| { | |
| "best_global_step": 500, | |
| "best_metric": 1.0, | |
| "best_model_checkpoint": "experiments/combined/checkpoint-500", | |
| "epoch": 0.9652509652509652, | |
| "eval_steps": 500, | |
| "global_step": 500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.19305019305019305, | |
| "grad_norm": 2.48384165763855, | |
| "learning_rate": 1.2692307692307693e-05, | |
| "loss": 0.4237, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.3861003861003861, | |
| "grad_norm": 6.34004020690918, | |
| "learning_rate": 1.938483547925608e-05, | |
| "loss": 0.2115, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.5791505791505791, | |
| "grad_norm": 0.6042028665542603, | |
| "learning_rate": 1.795422031473534e-05, | |
| "loss": 0.1104, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.7722007722007722, | |
| "grad_norm": 0.008698650635778904, | |
| "learning_rate": 1.6523605150214594e-05, | |
| "loss": 0.0005, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.9652509652509652, | |
| "grad_norm": 20.775955200195312, | |
| "learning_rate": 1.509298998569385e-05, | |
| "loss": 0.0041, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.9652509652509652, | |
| "eval_accuracy": 1.0, | |
| "eval_f1": 1.0, | |
| "eval_loss": 4.6818098780931905e-05, | |
| "eval_precision": 1.0, | |
| "eval_recall": 1.0, | |
| "eval_runtime": 52.5745, | |
| "eval_samples_per_second": 8.749, | |
| "eval_steps_per_second": 0.285, | |
| "step": 500 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 1554, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 3, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 263111055360000.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |