last step. this happens when there is high memory pressure and is detrimental to performance. if this is happening frequently consider adjusting settings to reduce memory consumption. If you are unable to make the cache flushes go away consider adding get_accelerator().empty_cache() calls in your training loop to ensure that all ranks flush their caches at the same time
72%|███████▏ | 21/29 [31:44<12:00, 90.05s/it] {'loss': '0.4827', 'grad_norm': '0.5359', 'learning_rate': '3.087e-06', 'ppl': '1.62', 'memory/max_active (GiB)': '88.28', 'memory/max_allocated (GiB)': '88.28', 'memory/device_reserved (GiB)': '92.84', 'tokens/train_per_sec_per_gpu': '52.77', 'tokens/total': 17044800, 'tokens/trainable': 3268576, 'epoch': '2.107'}
72%|███████▏ | 21/29 [31:44<12:00, 90.05s/it][2026-04-22 17:40:55,036] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:55,070] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:55,130] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:55,188] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:55,246] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:55,305] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:55,365] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:55,422] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:55,482] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:55,540] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:55,600] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:55,660] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:55,719] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:55,778] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:55,837] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:55,897] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:55,955] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:56,015] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:56,075] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:56,135] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:56,194] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:56,252] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:56,313] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:56,372] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:56,432] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:56,493] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:56,553] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:56,612] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:56,672] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:56,733] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:56,793] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:56,852] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:56,913] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:56,973] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:57,033] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:40:57,093] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:05,291] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:05,310] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:05,338] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:05,366] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:05,397] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:05,425] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:05,456] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:05,486] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:05,563] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:05,617] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:05,672] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:05,728] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:05,791] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:05,862] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:05,919] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:05,982] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:06,045] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:06,109] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:06,188] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:06,251] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:06,306] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:06,363] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:06,427] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:06,773] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:06,823] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:06,883] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:06,947] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:07,006] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:07,040] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:07,096] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:07,151] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:07,211] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:07,275] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:07,334] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:07,368] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:07,423] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:16,886] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:16,906] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:16,967] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:17,034] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:17,099] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:17,163] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:17,229] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:17,294] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:17,360] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:17,424] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:17,490] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:17,556] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:17,621] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:17,688] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:17,754] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:17,819] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:17,884] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:17,949] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:18,016] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:18,083] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:18,148] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:18,215] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:18,284] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:18,354] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:18,425] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:18,494] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:18,561] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:18,629] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:18,696] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:18,763] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:18,830] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:18,896] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:18,962] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:19,031] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:19,096] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:19,160] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:28,535] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:28,556] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:28,618] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:28,684] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:28,752] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:28,820] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:28,886] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:28,953] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:29,021] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:29,089] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:29,157] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:29,225] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:29,291] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:29,358] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:29,425] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:29,966] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:29,987] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:30,050] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:30,116] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:30,182] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:30,246] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:30,312] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:30,376] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:30,443] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:30,510] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:30,577] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:30,644] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:30,712] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:30,780] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:30,846] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:30,914] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:30,981] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:31,047] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:31,114] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:31,183] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:31,246] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:41,386] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:41,407] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:41,460] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:41,517] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:41,575] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:41,634] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:41,692] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:41,751] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:41,811] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:41,869] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:41,928] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:41,988] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:42,047] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:42,108] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:42,170] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:42,232] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:42,294] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:42,356] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:42,418] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:42,480] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:42,541] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:42,603] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:42,665] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:42,728] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:42,790] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:42,853] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:42,916] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:42,978] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:43,040] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:43,103] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:43,166] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:43,229] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:43,291] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:43,354] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:43,416] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:43,479] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:53,203] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:53,224] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:53,273] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:53,327] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:53,380] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:53,434] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:53,490] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:53,545] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:53,600] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:53,655] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:53,710] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:53,766] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:53,821] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:53,877] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:53,934] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:53,991] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:54,048] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:54,105] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:54,163] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:54,221] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:54,279] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:54,337] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:54,393] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:54,451] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:54,509] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:54,567] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:54,626] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:54,683] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:54,740] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:54,797] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:54,855] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:54,913] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:54,972] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:55,031] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:55,088] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:41:55,144] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:04,171] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:04,193] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:04,240] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:04,292] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:04,344] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:04,397] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:04,450] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:04,502] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:04,556] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:04,611] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:04,667] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:04,722] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:04,778] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:04,833] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:04,885] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:04,937] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:04,989] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:05,044] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:05,099] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:05,154] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:05,210] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:05,267] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:05,324] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:05,380] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:05,434] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:05,486] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:05,539] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:05,592] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:05,647] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:05,703] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:05,759] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:05,815] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:05,871] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:05,935] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:05,991] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:06,052] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:15,154] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:15,174] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:15,234] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:15,298] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:15,362] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:15,428] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:15,495] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:15,560] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:15,626] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:15,693] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:15,760] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:15,828] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:15,895] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:15,961] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:16,028] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:16,095] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:16,161] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:16,228] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:16,295] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:16,364] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:16,433] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:16,500] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:16,567] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:16,634] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:16,702] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:16,770] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:16,838] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:16,905] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:16,973] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:17,043] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:17,111] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:17,179] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:17,246] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:17,314] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:17,381] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:17,448] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:28,638] [WARNING] [stage3.py:2497:step] 11 pytorch allocator cache flushes since last step. this happens when there is high memory pressure and is detrimental to performance. if this is happening frequently consider adjusting settings to reduce memory consumption. If you are unable to make the cache flushes go away consider adding get_accelerator().empty_cache() calls in your training loop to ensure that all ranks flush their caches at the same time
76%|███████▌ | 22/29 [33:18<10:37, 91.13s/it] {'loss': '0.4636', 'grad_norm': '0.5577', 'learning_rate': '2.5e-06', 'ppl': '1.59', 'memory/max_active (GiB)': '92.06', 'memory/max_allocated (GiB)': '92.06', 'memory/device_reserved (GiB)': '92.87', 'tokens/train_per_sec_per_gpu': '60.98', 'tokens/total': 17891264, 'tokens/trainable': 3430759, 'epoch': '2.213'}
76%|███████▌ | 22/29 [33:18<10:37, 91.13s/it][2026-04-22 17:42:28,672] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:28,705] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:28,764] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:28,825] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:28,886] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:28,947] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:29,009] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:29,068] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:29,130] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:29,191] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:29,252] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:29,313] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:29,375] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:29,435] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:29,495] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:29,555] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:29,616] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:29,677] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:29,738] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:29,798] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:29,860] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:29,921] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:29,983] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:30,043] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:30,104] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:30,164] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:30,225] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:30,287] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:30,349] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:30,409] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:30,470] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:30,532] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:30,593] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:30,654] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:30,714] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:30,774] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:40,015] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:40,038] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:40,634] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:40,675] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:40,725] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:40,777] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:40,831] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:40,884] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:40,941] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:40,993] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:41,046] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:41,100] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:41,156] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:41,210] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:41,267] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:41,325] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:41,379] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:41,434] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:41,491] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:41,544] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:41,602] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:41,657] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:41,733] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:41,783] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:41,871] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:41,921] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:41,977] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:42,043] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:42,114] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:42,177] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:42,233] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:42,312] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:42,385] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:42,442] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:42,519] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:42,584] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:54,903] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:54,924] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:54,976] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:55,031] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:55,089] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:55,146] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:55,202] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:55,257] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:55,315] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:55,371] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:55,430] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:55,488] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:55,546] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:55,603] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:55,661] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:55,718] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:55,775] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:55,832] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:55,889] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:55,945] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:56,002] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:56,059] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:56,116] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:56,173] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:56,230] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:56,286] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:56,343] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:56,400] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:56,457] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:56,513] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:56,571] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:56,628] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:56,685] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:56,741] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:56,798] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:42:56,853] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:06,522] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:06,543] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:06,586] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:06,631] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:06,677] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:06,724] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:06,773] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:06,818] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:06,866] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:06,913] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:06,961] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:07,009] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:07,075] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:07,129] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:07,196] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:07,264] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:07,331] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:07,398] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:07,465] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:07,533] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:07,600] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:07,668] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:07,735] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:07,803] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:07,872] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:07,939] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:08,006] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:08,075] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:08,142] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:08,210] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:08,279] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:08,346] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:08,415] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:08,484] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:08,549] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:08,618] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:18,695] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:18,715] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:18,763] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:18,818] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:18,870] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:18,923] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:18,978] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:19,030] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:19,085] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:19,140] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:19,197] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:19,253] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:19,311] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:19,368] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:19,421] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:19,477] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:19,531] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:19,587] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:19,643] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:19,701] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:19,758] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:19,815] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:19,868] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:19,922] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:19,977] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:20,031] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:20,087] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:20,148] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:20,204] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:20,263] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:20,324] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:20,385] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:20,448] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:20,511] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:20,571] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:20,635] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:30,200] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:30,220] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:30,278] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:30,338] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:30,399] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:30,462] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:30,525] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:30,585] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:30,647] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:30,710] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:30,772] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:30,835] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:30,896] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:30,958] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:31,019] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:31,081] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:31,141] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:31,202] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:31,264] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:31,326] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:31,388] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:31,450] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:31,511] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:31,573] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:31,637] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:31,697] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:31,758] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:31,820] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:31,882] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:31,943] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:32,005] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:32,068] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:32,130] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:32,194] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:32,255] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:32,315] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:41,389] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:41,409] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:41,454] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:41,503] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:41,554] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:41,603] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:41,655] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:41,705] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:41,758] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:41,810] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:41,863] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:41,916] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:41,968] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:42,018] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:42,067] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:42,119] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:42,171] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:42,223] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:42,276] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:42,325] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:42,376] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:42,425] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:42,476] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:42,528] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:42,588] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:42,639] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:42,694] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:42,753] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:42,812] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:42,872] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:42,931] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:42,990] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:43,050] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:43,110] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:43,170] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:43,228] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:52,481] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:52,501] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:52,559] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:52,623] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:52,684] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:52,747] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:52,811] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:52,874] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:52,936] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:53,000] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:53,066] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:53,130] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:53,194] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:53,258] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:53,321] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:53,386] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:53,449] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:53,513] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:53,578] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:53,641] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:53,706] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:53,770] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:53,835] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:53,899] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:53,965] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:54,028] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:54,092] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:54,156] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:54,220] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:54,285] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:54,349] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:54,414] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:54,479] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:54,545] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:54,609] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:43:54,671] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:04,466] [WARNING] [stage3.py:2497:step] 11 pytorch allocator cache flushes since last step. this happens when there is high memory pressure and is detrimental to performance. if this is happening frequently consider adjusting settings to reduce memory consumption. If you are unable to make the cache flushes go away consider adding get_accelerator().empty_cache() calls in your training loop to ensure that all ranks flush their caches at the same time
79%|███████▉ | 23/29 [34:54<09:15, 92.54s/it] {'loss': '0.4462', 'grad_norm': '0.5342', 'learning_rate': '1.956e-06', 'ppl': '1.562', 'memory/max_active (GiB)': '89.58', 'memory/max_allocated (GiB)': '89.58', 'memory/device_reserved (GiB)': '92.87', 'tokens/train_per_sec_per_gpu': '48.33', 'tokens/total': 18766976, 'tokens/trainable': 3596545, 'epoch': '2.32'}
79%|███████▉ | 23/29 [34:54<09:15, 92.54s/it][2026-04-22 17:44:04,499] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:04,534] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:04,597] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:04,659] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:04,721] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:04,783] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:04,845] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:04,908] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:04,970] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:05,034] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:05,097] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:05,159] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:05,222] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:05,284] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:05,346] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:05,409] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:05,473] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:05,535] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:05,598] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:05,660] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:05,724] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:05,786] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:05,848] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:05,912] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:05,974] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:06,037] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:06,099] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:06,163] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:06,227] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:06,289] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:06,352] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:06,415] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:06,478] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:06,541] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:06,605] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:06,668] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:16,179] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:16,201] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:16,256] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:16,317] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:16,378] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:16,438] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:16,500] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:16,561] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:16,621] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:16,680] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:16,740] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:16,802] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:16,863] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:16,925] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:16,986] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:17,047] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:17,106] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:17,167] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:17,228] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:17,288] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:17,349] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:17,411] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:17,472] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:17,532] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:17,593] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:17,652] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:17,712] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:17,772] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:17,832] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:17,892] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:17,952] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:18,012] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:18,072] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:18,155] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:18,195] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:18,259] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:26,985] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:27,005] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:27,046] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:27,091] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:27,136] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:27,180] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:27,226] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:27,273] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:27,320] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:27,368] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:27,414] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:27,459] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:27,506] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:27,554] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:27,601] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:27,652] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:28,027] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:28,074] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:28,124] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:28,181] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:28,235] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:28,291] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:28,348] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:28,392] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:28,438] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:28,487] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:28,539] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:28,592] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:28,645] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:28,698] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:28,757] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:28,814] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:28,870] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:28,915] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:28,962] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:29,013] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:37,217] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:37,236] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:37,293] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:37,355] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:37,416] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:37,478] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:37,538] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:37,600] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:37,661] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:37,723] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:37,785] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:37,847] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:37,911] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:37,973] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:38,035] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:38,098] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:38,160] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:38,222] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:38,285] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:38,347] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:38,411] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:38,474] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:38,537] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:38,601] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:38,668] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:38,734] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:38,824] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:38,885] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:38,947] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:39,011] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:39,075] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:39,138] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:39,200] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:39,263] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:39,326] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:39,387] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:48,861] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:48,881] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:48,938] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:48,999] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:49,059] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:49,121] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:49,183] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:49,244] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:49,307] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:49,370] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:49,432] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:49,494] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:49,556] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:49,618] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:49,680] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:49,741] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:49,803] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:49,866] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:49,929] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:49,991] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:50,053] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:50,115] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:50,177] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:50,238] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:50,300] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:50,362] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:50,426] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:50,986] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:51,007] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:51,064] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:51,125] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:51,187] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:51,249] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:51,312] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:51,375] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:44:51,435] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:01,978] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:01,998] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:02,049] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:02,104] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:02,158] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:02,214] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:02,269] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:02,325] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:02,381] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:02,436] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:02,491] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:02,549] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:02,606] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:02,665] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:02,724] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:02,782] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:02,840] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:02,898] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:02,957] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:03,016] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:03,075] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:03,133] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:03,192] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:03,251] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:03,311] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:03,370] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:03,430] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:03,490] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:03,549] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:03,609] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:03,669] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:03,728] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:03,788] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:03,848] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:03,906] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:03,967] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:12,899] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:12,920] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:12,959] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:13,002] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:13,045] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:13,089] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:13,134] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:13,175] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:13,217] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:13,258] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:13,302] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:13,348] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:13,393] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:13,435] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:13,478] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:13,527] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:13,576] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:13,628] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:13,685] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:13,740] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:13,797] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:13,852] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:13,919] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:13,972] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:14,023] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:14,077] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:14,133] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:14,190] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:14,246] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:14,303] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:14,359] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:14,416] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:14,472] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:14,529] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:14,583] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:14,641] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:23,177] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:23,196] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:23,244] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:23,297] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:23,349] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:23,401] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:23,456] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:23,510] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:23,563] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:23,618] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:23,670] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:23,723] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:23,778] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:23,833] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:23,884] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:23,964] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:24,014] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:24,072] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:24,128] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:24,202] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:24,253] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:24,334] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:24,400] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:24,466] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:24,538] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:24,597] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:24,667] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:24,729] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:24,801] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:24,870] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:24,936] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:25,004] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:25,068] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:25,135] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:25,200] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:25,266] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:36,830] [WARNING] [stage3.py:2497:step] 11 pytorch allocator cache flushes since last step. this happens when there is high memory pressure and is detrimental to performance. if this is happening frequently consider adjusting settings to reduce memory consumption. If you are unable to make the cache flushes go away consider adding get_accelerator().empty_cache() calls in your training loop to ensure that all ranks flush their caches at the same time
83%|████████▎ | 24/29 [36:26<07:42, 92.49s/it] {'loss': '0.4397', 'grad_norm': '0.4829', 'learning_rate': '1.464e-06', 'ppl': '1.552', 'memory/max_active (GiB)': '88.99', 'memory/max_allocated (GiB)': '88.99', 'memory/device_reserved (GiB)': '92.79', 'tokens/train_per_sec_per_gpu': '60.14', 'tokens/total': 19643520, 'tokens/trainable': 3763774, 'epoch': '2.427'}
83%|████████▎ | 24/29 [36:26<07:42, 92.49s/it][2026-04-22 17:45:36,865] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:36,898] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:36,955] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:37,015] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:37,076] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:37,135] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:37,195] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:37,254] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:37,313] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:37,374] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:37,433] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:37,493] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:37,553] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:37,614] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:37,675] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:37,735] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:37,795] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:37,856] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:37,916] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:37,977] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:38,037] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:38,097] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:38,157] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:38,217] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:38,278] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:38,338] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:38,398] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:38,458] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:38,518] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:38,578] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:38,639] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:38,700] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:38,761] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:38,821] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:38,882] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:38,942] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:47,693] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:47,713] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:47,760] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:47,811] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:47,862] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:47,914] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:47,965] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:48,016] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:48,067] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:48,120] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:48,173] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:48,226] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:48,280] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:48,334] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:48,389] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:48,442] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:48,494] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:48,548] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:48,603] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:48,656] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:48,708] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:48,759] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:48,811] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:48,863] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:48,916] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:48,969] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:49,024] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:49,077] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:49,130] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:49,184] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:49,239] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:49,293] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:49,347] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:49,402] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:49,457] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:49,512] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:58,006] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:58,026] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:58,068] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:58,113] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:58,159] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:58,206] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:58,253] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:58,299] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:58,348] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:58,397] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:58,445] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:58,495] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:58,541] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:58,589] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:58,637] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:58,684] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:58,732] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:58,780] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:58,830] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:58,880] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:58,929] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:58,979] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:59,025] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:59,073] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:59,119] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:59,550] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:59,600] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:59,654] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:59,707] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:59,760] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:59,813] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:59,866] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:59,919] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:45:59,973] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:00,026] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:00,080] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:07,711] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:07,730] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:07,785] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:07,845] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:07,905] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:07,966] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:08,026] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:08,086] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:08,146] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:08,207] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:08,268] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:08,330] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:08,391] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:08,451] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:08,513] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:08,574] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:08,635] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:08,697] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:08,758] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:08,820] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:08,881] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:08,941] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:09,004] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:09,065] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:09,128] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:09,189] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:09,250] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:09,312] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:09,373] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:09,434] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:09,496] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:09,557] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:09,619] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:09,682] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:09,744] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:09,804] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:19,818] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:19,838] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:19,884] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:19,935] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:19,984] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:20,034] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:20,088] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:20,141] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:20,195] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:20,245] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:20,296] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:20,349] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:20,403] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:20,455] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:20,508] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:20,560] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:20,613] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:20,920] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:20,969] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:21,029] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:21,091] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:21,162] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:21,219] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:21,267] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:21,319] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:21,378] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:21,427] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:21,484] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:21,535] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:21,593] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:21,656] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:21,707] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:21,758] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:21,810] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:21,860] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:21,915] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:32,818] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:32,840] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:32,894] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:33,350] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:33,403] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:33,463] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:33,519] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:33,578] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:33,635] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:33,695] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:33,754] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:33,813] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:33,872] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:33,931] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:33,991] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:34,052] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:34,111] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:34,172] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:34,233] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:34,291] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:34,349] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:34,408] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:34,468] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:34,527] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:34,586] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:34,646] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:34,706] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:34,766] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:34,825] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:34,885] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:34,944] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:35,005] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:35,065] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:35,126] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:35,183] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:35,240] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:44,567] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:44,586] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:44,625] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:44,665] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:44,707] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:44,749] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:44,792] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:44,831] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:44,873] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:44,913] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:44,954] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:45,000] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:45,060] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:45,124] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:45,188] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:45,249] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:45,312] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:45,371] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:45,447] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:45,506] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:45,563] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:45,623] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:45,686] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:45,751] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:45,811] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:45,872] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:45,934] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:45,995] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:46,070] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:46,148] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:46,210] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:46,250] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:46,330] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:46,394] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:46,455] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:46,519] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:56,124] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:56,144] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:56,196] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:56,252] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:56,308] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:56,365] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:56,423] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:56,479] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:56,537] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:56,595] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:56,651] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:56,710] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:56,770] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:56,829] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:56,889] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:56,948] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:57,009] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:57,070] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:57,131] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:57,191] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:57,252] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:57,312] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:57,372] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:57,433] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:57,493] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:57,553] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:57,613] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:57,675] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:57,734] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:57,796] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:57,857] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:57,919] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:57,980] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:58,042] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:58,103] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:46:58,165] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:47:08,347] [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
86%|████████▌ | 25/29 [37:58<06:08, 92.20s/it] {'loss': '0.4678', 'grad_norm': '0.5201', 'learning_rate': '1.033e-06', 'ppl': '1.597', 'memory/max_active (GiB)': '88.04', 'memory/max_allocated (GiB)': '88.04', 'memory/device_reserved (GiB)': '91.99', 'tokens/train_per_sec_per_gpu': '48.68', 'tokens/total': 20503168, 'tokens/trainable': 3922869, 'epoch': '2.533'}
86%|████████▌ | 25/29 [37:58<06:08, 92.20s/it][2026-04-22 17:47:08,380] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:47:08,413] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:47:08,473] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:47:08,532] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:47:08,591] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:47:08,652] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:47:08,711] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:47:08,772] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:47:08,832] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:47:08,891] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:47:08,951] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:47:09,012] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:47:09,073] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:47:09,131] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:47:09,191] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:47:09,251] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:47:09,312] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:47:09,372] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:47:09,433] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:47:09,492] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:47:09,552] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:47:09,613] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:47:09,673] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:47:09,733] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:47:09,792] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:47:09,853] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:47:09,913] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:47:09,974] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:47:10,035] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:47:10,094] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:47:10,154] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:47:10,215] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:47:10,276] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:47:10,336] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:47:10,396] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:47:10,457] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:47:19,699] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:47:19,722] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:47:19,779] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:47:19,844] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:47:19,908] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:47:19,974] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:47:20,039] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:47:20,105] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:47:20,172] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:47:20,239] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:47:20,307] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:47:20,377] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:47:20,444] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:47:20,512] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:47:20,579] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:47:20,647] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:47:20,714] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:47:20,782] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:47:20,849] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:47:20,916] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:47:20,984] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:47:21,051] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:47:21,117] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:47:21,184] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:47:21,252] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:47:21,318] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:47:21,387] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:47:21,456] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:47:21,524] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:47:21,591] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:47:21,659] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:47:21,727] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:47:21,796] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:47:21,870] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:47:21,932] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:47:22,001] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:47:33,251] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:47:33,271] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:47:33,330] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:47:33,394] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:47:33,461] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:47:33,526] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:47:33,593] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:47:33,658] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:47:33,725] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:47:33,791] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:47:33,858] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:47:33,924] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:47:33,991] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:47:34,056] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:47:34,122] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:47:34,188] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:47:34,252] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:47:34,317] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:47:34,382] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:47:34,447] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:47:34,512] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:47:34,577] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:47:34,640] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:47:34,707] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:47:34,773] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:47:34,838] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:47:34,904] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:47:34,970] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:47:35,035] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:47:35,100] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:47:35,166] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:47:35,231] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:47:35,296] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:47:35,362] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:47:35,428] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:47:35,492] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:47:45,991] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:47:46,011] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:47:46,073] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:47:46,140] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:47:46,207] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:47:46,278] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:47:46,348] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:47:46,415] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:47:46,484] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:47:46,555] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:47:46,626] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:47:46,696] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:47:46,764] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:47:46,833] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:47:46,901] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:47:46,968] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:47:47,035] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:47:47,102] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:47:47,173] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:47:47,242] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:47:47,315] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:47:47,383] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:47:47,450] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:47:47,518] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:47:47,586] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:47:47,655] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:47:47,724] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:47:47,793] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:47:47,862] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:47:47,931] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:47:48,000] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:47:48,069] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:47:48,137] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:47:48,207] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:47:48,275] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:47:48,340] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:47:59,800] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:47:59,820] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:47:59,875] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:47:59,935] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:47:59,996] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:00,057] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:00,118] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:00,178] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:00,238] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:00,301] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:00,364] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:00,426] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:00,487] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:00,552] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:00,615] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:00,680] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:00,745] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:00,811] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:00,875] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:00,937] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:01,002] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:01,064] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:01,125] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:01,186] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:01,247] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:01,309] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:01,372] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:01,436] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:01,500] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:01,566] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:01,631] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:01,697] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:01,762] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:01,832] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:01,894] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:02,153] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:13,213] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:13,234] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:13,276] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:13,322] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:13,370] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:13,416] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:13,465] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:13,514] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:13,561] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:13,608] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:13,655] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:13,705] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:14,229] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:14,272] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:14,317] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:14,363] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:14,410] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:14,456] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:14,502] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:14,551] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:14,610] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:14,668] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:14,728] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:14,788] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:14,849] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:14,909] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:14,969] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:15,029] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:15,089] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:15,149] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:15,209] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:15,269] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:15,329] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:15,390] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:15,449] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:15,510] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:24,157] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:24,178] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:24,206] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:24,235] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:24,267] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:24,297] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:24,330] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:24,361] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:24,429] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:24,495] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:24,554] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:24,622] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:24,677] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:24,746] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:24,812] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:24,878] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:24,944] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:25,010] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:25,091] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:25,157] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:25,216] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:25,276] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:25,342] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:25,408] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:25,474] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:25,540] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:25,607] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:25,672] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:25,738] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:25,821] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:25,886] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:25,945] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:26,010] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:26,073] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:26,138] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:26,205] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:36,241] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:36,260] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:36,288] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:36,316] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:36,346] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:36,375] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:36,405] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:36,436] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:36,502] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:36,584] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:36,652] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:36,713] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:36,776] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:36,841] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:36,904] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:36,972] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:37,040] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:37,106] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:37,174] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:37,241] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:37,308] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:37,375] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:37,442] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:37,508] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:37,576] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:37,643] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:37,729] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:37,796] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:37,860] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:37,922] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:37,984] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:38,053] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:38,114] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:38,182] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:38,249] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:38,316] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:49,056] [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
90%|████████▉ | 26/29 [39:38<04:44, 94.75s/it] {'loss': '0.4511', 'grad_norm': '0.5179', 'learning_rate': '6.699e-07', 'ppl': '1.57', 'memory/max_active (GiB)': '91.35', 'memory/max_allocated (GiB)': '91.35', 'memory/device_reserved (GiB)': '92.79', 'tokens/train_per_sec_per_gpu': '60.16', 'tokens/total': 21392512, 'tokens/trainable': 4096487, 'epoch': '2.64'}
90%|████████▉ | 26/29 [39:38<04:44, 94.75s/it][2026-04-22 17:48:49,089] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:49,122] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:49,180] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:49,240] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:49,301] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:49,361] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:49,422] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:49,483] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:49,543] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:49,604] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:49,663] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:49,724] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:49,782] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:49,844] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:49,904] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:49,964] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:50,025] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:50,085] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:50,146] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:50,206] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:50,267] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:50,327] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:50,388] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:50,448] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:50,508] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:50,570] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:50,630] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:50,690] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:50,750] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:50,812] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:50,873] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:50,934] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:50,995] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:51,055] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:51,117] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:51,179] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:59,937] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:48:59,959] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:00,009] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:00,066] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:00,124] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:00,181] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:00,238] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:00,295] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:00,352] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:00,412] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:00,473] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:00,534] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:00,596] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:00,658] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:00,721] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:00,782] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:00,844] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:00,902] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:00,960] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:01,018] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:01,077] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:01,136] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:01,198] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:01,260] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:01,323] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:01,384] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:01,446] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:01,508] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:01,570] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:01,627] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:01,685] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:01,743] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:01,803] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:01,870] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:01,925] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:01,987] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:12,745] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:12,766] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:12,814] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:12,866] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:12,919] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:12,971] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:13,023] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:13,077] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:13,130] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:13,184] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:13,239] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:13,296] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:13,353] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:13,406] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:13,459] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:13,514] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:13,567] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:13,623] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:13,679] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:13,735] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:13,788] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:13,840] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:13,895] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:13,951] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:14,014] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:14,075] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:14,144] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:14,205] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:14,267] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:14,330] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:14,392] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:14,455] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:14,517] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:14,580] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:14,642] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:14,705] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:24,510] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:24,530] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:24,581] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:24,637] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:24,694] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:24,750] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:24,806] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:24,863] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:24,921] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:24,980] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:25,040] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:25,101] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:25,163] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:25,224] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:25,284] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:25,344] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:25,404] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:25,465] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:25,521] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:25,578] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:25,635] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:25,694] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:25,753] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:25,814] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:25,874] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:25,934] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:26,153] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:26,207] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:26,266] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:26,330] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:26,385] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:26,443] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:26,500] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:26,556] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:26,616] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:26,674] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:36,636] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:36,656] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:36,703] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:36,753] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:36,804] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:36,853] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:36,904] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:36,955] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:37,006] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:37,057] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:37,108] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:37,159] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:37,212] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:37,262] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:37,315] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:37,368] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:37,420] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:37,474] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:37,527] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:37,580] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:37,633] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:37,687] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:37,740] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:37,795] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:37,850] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:37,904] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:37,959] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:38,014] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:38,068] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:38,122] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:38,176] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:38,229] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:38,284] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:38,338] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:38,392] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:38,447] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:46,857] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:46,878] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:46,919] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:46,964] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:47,008] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:47,051] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:47,096] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:47,140] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:47,183] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:47,227] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:47,270] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:47,313] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:47,357] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:47,402] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:47,446] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:47,490] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:47,535] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:47,579] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:47,624] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:47,668] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:47,711] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:48,238] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:48,278] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:48,321] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:48,364] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:48,407] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:48,450] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:48,493] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:48,537] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:48,581] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:48,625] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:48,668] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:48,711] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:48,756] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:48,801] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:48,844] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:55,004] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:55,023] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:55,079] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:55,138] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:55,200] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:55,260] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:55,320] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:55,382] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:55,442] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:55,504] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:55,565] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:55,626] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:55,687] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:55,749] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:55,808] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:55,868] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:55,928] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:55,989] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:56,049] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:56,110] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:56,171] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:56,231] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:56,292] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:56,353] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:56,413] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:56,473] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:56,533] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:56,593] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:56,654] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:56,714] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:56,775] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:56,834] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:56,895] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:56,956] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:57,018] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:49:57,076] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:06,988] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:07,008] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:07,060] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:07,117] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:07,172] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:07,225] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:07,279] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:07,334] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:07,392] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:07,450] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:07,506] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:07,564] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:07,622] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:07,681] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:07,736] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:07,792] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:07,848] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:07,905] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:07,964] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:08,022] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:08,079] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:08,136] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:08,195] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:08,249] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:08,304] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:08,359] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:08,417] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:08,475] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:08,532] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:08,589] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:08,653] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:08,716] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:08,781] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:08,843] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:08,906] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:08,971] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:18,711] [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
93%|█████████▎| 27/29 [41:08<03:06, 93.22s/it] {'loss': '0.4566', 'grad_norm': '0.544', 'learning_rate': '3.806e-07', 'ppl': '1.579', 'memory/max_active (GiB)': '86.75', 'memory/max_allocated (GiB)': '86.75', 'memory/device_reserved (GiB)': '92.79', 'tokens/train_per_sec_per_gpu': '64.89', 'tokens/total': 22224512, 'tokens/trainable': 4261202, 'epoch': '2.747'}
93%|█████████▎| 27/29 [41:08<03:06, 93.22s/it][2026-04-22 17:50:18,745] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:18,781] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:18,845] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:18,908] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:18,969] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:19,031] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:19,092] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:19,155] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:19,217] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:19,277] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:19,341] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:19,406] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:19,467] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:19,531] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:19,593] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:19,656] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:19,719] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:19,783] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:19,846] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:19,909] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:19,973] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:20,034] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:20,096] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:20,160] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:20,223] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:20,287] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:20,350] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:20,413] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:20,477] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:20,540] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:20,604] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:20,667] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:20,730] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:20,793] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:20,857] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:20,920] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:29,645] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:29,666] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:29,720] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:29,778] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:29,838] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:29,898] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:29,958] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:30,017] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:30,075] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:30,134] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:30,194] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:30,254] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:30,313] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:30,372] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:30,431] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:30,491] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:30,550] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:30,610] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:30,669] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:30,728] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:30,787] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:30,846] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:30,905] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:30,964] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:31,023] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:31,082] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:31,141] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:31,201] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:31,260] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:31,320] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:31,380] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:31,438] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:31,498] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:31,573] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:31,620] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:31,682] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:39,916] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:39,937] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:39,986] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:40,039] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:40,093] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:40,147] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:40,201] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:40,256] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:40,311] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:40,365] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:40,420] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:40,475] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:40,529] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:40,583] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:40,637] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:40,693] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:40,749] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:40,805] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:40,863] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:40,919] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:40,975] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:41,032] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:41,088] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:41,145] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:41,203] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:41,261] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:41,318] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:41,375] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:41,431] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:41,489] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:41,546] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:41,603] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:41,661] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:41,719] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:41,776] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:41,833] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:50,438] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:50,458] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:50,517] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:50,581] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:50,647] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:50,712] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:50,776] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:50,839] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:50,903] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:50,967] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:51,032] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:51,096] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:51,162] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:51,227] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:51,290] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:51,354] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:51,418] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:51,481] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:51,545] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:51,608] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:51,671] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:51,734] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:51,798] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:51,862] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:51,926] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:51,988] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:52,052] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:52,115] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:52,179] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:52,242] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:52,306] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:52,369] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:52,432] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:52,496] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:52,561] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:50:52,623] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:02,198] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:02,218] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:02,253] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:02,291] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:02,330] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:02,369] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:02,405] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:02,444] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:02,482] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:02,855] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:02,898] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:02,960] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:02,996] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:03,047] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:03,099] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:03,158] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:03,227] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:03,262] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:03,300] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:03,356] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:03,392] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:03,452] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:03,503] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:03,562] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:03,635] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:03,692] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:03,750] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:03,814] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:03,888] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:03,949] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:04,008] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:04,071] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:04,148] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:04,209] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:04,263] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:04,327] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:13,831] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:13,849] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:13,905] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:13,965] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:14,025] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:14,085] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:14,144] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:14,204] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:14,266] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:14,327] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:14,389] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:14,451] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:14,514] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:14,575] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:14,636] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:14,699] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:14,761] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:14,824] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:14,885] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:14,947] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:15,008] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:15,071] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:15,132] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:15,195] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:15,257] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:15,320] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:15,382] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:15,444] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:15,506] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:15,568] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:15,632] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:15,695] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:15,758] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:15,822] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:15,882] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:15,945] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:27,676] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:27,695] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:27,758] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:27,825] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:27,892] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:27,960] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:28,029] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:28,096] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:28,164] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:28,232] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:28,302] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:28,369] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:28,437] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:28,504] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:28,571] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:28,637] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:28,707] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:28,779] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:28,850] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:28,953] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:29,022] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:29,095] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:29,162] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:29,230] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:29,299] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:29,370] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:29,440] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:29,510] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:29,578] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:29,651] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:29,724] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:29,793] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:29,863] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:29,932] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:30,001] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:30,069] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:40,693] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:40,713] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:40,749] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:40,789] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:40,828] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:40,869] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:40,908] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:40,948] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:40,989] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:41,029] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:41,069] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:41,119] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:41,182] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:41,243] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:41,305] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:41,368] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:41,451] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:41,511] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:41,573] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:41,634] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:41,700] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:41,762] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:41,821] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:41,882] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:41,943] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:42,004] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:42,069] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:42,128] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:42,190] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:42,253] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:42,317] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:42,378] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:42,440] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:42,503] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:42,565] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:42,628] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:52,588] [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
97%|█████████▋| 28/29 [42:42<01:33, 93.42s/it] {'loss': '0.4558', 'grad_norm': '0.502', 'learning_rate': '1.704e-07', 'ppl': '1.577', 'memory/max_active (GiB)': '92.18', 'memory/max_allocated (GiB)': '92.18', 'memory/device_reserved (GiB)': '92.87', 'tokens/train_per_sec_per_gpu': '64.81', 'tokens/total': 23084672, 'tokens/trainable': 4422745, 'epoch': '2.853'}
97%|█████████▋| 28/29 [42:42<01:33, 93.42s/it][2026-04-22 17:51:52,621] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:52,655] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:52,711] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:52,773] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:52,833] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:52,893] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:52,954] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:53,014] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:53,075] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:53,137] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:53,198] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:53,260] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:53,322] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:53,383] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:53,444] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:53,506] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:53,569] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:53,630] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:53,691] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:53,752] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:53,812] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:53,874] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:53,935] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:53,996] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:54,057] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:54,118] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:54,180] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:54,241] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:54,303] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:54,365] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:54,427] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:54,488] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:54,551] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:54,612] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:54,674] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:51:54,735] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:03,887] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:03,910] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:03,954] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:04,007] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:04,058] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:04,110] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:04,161] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:04,213] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:04,267] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:04,321] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:04,375] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:04,427] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:04,479] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:04,530] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:04,585] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:04,640] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:04,695] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:04,751] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:04,807] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:04,858] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:04,911] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:04,964] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:05,019] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:05,073] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:05,128] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:05,188] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:05,249] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:05,311] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:05,372] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:05,435] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:05,497] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:05,558] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:05,621] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:05,691] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:05,745] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:05,808] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:15,576] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:15,596] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:15,651] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:15,711] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:15,770] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:15,828] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:15,887] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:15,947] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:16,007] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:16,067] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:16,127] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:16,188] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:16,249] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:16,310] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:16,370] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:16,430] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:16,490] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:16,550] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:16,610] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:16,669] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:16,728] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:16,788] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:16,847] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:16,907] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:16,966] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:17,025] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:17,084] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:17,146] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:17,206] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:17,266] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:17,327] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:17,387] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:17,447] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:17,508] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:17,568] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:17,625] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:26,502] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:26,522] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:26,555] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:26,590] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:26,625] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:26,660] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:26,695] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:26,731] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:26,767] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:26,829] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:26,888] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:26,963] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:27,017] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:27,084] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:27,149] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:27,224] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:27,281] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:27,346] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:27,411] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:27,476] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:27,542] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:27,606] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:27,672] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:27,737] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:27,803] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:27,869] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:27,934] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:28,000] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:28,065] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:28,131] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:28,196] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:28,261] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:28,327] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:28,394] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:28,459] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:28,525] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:38,409] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:38,428] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:38,471] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:38,516] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:38,562] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:38,610] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:38,656] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:38,706] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:38,750] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:38,801] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:38,850] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:38,896] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:38,944] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:38,992] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:39,050] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:39,113] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:39,176] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:39,241] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:39,305] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:39,382] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:39,445] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:39,503] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:39,564] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:39,627] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:39,692] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:39,756] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:40,087] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:40,139] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:40,201] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:40,265] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:40,320] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:40,368] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:40,415] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:40,467] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:40,532] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:40,598] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:49,935] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:49,954] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:50,012] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:50,075] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:50,138] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:50,201] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:50,265] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:50,327] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:50,390] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:50,455] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:50,522] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:50,588] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:50,653] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:50,719] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:50,785] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:50,850] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:50,915] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:50,980] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:51,046] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:51,110] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:51,176] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:51,241] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:51,307] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:51,372] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:51,436] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:51,502] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:51,567] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:51,632] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:51,697] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:51,763] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:51,828] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:51,894] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:51,961] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:52,027] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:52,092] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:52:52,159] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:53:02,721] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:53:02,742] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:53:02,793] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:53:02,848] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:53:02,902] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:53:02,958] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:53:03,013] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:53:03,071] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:53:03,128] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:53:03,186] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:53:03,244] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:53:03,299] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:53:03,355] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:53:03,412] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:53:03,470] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:53:03,527] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:53:03,586] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:53:03,644] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:53:03,698] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:53:03,753] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:53:03,811] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:53:03,869] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:53:03,928] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:53:04,504] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:53:04,551] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:53:04,604] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:53:04,659] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:53:04,713] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:53:04,765] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:53:04,818] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:53:04,872] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:53:04,927] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:53:04,980] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:53:05,034] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:53:05,087] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:53:05,138] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:53:15,281] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:53:15,301] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:53:15,350] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:53:15,403] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:53:15,457] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:53:15,512] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:53:15,564] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:53:15,619] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:53:15,673] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:53:15,727] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:53:15,779] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:53:15,833] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:53:15,886] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:53:15,940] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:53:15,993] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:53:16,047] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:53:16,100] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:53:16,153] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:53:16,206] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:53:16,259] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:53:16,312] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:53:16,365] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:53:16,417] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:53:16,471] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:53:16,523] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:53:16,576] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:53:16,629] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:53:16,682] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:53:16,735] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:53:16,788] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:53:16,841] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:53:16,894] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:53:16,948] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:53:17,010] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:53:17,056] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:53:17,108] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:1024775] Forwarded ds_grads_remaining to wrapped module Qwen3DecoderLayer
[2026-04-22 17:53:25,316] [WARNING] [stage3.py:2497:step] 9 pytorch allocator cache flushes since last step. this happens when there is high memory pressure and is detrimental to performance. if this is happening frequently consider adjusting settings to reduce memory consumption. If you are unable to make the cache flushes go away consider adding get_accelerator().empty_cache() calls in your training loop to ensure that all ranks flush their caches at the same time
100%|██████████| 29/29 [44:15<00:00, 93.21s/it] {'loss': '0.4778', 'grad_norm': '0.4959', 'learning_rate': '4.278e-08', 'ppl': '1.613', 'memory/max_active (GiB)': '89.7', 'memory/max_allocated (GiB)': '89.7', 'memory/device_reserved (GiB)': '92.18', 'tokens/train_per_sec_per_gpu': '50.72', 'tokens/total': 23932224, 'tokens/trainable': 4582437, 'epoch': '2.96'}
100%|██████████| 29/29 [44:15<00:00, 93.21s/it][2026-04-22 17:53:27,673] [INFO] [axolotl.core.trainers.base._save:741] [PID:1024775] Saving model checkpoint to /e/data1/datasets/playground/ot-baf/checkpoints/sera-v3-1000-axolotl__Qwen3-8B/checkpoint-29
Writing model shards: 0%| | 0/1 [00:00<?, ?it/s]
Writing model shards: 100%|██████████| 1/1 [00:06<00:00, 6.60s/it] Writing model shards: 100%|██████████| 1/1 [00:06<00:00, 6.60s/it]
{'train_runtime': '2682', 'train_samples_per_second': '0.346', 'train_steps_per_second': '0.011', 'train_loss': '0.6266', 'memory/max_active (GiB)': '31.77', 'memory/max_allocated (GiB)': '31.77', 'memory/device_reserved (GiB)': '83.96', 'epoch': '2.96', 'tokens/train_per_sec_per_gpu': '0'}
100%|██████████| 29/29 [44:42<00:00, 93.21s/it] 100%|██████████| 29/29 [44:42<00:00, 92.50s/it]
[2026-04-22 17:53:53,466] [INFO] [axolotl.train.save_trained_model:241] [PID:1024775] Training completed! Saving trained model to /e/data1/datasets/playground/ot-baf/checkpoints/sera-v3-1000-axolotl__Qwen3-8B.
[2026-04-22 17:53:55,867] [INFO] [axolotl.core.trainers.base._save:741] [PID:1024775] Saving model checkpoint to /e/data1/datasets/playground/ot-baf/checkpoints/sera-v3-1000-axolotl__Qwen3-8B
Writing model shards: 0%| | 0/1 [00:00<?, ?it/s] Writing model shards: 100%|██████████| 1/1 [00:06<00:00, 6.63s/it] Writing model shards: 100%|██████████| 1/1 [00:06<00:00, 6.63s/it]
[2026-04-22 17:54:02,727] [INFO] [axolotl.train.save_trained_model:355] [PID:1024775] Model successfully saved to /e/data1/datasets/playground/ot-baf/checkpoints/sera-v3-1000-axolotl__Qwen3-8B