{ "best_metric": 2.0724549293518066, "best_model_checkpoint": "satriadata/run-0/checkpoint-25", "epoch": 1.0, "eval_steps": 500, "global_step": 25, "is_hyper_param_search": true, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 1.0, "eval_f1": 0.1636422261948578, "eval_loss": 2.0724549293518066, "eval_runtime": 1.5492, "eval_samples_per_second": 64.55, "eval_steps_per_second": 4.519, "step": 25 } ], "logging_steps": 500, "max_steps": 125, "num_input_tokens_seen": 0, "num_train_epochs": 5, "save_steps": 500, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 0, "train_batch_size": 16, "trial_name": null, "trial_params": { "gradient_accumulation_steps": 1, "learning_rate": 1.4430981363245122e-05, "num_train_epochs": 5, "optimizer": "sgd", "warmup_ratio": 0.3, "weight_decay": 0.0 } }