| { | |
| "best_metric": 0.626596640291279, | |
| "best_model_checkpoint": "students_scores_model/run-1/checkpoint-1128", | |
| "epoch": 4.0, | |
| "eval_steps": 500, | |
| "global_step": 1128, | |
| "is_hyper_param_search": true, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_f1": 0.49162421787585286, | |
| "eval_loss": 1.09846031665802, | |
| "eval_runtime": 37.7448, | |
| "eval_samples_per_second": 59.611, | |
| "eval_steps_per_second": 7.471, | |
| "step": 282 | |
| }, | |
| { | |
| "epoch": 1.773049645390071, | |
| "grad_norm": 8.43077564239502, | |
| "learning_rate": 1.4687315682489477e-05, | |
| "loss": 1.0146, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_f1": 0.5968612549522194, | |
| "eval_loss": 0.9038913249969482, | |
| "eval_runtime": 37.6284, | |
| "eval_samples_per_second": 59.795, | |
| "eval_steps_per_second": 7.494, | |
| "step": 564 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_f1": 0.60670227423826, | |
| "eval_loss": 0.919843316078186, | |
| "eval_runtime": 37.6908, | |
| "eval_samples_per_second": 59.696, | |
| "eval_steps_per_second": 7.482, | |
| "step": 846 | |
| }, | |
| { | |
| "epoch": 3.546099290780142, | |
| "grad_norm": 27.95517349243164, | |
| "learning_rate": 6.617362010791962e-06, | |
| "loss": 0.7766, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_f1": 0.626596640291279, | |
| "eval_loss": 0.8775350451469421, | |
| "eval_runtime": 37.7332, | |
| "eval_samples_per_second": 59.629, | |
| "eval_steps_per_second": 7.474, | |
| "step": 1128 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 1410, | |
| "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": 8400122116761600.0, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": { | |
| "learning_rate": 2.275726935418699e-05, | |
| "num_train_epochs": 5, | |
| "per_device_train_batch_size": 32, | |
| "weight_decay": 0.0002055903667746397 | |
| } | |
| } | |