| 2025-11-11 11:24:34,344 - INFO - SFT Config: 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}, | |
| activation_offloading=False, | |
| adafactor=False, | |
| adam_beta1=0.9, | |
| adam_beta2=0.999, | |
| adam_epsilon=1e-08, | |
| assistant_only_loss=False, | |
| auto_find_batch_size=False, | |
| average_tokens_across_devices=True, | |
| batch_eval_metrics=True, | |
| bf16=False, | |
| bf16_full_eval=False, | |
| chat_template_path=None, | |
| completion_only_loss=True, | |
| data_seed=42, | |
| dataloader_drop_last=False, | |
| dataloader_num_workers=0, | |
| dataloader_persistent_workers=False, | |
| dataloader_pin_memory=True, | |
| dataloader_prefetch_factor=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=1800, | |
| debug=[], | |
| deepspeed=None, | |
| disable_tqdm=False, | |
| do_eval=True, | |
| do_predict=False, | |
| do_train=False, | |
| eos_token=<EOS_TOKEN>, | |
| eval_accumulation_steps=None, | |
| eval_delay=0, | |
| eval_do_concat_batches=True, | |
| eval_on_start=True, | |
| eval_packing=None, | |
| eval_steps=0.1, | |
| eval_strategy=IntervalStrategy.STEPS, | |
| 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=2, | |
| gradient_checkpointing=False, | |
| gradient_checkpointing_kwargs=None, | |
| greater_is_better=None, | |
| group_by_length=False, | |
| half_precision_backend=auto, | |
| hub_always_push=False, | |
| hub_model_id=None, | |
| hub_private_repo=False, | |
| hub_revision=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=no, | |
| include_tokens_per_second=False, | |
| jit_mode_eval=False, | |
| label_names=None, | |
| label_smoothing_factor=0.0, | |
| learning_rate=2e-05, | |
| length_column_name=length, | |
| liger_kernel_config=None, | |
| load_best_model_at_end=False, | |
| local_rank=0, | |
| log_level=info, | |
| log_level_replica=warning, | |
| log_on_each_node=True, | |
| logging_dir=./runs, | |
| logging_first_step=True, | |
| logging_nan_inf_filter=True, | |
| logging_steps=5, | |
| logging_strategy=IntervalStrategy.STEPS, | |
| loss_type=nll, | |
| lr_scheduler_kwargs={}, | |
| lr_scheduler_type=SchedulerType.COSINE, | |
| max_grad_norm=1.0, | |
| max_length=1024, | |
| max_steps=-1, | |
| metric_for_best_model=None, | |
| model_init_kwargs=None, | |
| mp_parameters=, | |
| neftune_noise_alpha=None, | |
| no_cuda=False, | |
| num_train_epochs=2, | |
| optim=OptimizerNames.ADAMW_TORCH_FUSED, | |
| optim_args=None, | |
| optim_target_modules=None, | |
| output_dir=./models, | |
| overwrite_output_dir=False, | |
| packing=False, | |
| packing_strategy=bfd, | |
| pad_to_multiple_of=None, | |
| pad_token=<PAD_TOKEN>, | |
| padding_free=False, | |
| parallelism_config=None, | |
| past_index=-1, | |
| per_device_eval_batch_size=6, | |
| per_device_train_batch_size=6, | |
| prediction_loss_only=False, | |
| project=huggingface, | |
| push_to_hub=False, | |
| push_to_hub_model_id=None, | |
| push_to_hub_organization=None, | |
| push_to_hub_token=<PUSH_TO_HUB_TOKEN>, | |
| ray_scope=last, | |
| remove_unused_columns=True, | |
| report_to=['tensorboard'], | |
| restore_callback_states_from_checkpoint=False, | |
| resume_from_checkpoint=None, | |
| run_name=None, | |
| save_on_each_node=False, | |
| save_only_model=False, | |
| save_safetensors=True, | |
| save_steps=0.1, | |
| save_strategy=SaveStrategy.STEPS, | |
| save_total_limit=3, | |
| seed=42, | |
| skip_memory_metrics=True, | |
| 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, | |
| trackio_space_id=trackio, | |
| use_cpu=False, | |
| use_legacy_prediction_loop=False, | |
| use_liger_kernel=False, | |
| use_mps_device=False, | |
| warmup_ratio=0.05, | |
| warmup_steps=0, | |
| weight_decay=0.01, | |
| ) | |
| 2025-11-11 11:24:34,344 - INFO - Data Config: data_train_path='./data/train_sft_data.jsonl' data_dev_path='./data/dev_preprocessed_human.jsonl' data_test_path='./data/test_preprocessed_human.jsonl' db_train_path='./data/train.db' db_dev_path='./data/dev.db' db_test_path='./data/test.db' do_sample_train=False do_sample_dev=False do_sample_test=False n_sample_train=200 n_sample_dev=50 n_sample_test=50 | |
| 2025-11-11 11:25:42,178 - INFO - Starting full pipeline. | |
| 2025-11-11 11:25:42,178 - INFO - Training model... | |
| 2025-11-11 13:23:39,551 - INFO - Training completed. | |
| 2025-11-11 13:47:01,198 - INFO - Final Dev Metrics: {'lf_accuracy': 0.7649813858532485, 'execution_accuracy': 0.8046115047436051} | |
| 2025-11-11 13:47:01,198 - INFO - Running final test evaluation... | |
| 2025-11-11 14:31:11,980 - INFO - Test Metrics: {'lf_accuracy': 0.7681140965236215, 'execution_accuracy': 0.807143766713358} | |
| 2025-11-11 14:31:11,980 - INFO - Final Test Metrics: {'lf_accuracy': 0.7681140965236215, 'execution_accuracy': 0.807143766713358} | |