{ "best_metric": 0.5438473456606133, "best_model_checkpoint": "students_scores_model/run-1/checkpoint-563", "epoch": 1.0, "eval_steps": 500, "global_step": 563, "is_hyper_param_search": true, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.8880994671403197, "grad_norm": 16.69457244873047, "learning_rate": 1.3821787207411013e-05, "loss": 1.0782, "step": 500 }, { "epoch": 1.0, "eval_f1": 0.5438473456606133, "eval_loss": 1.0308393239974976, "eval_runtime": 37.8021, "eval_samples_per_second": 59.52, "eval_steps_per_second": 7.46, "step": 563 } ], "logging_steps": 500, "max_steps": 1689, "num_input_tokens_seen": 0, "num_train_epochs": 3, "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": 2104964038656000.0, "train_batch_size": 16, "trial_name": null, "trial_params": { "learning_rate": 1.9634145158382844e-05, "num_train_epochs": 3, "per_device_train_batch_size": 16, "weight_decay": 0.000263763325616835 } }