{ "best_metric": 0.6268681418752026, "best_model_checkpoint": "students_scores_model/run-4/checkpoint-1126", "epoch": 3.0, "eval_steps": 500, "global_step": 1689, "is_hyper_param_search": true, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.8880994671403197, "grad_norm": 12.275317192077637, "learning_rate": 1.4598246141554418e-05, "loss": 1.0768, "step": 500 }, { "epoch": 1.0, "eval_f1": 0.5337342004113407, "eval_loss": 1.0920056104660034, "eval_runtime": 37.5701, "eval_samples_per_second": 59.888, "eval_steps_per_second": 7.506, "step": 563 }, { "epoch": 1.7761989342806395, "grad_norm": 22.032495498657227, "learning_rate": 1.1445277212492988e-05, "loss": 0.881, "step": 1000 }, { "epoch": 2.0, "eval_f1": 0.6268681418752026, "eval_loss": 0.8564010858535767, "eval_runtime": 37.4689, "eval_samples_per_second": 60.05, "eval_steps_per_second": 7.526, "step": 1126 }, { "epoch": 2.664298401420959, "grad_norm": 14.71834945678711, "learning_rate": 8.29230828343156e-06, "loss": 0.775, "step": 1500 }, { "epoch": 3.0, "eval_f1": 0.5967192597885715, "eval_loss": 0.9332024455070496, "eval_runtime": 37.6856, "eval_samples_per_second": 59.705, "eval_steps_per_second": 7.483, "step": 1689 } ], "logging_steps": 500, "max_steps": 2815, "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": 6310155946881024.0, "train_batch_size": 16, "trial_name": null, "trial_params": { "learning_rate": 1.7751215070615847e-05, "num_train_epochs": 5, "per_device_train_batch_size": 16, "weight_decay": 0.0002884204184667258 } }