2025-03-31 14:28:07 - INFO - __main__ - Model parameters ModelConfig(model_name_or_path='Qwen/Qwen2.5-1.5B-Instruct', model_revision='main', torch_dtype='bfloat16', trust_remote_code=False, 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) 2025-03-31 14:28:07 - INFO - __main__ - Script parameters ScriptArguments(dataset_name='open-r1/OpenR1-Math-220k', dataset_config=None, dataset_train_split='train', dataset_test_split='test', gradient_checkpointing_use_reentrant=False, ignore_bias_buffers=False) 2025-03-31 14:28:07 - 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=, 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=8, dataset_text_field=text, ddp_backend=None, ddp_broadcast_buffers=None, ddp_bucket_cap_mb=None, ddp_find_unused_parameters=None, ddp_timeout=1800, debug=[], deepspeed=None, disable_tqdm=False, dispatch_batches=None, do_eval=False, 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, evaluation_strategy=None, 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=Qwen2.5-1.5B-Open-R1-Distill, hub_model_revision=main, hub_private_repo=None, hub_strategy=HubStrategy.EVERY_SAVE, 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=5e-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=data/Qwen2.5-1.5B-Open-R1-Distill/runs/Mar31_14-28-06_w004.ib.bridges2.psc.edu, logging_first_step=False, logging_nan_inf_filter=True, logging_steps=5, 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=16384, 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=data/Qwen2.5-1.5B-Open-R1-Distill, overwrite_hub_revision=False, overwrite_output_dir=True, packing=True, past_index=-1, per_device_eval_batch_size=16, per_device_train_batch_size=16, 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=, ray_scope=last, remove_unused_columns=True, report_to=['wandb'], restore_callback_states_from_checkpoint=False, resume_from_checkpoint=None, run_name=data/Qwen2.5-1.5B-Open-R1-Distill, save_on_each_node=False, save_only_model=False, save_safetensors=True, save_steps=100, save_strategy=SaveStrategy.STEPS, save_total_limit=1, seed=42, skip_memory_metrics=True, split_batches=None, system_prompt=None, tf32=None, torch_compile=False, torch_compile_backend=None, torch_compile_mode=None, torch_empty_cache_steps=None, torchdynamo=None, tpu_metrics_debug=False, tpu_num_cores=None, use_cpu=False, use_ipex=False, use_legacy_prediction_loop=False, use_liger=True, use_liger_kernel=False, use_mps_device=False, wandb_entity=None, wandb_project=None, warmup_ratio=0.05, warmup_steps=0, weight_decay=0.0, ) 2025-03-31 14:28:09 - INFO - __main__ - *** Initializing model kwargs *** 2025-03-31 14:28:57 - INFO - __main__ - *** Train *** 2025-03-31 14:58:16 - INFO - __main__ - Model parameters ModelConfig(model_name_or_path='Qwen/Qwen2.5-1.5B-Instruct', model_revision='main', torch_dtype='bfloat16', trust_remote_code=False, 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) 2025-03-31 14:58:16 - INFO - __main__ - Script parameters ScriptArguments(dataset_name='open-r1/OpenR1-Math-220k', dataset_config=None, dataset_train_split='train', dataset_test_split='test', gradient_checkpointing_use_reentrant=False, ignore_bias_buffers=False) 2025-03-31 14:58:16 - 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=, 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=8, dataset_text_field=text, ddp_backend=None, ddp_broadcast_buffers=None, ddp_bucket_cap_mb=None, ddp_find_unused_parameters=None, ddp_timeout=1800, debug=[], deepspeed=None, disable_tqdm=False, dispatch_batches=None, do_eval=False, 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, evaluation_strategy=None, 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=Qwen2.5-1.5B-Open-R1-Distill, hub_model_revision=main, hub_private_repo=None, hub_strategy=HubStrategy.EVERY_SAVE, 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=5e-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=data/Qwen2.5-1.5B-Open-R1-Distill/runs/Mar31_14-58-15_w004.ib.bridges2.psc.edu, logging_first_step=False, logging_nan_inf_filter=True, logging_steps=5, 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=16384, 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=data/Qwen2.5-1.5B-Open-R1-Distill, overwrite_hub_revision=False, overwrite_output_dir=True, packing=True, past_index=-1, per_device_eval_batch_size=16, per_device_train_batch_size=16, 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=, ray_scope=last, remove_unused_columns=True, report_to=['wandb'], restore_callback_states_from_checkpoint=False, resume_from_checkpoint=None, run_name=data/Qwen2.5-1.5B-Open-R1-Distill, save_on_each_node=False, save_only_model=False, save_safetensors=True, save_steps=100, save_strategy=SaveStrategy.STEPS, save_total_limit=1, seed=42, skip_memory_metrics=True, split_batches=None, system_prompt=None, tf32=None, torch_compile=False, torch_compile_backend=None, torch_compile_mode=None, torch_empty_cache_steps=None, torchdynamo=None, tpu_metrics_debug=False, tpu_num_cores=None, use_cpu=False, use_ipex=False, use_legacy_prediction_loop=False, use_liger=True, use_liger_kernel=False, use_mps_device=False, wandb_entity=None, wandb_project=None, warmup_ratio=0.05, warmup_steps=0, weight_decay=0.0, ) 2025-03-31 14:58:16 - INFO - __main__ - Checkpoint detected, resuming training at last_checkpoint='data/Qwen2.5-1.5B-Open-R1-Distill/checkpoint-100'. 2025-03-31 14:58:17 - INFO - __main__ - *** Initializing model kwargs *** 2025-03-31 14:58:19 - INFO - __main__ - *** Train *** 2025-03-31 14:58:19 - INFO - __main__ - Qwen2ForCausalLM( (model): Qwen2Model( (embed_tokens): Embedding(151936, 1536) (layers): ModuleList( (0-27): 28 x Qwen2DecoderLayer( (self_attn): Qwen2Attention( (q_proj): Linear(in_features=1536, out_features=1536, bias=True) (k_proj): Linear(in_features=1536, out_features=256, bias=True) (v_proj): Linear(in_features=1536, out_features=256, bias=True) (o_proj): Linear(in_features=1536, out_features=1536, bias=False) ) (mlp): LigerSwiGLUMLP( (gate_proj): Linear(in_features=1536, out_features=8960, bias=False) (up_proj): Linear(in_features=1536, out_features=8960, bias=False) (down_proj): Linear(in_features=8960, out_features=1536, bias=False) ) (input_layernorm): LigerRMSNorm((0,), eps=1e-06, offset=0.0, in_place=True) (post_attention_layernorm): LigerRMSNorm((0,), eps=1e-06, offset=0.0, in_place=True) ) ) (norm): LigerRMSNorm((0,), eps=1e-06, offset=0.0, in_place=True) (rotary_emb): Qwen2RotaryEmbedding() ) (lm_head): Linear(in_features=1536, out_features=151936, bias=False) )