| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0, | |
| "global_step": 1500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 0.2387, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.954995499549955, | |
| "eval_f1": 0.9358974358974359, | |
| "eval_loss": 0.16049383580684662, | |
| "eval_precision": 0.9972677595628415, | |
| "eval_recall": 0.8816425120772947, | |
| "eval_runtime": 19.741, | |
| "eval_samples_per_second": 56.279, | |
| "eval_steps_per_second": 7.041, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 0.0872, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.9936993699369937, | |
| "eval_f1": 0.991494532199271, | |
| "eval_loss": 0.020622961223125458, | |
| "eval_precision": 0.9975550122249389, | |
| "eval_recall": 0.9855072463768116, | |
| "eval_runtime": 15.1133, | |
| "eval_samples_per_second": 73.511, | |
| "eval_steps_per_second": 9.197, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 0.0, | |
| "loss": 0.0226, | |
| "step": 1500 | |
| } | |
| ], | |
| "max_steps": 1500, | |
| "num_train_epochs": 3, | |
| "total_flos": 3157332664320000.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |