| 2025-09-15 01:41:22 - INFO - __main__ - Model parameters AuxFreeModelConfig(model_name_or_path='Qwen/Qwen1.5-MoE-A2.7B', model_revision='main', torch_dtype='bfloat16', trust_remote_code=True, attn_implementation='flash_attention_2', use_peft=False, lora_r=16, lora_alpha=32, lora_dropout=0.05, lora_target_modules=None, lora_modules_to_save=None, lora_task_type='CAUSAL_LM', use_rslora=False, load_in_8bit=False, load_in_4bit=False, bnb_4bit_quant_type='nf4', use_bnb_nested_quant=False, bias_update_speed=0.001, remove_aux_loss=True, add_aux_free_loss=True) |
| 2025-09-15 01:41:22 - INFO - __main__ - Script parameters ScriptArguments(dataset_name='HectorHe/math7k', dataset_config=None, dataset_train_split='train', dataset_test_split='test', gradient_checkpointing_use_reentrant=False, ignore_bias_buffers=False) |
| 2025-09-15 01:41:22 - INFO - __main__ - Training parameters SFTConfig( |
| _n_gpu=1, |
| accelerator_config={'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None, 'use_configured_state': False}, |
| adafactor=False, |
| adam_beta1=0.9, |
| adam_beta2=0.999, |
| adam_epsilon=1e-08, |
| auto_find_batch_size=False, |
| average_tokens_across_devices=False, |
| batch_eval_metrics=False, |
| benchmarks=[], |
| bf16=True, |
| bf16_full_eval=False, |
| callbacks=[], |
| chars_per_token=<CHARS_PER_TOKEN>, |
| chat_template=None, |
| data_seed=None, |
| dataloader_drop_last=False, |
| dataloader_num_workers=0, |
| dataloader_persistent_workers=False, |
| dataloader_pin_memory=True, |
| dataloader_prefetch_factor=None, |
| dataset_batch_size=None, |
| dataset_kwargs=None, |
| dataset_num_proc=None, |
| dataset_text_field=text, |
| ddp_backend=None, |
| ddp_broadcast_buffers=None, |
| ddp_bucket_cap_mb=None, |
| ddp_find_unused_parameters=None, |
| ddp_timeout=1800000000, |
| debug=[], |
| deepspeed=None, |
| disable_tqdm=False, |
| do_eval=True, |
| do_predict=False, |
| do_train=False, |
| eval_accumulation_steps=None, |
| eval_delay=0, |
| eval_do_concat_batches=True, |
| eval_on_start=False, |
| eval_packing=None, |
| eval_steps=None, |
| eval_strategy=IntervalStrategy.NO, |
| eval_use_gather_object=False, |
| fp16=False, |
| fp16_backend=auto, |
| fp16_full_eval=False, |
| fp16_opt_level=O1, |
| fsdp=[], |
| fsdp_config={'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, |
| fsdp_min_num_params=0, |
| fsdp_transformer_layer_cls_to_wrap=None, |
| full_determinism=False, |
| gradient_accumulation_steps=1, |
| gradient_checkpointing=True, |
| gradient_checkpointing_kwargs={'use_reentrant': False}, |
| greater_is_better=None, |
| group_by_length=False, |
| half_precision_backend=auto, |
| hub_always_push=False, |
| hub_model_id=Qwen1.5-MOE-aux-free-sft-math7k-1e-3-gamma, |
| hub_model_revision=main, |
| hub_private_repo=None, |
| hub_strategy=HubStrategy.EVERY_SAVE, |
| hub_token=<HUB_TOKEN>, |
| ignore_data_skip=False, |
| include_for_metrics=[], |
| include_inputs_for_metrics=False, |
| include_num_input_tokens_seen=False, |
| include_tokens_per_second=False, |
| jit_mode_eval=False, |
| label_names=None, |
| label_smoothing_factor=0.0, |
| learning_rate=1e-05, |
| length_column_name=length, |
| load_best_model_at_end=False, |
| local_rank=0, |
| log_level=info, |
| log_level_replica=warning, |
| log_on_each_node=True, |
| logging_dir=/tmp/data/Qwen1.5-MOE/aux_free_sft/math7k/1e-3-gamma/runs/Sep15_01-41-22_orchard-flame-15, |
| logging_first_step=False, |
| logging_nan_inf_filter=True, |
| logging_steps=1, |
| logging_strategy=IntervalStrategy.STEPS, |
| lr_scheduler_kwargs={'min_lr_rate': 0.1}, |
| lr_scheduler_type=SchedulerType.COSINE_WITH_MIN_LR, |
| max_grad_norm=1.0, |
| max_length=4096, |
| max_seq_length=None, |
| max_steps=-1, |
| metric_for_best_model=None, |
| model_init_kwargs=None, |
| mp_parameters=, |
| neftune_noise_alpha=None, |
| no_cuda=False, |
| num_of_sequences=None, |
| num_train_epochs=1, |
| optim=OptimizerNames.ADAMW_TORCH, |
| optim_args=None, |
| optim_target_modules=None, |
| output_dir=/tmp/data/Qwen1.5-MOE/aux_free_sft/math7k/1e-3-gamma, |
| overwrite_hub_revision=False, |
| overwrite_output_dir=True, |
| packing=False, |
| past_index=-1, |
| per_device_eval_batch_size=16, |
| per_device_train_batch_size=4, |
| prediction_loss_only=False, |
| push_to_hub=True, |
| push_to_hub_model_id=None, |
| push_to_hub_organization=None, |
| push_to_hub_revision=False, |
| push_to_hub_token=<PUSH_TO_HUB_TOKEN>, |
| ray_scope=last, |
| remove_unused_columns=True, |
| report_to=['wandb'], |
| restore_callback_states_from_checkpoint=False, |
| resume_from_checkpoint=None, |
| run_name=/tmp/data/Qwen1.5-MOE/aux_free_sft/math7k/1e-3-gamma, |
| save_on_each_node=False, |
| save_only_model=False, |
| save_safetensors=True, |
| save_steps=500, |
| save_strategy=SaveStrategy.EPOCH, |
| save_total_limit=1, |
| seed=1234, |
| skip_memory_metrics=True, |
| system_prompt=None, |
| tf32=None, |
| torch_compile=False, |
| torch_compile_backend=None, |
| torch_compile_mode=None, |
| torch_empty_cache_steps=None, |
| torchdynamo=None, |
| tp_size=0, |
| tpu_metrics_debug=False, |
| tpu_num_cores=None, |
| use_cpu=False, |
| use_ipex=False, |
| use_legacy_prediction_loop=False, |
| use_liger=False, |
| use_liger_kernel=False, |
| use_mps_device=False, |
| wandb_entity=None, |
| wandb_project=None, |
| warmup_ratio=0.1, |
| warmup_steps=0, |
| weight_decay=0.0, |
| ) |
| 2025-09-15 01:41:24 - INFO - __main__ - *** Initializing model kwargs *** |
| 2025-09-15 01:41:35 - INFO - __main__ - *** Train *** |
| 2025-09-15 01:41:35 - INFO - __main__ - Qwen2MoeForCausalLM( |
| (model): Qwen2MoeModel( |
| (embed_tokens): Embedding(151936, 2048) |
| (layers): ModuleList( |
| (0-23): 24 x Qwen2MoeDecoderLayer( |
| (self_attn): Qwen2MoeFlashAttention2( |
| (q_proj): Linear(in_features=2048, out_features=2048, bias=True) |
| (k_proj): Linear(in_features=2048, out_features=2048, bias=True) |
| (v_proj): Linear(in_features=2048, out_features=2048, bias=True) |
| (o_proj): Linear(in_features=2048, out_features=2048, bias=False) |
| (rotary_emb): Qwen2MoeRotaryEmbedding() |
| ) |
| (mlp): Qwen2MoeSparseMoeBlock( |
| (gate): Linear(in_features=2048, out_features=60, bias=False) |
| (experts): ModuleList( |
| (0-59): 60 x Qwen2MoeMLP( |
| (gate_proj): Linear(in_features=2048, out_features=1408, bias=False) |
| (up_proj): Linear(in_features=2048, out_features=1408, bias=False) |
| (down_proj): Linear(in_features=1408, out_features=2048, bias=False) |
| (act_fn): SiLU() |
| ) |
| ) |
| (shared_expert): Qwen2MoeMLP( |
| (gate_proj): Linear(in_features=2048, out_features=5632, bias=False) |
| (up_proj): Linear(in_features=2048, out_features=5632, bias=False) |
| (down_proj): Linear(in_features=5632, out_features=2048, bias=False) |
| (act_fn): SiLU() |
| ) |
| (shared_expert_gate): Linear(in_features=2048, out_features=1, bias=False) |
| ) |
| (input_layernorm): Qwen2MoeRMSNorm((2048,), eps=1e-06) |
| (post_attention_layernorm): Qwen2MoeRMSNorm((2048,), eps=1e-06) |
| ) |
| ) |
| (norm): Qwen2MoeRMSNorm((2048,), eps=1e-06) |
| (rotary_emb): Qwen2MoeRotaryEmbedding() |
| ) |
| (lm_head): Linear(in_features=2048, out_features=151936, bias=False) |
| ) |
| 2025-09-15 01:46:07 - INFO - __main__ - Model parameters AuxFreeModelConfig(model_name_or_path='Qwen/Qwen1.5-MoE-A2.7B', model_revision='main', torch_dtype='bfloat16', trust_remote_code=True, attn_implementation='flash_attention_2', use_peft=False, lora_r=16, lora_alpha=32, lora_dropout=0.05, lora_target_modules=None, lora_modules_to_save=None, lora_task_type='CAUSAL_LM', use_rslora=False, load_in_8bit=False, load_in_4bit=False, bnb_4bit_quant_type='nf4', use_bnb_nested_quant=False, bias_update_speed=0.001, remove_aux_loss=True, add_aux_free_loss=True) |
| 2025-09-15 01:46:07 - INFO - __main__ - Script parameters ScriptArguments(dataset_name='HectorHe/math7k', dataset_config=None, dataset_train_split='train', dataset_test_split='test', gradient_checkpointing_use_reentrant=False, ignore_bias_buffers=False) |
| 2025-09-15 01:46:07 - INFO - __main__ - Training parameters SFTConfig( |
| _n_gpu=1, |
| accelerator_config={'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None, 'use_configured_state': False}, |
| adafactor=False, |
| adam_beta1=0.9, |
| adam_beta2=0.999, |
| adam_epsilon=1e-08, |
| auto_find_batch_size=False, |
| average_tokens_across_devices=False, |
| batch_eval_metrics=False, |
| benchmarks=[], |
| bf16=True, |
| bf16_full_eval=False, |
| callbacks=[], |
| chars_per_token=<CHARS_PER_TOKEN>, |
| chat_template=None, |
| data_seed=None, |
| dataloader_drop_last=False, |
| dataloader_num_workers=0, |
| dataloader_persistent_workers=False, |
| dataloader_pin_memory=True, |
| dataloader_prefetch_factor=None, |
| dataset_batch_size=None, |
| dataset_kwargs=None, |
| dataset_num_proc=None, |
| dataset_text_field=text, |
| ddp_backend=None, |
| ddp_broadcast_buffers=None, |
| ddp_bucket_cap_mb=None, |
| ddp_find_unused_parameters=None, |
| ddp_timeout=1800000000, |
| debug=[], |
| deepspeed=None, |
| disable_tqdm=False, |
| do_eval=True, |
| do_predict=False, |
| do_train=False, |
| eval_accumulation_steps=None, |
| eval_delay=0, |
| eval_do_concat_batches=True, |
| eval_on_start=False, |
| eval_packing=None, |
| eval_steps=None, |
| eval_strategy=IntervalStrategy.NO, |
| eval_use_gather_object=False, |
| fp16=False, |
| fp16_backend=auto, |
| fp16_full_eval=False, |
| fp16_opt_level=O1, |
| fsdp=[], |
| fsdp_config={'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, |
| fsdp_min_num_params=0, |
| fsdp_transformer_layer_cls_to_wrap=None, |
| full_determinism=False, |
| gradient_accumulation_steps=1, |
| gradient_checkpointing=True, |
| gradient_checkpointing_kwargs={'use_reentrant': False}, |
| greater_is_better=None, |
| group_by_length=False, |
| half_precision_backend=auto, |
| hub_always_push=False, |
| hub_model_id=Qwen1.5-MOE-aux-free-sft-math7k-1e-3-gamma, |
| hub_model_revision=main, |
| hub_private_repo=None, |
| hub_strategy=HubStrategy.EVERY_SAVE, |
| hub_token=<HUB_TOKEN>, |
| ignore_data_skip=False, |
| include_for_metrics=[], |
| include_inputs_for_metrics=False, |
| include_num_input_tokens_seen=False, |
| include_tokens_per_second=False, |
| jit_mode_eval=False, |
| label_names=None, |
| label_smoothing_factor=0.0, |
| learning_rate=1e-05, |
| length_column_name=length, |
| load_best_model_at_end=False, |
| local_rank=0, |
| log_level=info, |
| log_level_replica=warning, |
| log_on_each_node=True, |
| logging_dir=/tmp/data/Qwen1.5-MOE/aux_free_sft/math7k/1e-3-gamma/runs/Sep15_01-46-06_orchard-flame-15, |
| logging_first_step=False, |
| logging_nan_inf_filter=True, |
| logging_steps=1, |
| logging_strategy=IntervalStrategy.STEPS, |
| lr_scheduler_kwargs={'min_lr_rate': 0.1}, |
| lr_scheduler_type=SchedulerType.COSINE_WITH_MIN_LR, |
| max_grad_norm=1.0, |
| max_length=4096, |
| max_seq_length=None, |
| max_steps=-1, |
| metric_for_best_model=None, |
| model_init_kwargs=None, |
| mp_parameters=, |
| neftune_noise_alpha=None, |
| no_cuda=False, |
| num_of_sequences=None, |
| num_train_epochs=1, |
| optim=OptimizerNames.ADAMW_TORCH, |
| optim_args=None, |
| optim_target_modules=None, |
| output_dir=/tmp/data/Qwen1.5-MOE/aux_free_sft/math7k/1e-3-gamma, |
| overwrite_hub_revision=False, |
| overwrite_output_dir=True, |
| packing=False, |
| past_index=-1, |
| per_device_eval_batch_size=16, |
| per_device_train_batch_size=4, |
| prediction_loss_only=False, |
| push_to_hub=True, |
| push_to_hub_model_id=None, |
| push_to_hub_organization=None, |
| push_to_hub_revision=False, |
| push_to_hub_token=<PUSH_TO_HUB_TOKEN>, |
| ray_scope=last, |
| remove_unused_columns=True, |
| report_to=['wandb'], |
| restore_callback_states_from_checkpoint=False, |
| resume_from_checkpoint=None, |
| run_name=/tmp/data/Qwen1.5-MOE/aux_free_sft/math7k/1e-3-gamma, |
| save_on_each_node=False, |
| save_only_model=False, |
| save_safetensors=True, |
| save_steps=500, |
| save_strategy=SaveStrategy.EPOCH, |
| save_total_limit=1, |
| seed=1234, |
| skip_memory_metrics=True, |
| system_prompt=None, |
| tf32=None, |
| torch_compile=False, |
| torch_compile_backend=None, |
| torch_compile_mode=None, |
| torch_empty_cache_steps=None, |
| torchdynamo=None, |
| tp_size=0, |
| tpu_metrics_debug=False, |
| tpu_num_cores=None, |
| use_cpu=False, |
| use_ipex=False, |
| use_legacy_prediction_loop=False, |
| use_liger=False, |
| use_liger_kernel=False, |
| use_mps_device=False, |
| wandb_entity=None, |
| wandb_project=None, |
| warmup_ratio=0.1, |
| warmup_steps=0, |
| weight_decay=0.0, |
| ) |
| 2025-09-15 01:46:08 - INFO - __main__ - *** Initializing model kwargs *** |
| 2025-09-15 01:46:20 - INFO - __main__ - *** Train *** |
| 2025-09-15 01:46:20 - INFO - __main__ - Qwen2MoeForCausalLM( |
| (model): Qwen2MoeModel( |
| (embed_tokens): Embedding(151936, 2048) |
| (layers): ModuleList( |
| (0-23): 24 x Qwen2MoeDecoderLayer( |
| (self_attn): Qwen2MoeFlashAttention2( |
| (q_proj): Linear(in_features=2048, out_features=2048, bias=True) |
| (k_proj): Linear(in_features=2048, out_features=2048, bias=True) |
| (v_proj): Linear(in_features=2048, out_features=2048, bias=True) |
| (o_proj): Linear(in_features=2048, out_features=2048, bias=False) |
| (rotary_emb): Qwen2MoeRotaryEmbedding() |
| ) |
| (mlp): Qwen2MoeSparseMoeBlock( |
| (gate): Linear(in_features=2048, out_features=60, bias=False) |
| (experts): ModuleList( |
| (0-59): 60 x Qwen2MoeMLP( |
| (gate_proj): Linear(in_features=2048, out_features=1408, bias=False) |
| (up_proj): Linear(in_features=2048, out_features=1408, bias=False) |
| (down_proj): Linear(in_features=1408, out_features=2048, bias=False) |
| (act_fn): SiLU() |
| ) |
| ) |
| (shared_expert): Qwen2MoeMLP( |
| (gate_proj): Linear(in_features=2048, out_features=5632, bias=False) |
| (up_proj): Linear(in_features=2048, out_features=5632, bias=False) |
| (down_proj): Linear(in_features=5632, out_features=2048, bias=False) |
| (act_fn): SiLU() |
| ) |
| (shared_expert_gate): Linear(in_features=2048, out_features=1, bias=False) |
| ) |
| (input_layernorm): Qwen2MoeRMSNorm((2048,), eps=1e-06) |
| (post_attention_layernorm): Qwen2MoeRMSNorm((2048,), eps=1e-06) |
| ) |
| ) |
| (norm): Qwen2MoeRMSNorm((2048,), eps=1e-06) |
| (rotary_emb): Qwen2MoeRotaryEmbedding() |
| ) |
| (lm_head): Linear(in_features=2048, out_features=151936, bias=False) |
| ) |
| 2025-09-15 01:49:27 - INFO - __main__ - Model parameters AuxFreeModelConfig(model_name_or_path='Qwen/Qwen1.5-MoE-A2.7B', model_revision='main', torch_dtype='bfloat16', trust_remote_code=True, attn_implementation='flash_attention_2', use_peft=False, lora_r=16, lora_alpha=32, lora_dropout=0.05, lora_target_modules=None, lora_modules_to_save=None, lora_task_type='CAUSAL_LM', use_rslora=False, load_in_8bit=False, load_in_4bit=False, bnb_4bit_quant_type='nf4', use_bnb_nested_quant=False, bias_update_speed=0.001, remove_aux_loss=True, add_aux_free_loss=True) |
| 2025-09-15 01:49:27 - INFO - __main__ - Script parameters ScriptArguments(dataset_name='HectorHe/math7k', dataset_config=None, dataset_train_split='train', dataset_test_split='test', gradient_checkpointing_use_reentrant=False, ignore_bias_buffers=False) |
| 2025-09-15 01:49:27 - INFO - __main__ - Training parameters SFTConfig( |
| _n_gpu=1, |
| accelerator_config={'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None, 'use_configured_state': False}, |
| adafactor=False, |
| adam_beta1=0.9, |
| adam_beta2=0.999, |
| adam_epsilon=1e-08, |
| auto_find_batch_size=False, |
| average_tokens_across_devices=False, |
| batch_eval_metrics=False, |
| benchmarks=[], |
| bf16=True, |
| bf16_full_eval=False, |
| callbacks=[], |
| chars_per_token=<CHARS_PER_TOKEN>, |
| chat_template=None, |
| data_seed=None, |
| dataloader_drop_last=False, |
| dataloader_num_workers=0, |
| dataloader_persistent_workers=False, |
| dataloader_pin_memory=True, |
| dataloader_prefetch_factor=None, |
| dataset_batch_size=None, |
| dataset_kwargs=None, |
| dataset_num_proc=None, |
| dataset_text_field=text, |
| ddp_backend=None, |
| ddp_broadcast_buffers=None, |
| ddp_bucket_cap_mb=None, |
| ddp_find_unused_parameters=None, |
| ddp_timeout=1800000000, |
| debug=[], |
| deepspeed=None, |
| disable_tqdm=False, |
| do_eval=True, |
| do_predict=False, |
| do_train=False, |
| eval_accumulation_steps=None, |
| eval_delay=0, |
| eval_do_concat_batches=True, |
| eval_on_start=False, |
| eval_packing=None, |
| eval_steps=None, |
| eval_strategy=IntervalStrategy.NO, |
| eval_use_gather_object=False, |
| fp16=False, |
| fp16_backend=auto, |
| fp16_full_eval=False, |
| fp16_opt_level=O1, |
| fsdp=[], |
| fsdp_config={'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, |
| fsdp_min_num_params=0, |
| fsdp_transformer_layer_cls_to_wrap=None, |
| full_determinism=False, |
| gradient_accumulation_steps=1, |
| gradient_checkpointing=True, |
| gradient_checkpointing_kwargs={'use_reentrant': True}, |
| greater_is_better=None, |
| group_by_length=False, |
| half_precision_backend=auto, |
| hub_always_push=False, |
| hub_model_id=Qwen1.5-MOE-aux-free-sft-math7k-1e-3-gamma, |
| hub_model_revision=main, |
| hub_private_repo=None, |
| hub_strategy=HubStrategy.EVERY_SAVE, |
| hub_token=<HUB_TOKEN>, |
| ignore_data_skip=False, |
| include_for_metrics=[], |
| include_inputs_for_metrics=False, |
| include_num_input_tokens_seen=False, |
| include_tokens_per_second=False, |
| jit_mode_eval=False, |
| label_names=None, |
| label_smoothing_factor=0.0, |
| learning_rate=1e-05, |
| length_column_name=length, |
| load_best_model_at_end=False, |
| local_rank=0, |
| log_level=info, |
| log_level_replica=warning, |
| log_on_each_node=True, |
| logging_dir=/tmp/data/Qwen1.5-MOE/aux_free_sft/math7k/1e-3-gamma/runs/Sep15_01-49-27_orchard-flame-15, |
| logging_first_step=False, |
| logging_nan_inf_filter=True, |
| logging_steps=1, |
| logging_strategy=IntervalStrategy.STEPS, |
| lr_scheduler_kwargs={'min_lr_rate': 0.1}, |
| lr_scheduler_type=SchedulerType.COSINE_WITH_MIN_LR, |
| max_grad_norm=1.0, |
| max_length=4096, |
| max_seq_length=None, |
| max_steps=-1, |
| metric_for_best_model=None, |
| model_init_kwargs=None, |
| mp_parameters=, |
| neftune_noise_alpha=None, |
| no_cuda=False, |
| num_of_sequences=None, |
| num_train_epochs=1, |
| optim=OptimizerNames.ADAMW_TORCH, |
| optim_args=None, |
| optim_target_modules=None, |
| output_dir=/tmp/data/Qwen1.5-MOE/aux_free_sft/math7k/1e-3-gamma, |
| overwrite_hub_revision=False, |
| overwrite_output_dir=True, |
| packing=False, |
| past_index=-1, |
| per_device_eval_batch_size=16, |
| per_device_train_batch_size=4, |
| prediction_loss_only=False, |
| push_to_hub=True, |
| push_to_hub_model_id=None, |
| push_to_hub_organization=None, |
| push_to_hub_revision=False, |
| push_to_hub_token=<PUSH_TO_HUB_TOKEN>, |
| ray_scope=last, |
| remove_unused_columns=True, |
| report_to=['wandb'], |
| restore_callback_states_from_checkpoint=False, |
| resume_from_checkpoint=None, |
| run_name=/tmp/data/Qwen1.5-MOE/aux_free_sft/math7k/1e-3-gamma, |
| save_on_each_node=False, |
| save_only_model=False, |
| save_safetensors=True, |
| save_steps=500, |
| save_strategy=SaveStrategy.EPOCH, |
| save_total_limit=1, |
| seed=1234, |
| skip_memory_metrics=True, |
| system_prompt=None, |
| tf32=None, |
| torch_compile=False, |
| torch_compile_backend=None, |
| torch_compile_mode=None, |
| torch_empty_cache_steps=None, |
| torchdynamo=None, |
| tp_size=0, |
| tpu_metrics_debug=False, |
| tpu_num_cores=None, |
| use_cpu=False, |
| use_ipex=False, |
| use_legacy_prediction_loop=False, |
| use_liger=False, |
| use_liger_kernel=False, |
| use_mps_device=False, |
| wandb_entity=None, |
| wandb_project=None, |
| warmup_ratio=0.1, |
| warmup_steps=0, |
| weight_decay=0.0, |
| ) |
| 2025-09-15 01:49:29 - INFO - __main__ - *** Initializing model kwargs *** |
| 2025-09-15 01:49:40 - INFO - __main__ - *** Train *** |
| 2025-09-15 01:49:40 - INFO - __main__ - Qwen2MoeForCausalLM( |
| (model): Qwen2MoeModel( |
| (embed_tokens): Embedding(151936, 2048) |
| (layers): ModuleList( |
| (0-23): 24 x Qwen2MoeDecoderLayer( |
| (self_attn): Qwen2MoeFlashAttention2( |
| (q_proj): Linear(in_features=2048, out_features=2048, bias=True) |
| (k_proj): Linear(in_features=2048, out_features=2048, bias=True) |
| (v_proj): Linear(in_features=2048, out_features=2048, bias=True) |
| (o_proj): Linear(in_features=2048, out_features=2048, bias=False) |
| (rotary_emb): Qwen2MoeRotaryEmbedding() |
| ) |
| (mlp): Qwen2MoeSparseMoeBlock( |
| (gate): Linear(in_features=2048, out_features=60, bias=False) |
| (experts): ModuleList( |
| (0-59): 60 x Qwen2MoeMLP( |
| (gate_proj): Linear(in_features=2048, out_features=1408, bias=False) |
| (up_proj): Linear(in_features=2048, out_features=1408, bias=False) |
| (down_proj): Linear(in_features=1408, out_features=2048, bias=False) |
| (act_fn): SiLU() |
| ) |
| ) |
| (shared_expert): Qwen2MoeMLP( |
| (gate_proj): Linear(in_features=2048, out_features=5632, bias=False) |
| (up_proj): Linear(in_features=2048, out_features=5632, bias=False) |
| (down_proj): Linear(in_features=5632, out_features=2048, bias=False) |
| (act_fn): SiLU() |
| ) |
| (shared_expert_gate): Linear(in_features=2048, out_features=1, bias=False) |
| ) |
| (input_layernorm): Qwen2MoeRMSNorm((2048,), eps=1e-06) |
| (post_attention_layernorm): Qwen2MoeRMSNorm((2048,), eps=1e-06) |
| ) |
| ) |
| (norm): Qwen2MoeRMSNorm((2048,), eps=1e-06) |
| (rotary_emb): Qwen2MoeRotaryEmbedding() |
| ) |
| (lm_head): Linear(in_features=2048, out_features=151936, bias=False) |
| ) |
| 2025-09-15 02:07:52 - INFO - __main__ - *** Save model *** |
| 2025-09-15 02:07:52 - INFO - __main__ - 💾 Saving MoE bias states... |
| 2025-09-15 02:07:52 - INFO - __main__ - 🔍 Searching for MoE layers with bias states... |
| 2025-09-15 02:07:52 - INFO - __main__ - ✅ Saved bias from model.layers.0.mlp: 60 experts, update_speed=0.001000 |
| 2025-09-15 02:07:52 - INFO - __main__ - ✅ Saved bias from model.layers.1.mlp: 60 experts, update_speed=0.001000 |
| 2025-09-15 02:07:52 - INFO - __main__ - ✅ Saved bias from model.layers.2.mlp: 60 experts, update_speed=0.001000 |
| 2025-09-15 02:07:52 - INFO - __main__ - ✅ Saved bias from model.layers.3.mlp: 60 experts, update_speed=0.001000 |
| 2025-09-15 02:07:52 - INFO - __main__ - ✅ Saved bias from model.layers.4.mlp: 60 experts, update_speed=0.001000 |
| 2025-09-15 02:07:52 - INFO - __main__ - ✅ Saved bias from model.layers.5.mlp: 60 experts, update_speed=0.001000 |
| 2025-09-15 02:07:52 - INFO - __main__ - ✅ Saved bias from model.layers.6.mlp: 60 experts, update_speed=0.001000 |
| 2025-09-15 02:07:52 - INFO - __main__ - ✅ Saved bias from model.layers.7.mlp: 60 experts, update_speed=0.001000 |
| 2025-09-15 02:07:52 - INFO - __main__ - ✅ Saved bias from model.layers.8.mlp: 60 experts, update_speed=0.001000 |
| 2025-09-15 02:07:52 - INFO - __main__ - ✅ Saved bias from model.layers.9.mlp: 60 experts, update_speed=0.001000 |
| 2025-09-15 02:07:52 - INFO - __main__ - ✅ Saved bias from model.layers.10.mlp: 60 experts, update_speed=0.001000 |
| 2025-09-15 02:07:52 - INFO - __main__ - ✅ Saved bias from model.layers.11.mlp: 60 experts, update_speed=0.001000 |
| 2025-09-15 02:07:52 - INFO - __main__ - ✅ Saved bias from model.layers.12.mlp: 60 experts, update_speed=0.001000 |
| 2025-09-15 02:07:52 - INFO - __main__ - ✅ Saved bias from model.layers.13.mlp: 60 experts, update_speed=0.001000 |
| 2025-09-15 02:07:52 - INFO - __main__ - ✅ Saved bias from model.layers.14.mlp: 60 experts, update_speed=0.001000 |
| 2025-09-15 02:07:52 - INFO - __main__ - ✅ Saved bias from model.layers.15.mlp: 60 experts, update_speed=0.001000 |
| 2025-09-15 02:07:52 - INFO - __main__ - ✅ Saved bias from model.layers.16.mlp: 60 experts, update_speed=0.001000 |
| 2025-09-15 02:07:52 - INFO - __main__ - ✅ Saved bias from model.layers.17.mlp: 60 experts, update_speed=0.001000 |
| 2025-09-15 02:07:52 - INFO - __main__ - ✅ Saved bias from model.layers.18.mlp: 60 experts, update_speed=0.001000 |
| 2025-09-15 02:07:52 - INFO - __main__ - ✅ Saved bias from model.layers.19.mlp: 60 experts, update_speed=0.001000 |
| 2025-09-15 02:07:52 - INFO - __main__ - ✅ Saved bias from model.layers.20.mlp: 60 experts, update_speed=0.001000 |
| 2025-09-15 02:07:52 - INFO - __main__ - ✅ Saved bias from model.layers.21.mlp: 60 experts, update_speed=0.001000 |
| 2025-09-15 02:07:52 - INFO - __main__ - ✅ Saved bias from model.layers.22.mlp: 60 experts, update_speed=0.001000 |
| 2025-09-15 02:07:52 - INFO - __main__ - ✅ Saved bias from model.layers.23.mlp: 60 experts, update_speed=0.001000 |
| 2025-09-15 02:07:52 - INFO - __main__ - 🎉 Successfully saved 24 MoE bias states to /tmp/data/Qwen1.5-MOE/aux_free_sft/math7k/1e-3-gamma/moe_bias_states.json |
| 2025-09-15 02:07:52 - INFO - __main__ - 📊 Bias States Summary: |
| 2025-09-15 02:07:52 - INFO - __main__ - model.layers.0.mlp: 60 experts, range=[-0.5000, 0.5000] |
| 2025-09-15 02:07:52 - INFO - __main__ - model.layers.1.mlp: 60 experts, range=[-0.5000, 0.5000] |
| 2025-09-15 02:07:52 - INFO - __main__ - model.layers.2.mlp: 60 experts, range=[-0.5000, 0.5000] |
| 2025-09-15 02:07:52 - INFO - __main__ - model.layers.3.mlp: 60 experts, range=[-0.5000, 0.5000] |
| 2025-09-15 02:07:52 - INFO - __main__ - model.layers.4.mlp: 60 experts, range=[-0.5000, 0.5000] |
| 2025-09-15 02:07:52 - INFO - __main__ - model.layers.5.mlp: 60 experts, range=[-0.5000, 0.5000] |
| 2025-09-15 02:07:52 - INFO - __main__ - model.layers.6.mlp: 60 experts, range=[-0.5000, 0.5000] |
| 2025-09-15 02:07:52 - INFO - __main__ - model.layers.7.mlp: 60 experts, range=[-0.5000, 0.5000] |
| 2025-09-15 02:07:52 - INFO - __main__ - model.layers.8.mlp: 60 experts, range=[-0.5000, 0.5000] |
| 2025-09-15 02:07:52 - INFO - __main__ - model.layers.9.mlp: 60 experts, range=[-0.5000, 0.5000] |
| 2025-09-15 02:07:52 - INFO - __main__ - model.layers.10.mlp: 60 experts, range=[-0.5000, 0.5000] |
| 2025-09-15 02:07:52 - INFO - __main__ - model.layers.11.mlp: 60 experts, range=[-0.5000, 0.5000] |
| 2025-09-15 02:07:52 - INFO - __main__ - model.layers.12.mlp: 60 experts, range=[-0.5000, 0.5000] |
| 2025-09-15 02:07:52 - INFO - __main__ - model.layers.13.mlp: 60 experts, range=[-0.5000, 0.5000] |
| 2025-09-15 02:07:52 - INFO - __main__ - model.layers.14.mlp: 60 experts, range=[-0.5000, 0.5000] |
| 2025-09-15 02:07:52 - INFO - __main__ - model.layers.15.mlp: 60 experts, range=[-0.5000, 0.5000] |
| 2025-09-15 02:07:52 - INFO - __main__ - model.layers.16.mlp: 60 experts, range=[-0.5000, 0.5000] |
| 2025-09-15 02:07:52 - INFO - __main__ - model.layers.17.mlp: 60 experts, range=[-0.5000, 0.5000] |
| 2025-09-15 02:07:52 - INFO - __main__ - model.layers.18.mlp: 60 experts, range=[-0.5000, 0.5000] |
| 2025-09-15 02:07:52 - INFO - __main__ - model.layers.19.mlp: 60 experts, range=[-0.5000, 0.5000] |
| 2025-09-15 02:07:52 - INFO - __main__ - model.layers.20.mlp: 60 experts, range=[-0.5000, 0.5000] |
| 2025-09-15 02:07:52 - INFO - __main__ - model.layers.21.mlp: 60 experts, range=[-0.5000, 0.5000] |
| 2025-09-15 02:07:52 - INFO - __main__ - model.layers.22.mlp: 60 experts, range=[-0.5000, 0.5000] |
| 2025-09-15 02:07:52 - INFO - __main__ - model.layers.23.mlp: 60 experts, range=[-0.5000, 0.5000] |
| 2025-09-15 02:09:35 - INFO - __main__ - Model saved to /tmp/data/Qwen1.5-MOE/aux_free_sft/math7k/1e-3-gamma |
| 2025-09-15 02:09:35 - INFO - __main__ - Pushing to hub... |
|
|
