| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 5.0, | |
| "eval_steps": 500, | |
| "global_step": 2815, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 1.6000000000000003e-05, | |
| "loss": 3.3692, | |
| "step": 563 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.872, | |
| "eval_f1": 0.856009752654711, | |
| "eval_loss": 3.21221923828125, | |
| "eval_runtime": 16.3666, | |
| "eval_samples_per_second": 61.1, | |
| "eval_steps_per_second": 3.849, | |
| "step": 563 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 1.2e-05, | |
| "loss": 3.0963, | |
| "step": 1126 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.866, | |
| "eval_f1": 0.8624612482571968, | |
| "eval_loss": 3.1044771671295166, | |
| "eval_runtime": 16.3224, | |
| "eval_samples_per_second": 61.265, | |
| "eval_steps_per_second": 3.86, | |
| "step": 1126 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 2.8698, | |
| "step": 1689 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.882, | |
| "eval_f1": 0.8755033031176542, | |
| "eval_loss": 3.1409871578216553, | |
| "eval_runtime": 16.3796, | |
| "eval_samples_per_second": 61.051, | |
| "eval_steps_per_second": 3.846, | |
| "step": 1689 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 2.6212, | |
| "step": 2252 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.876, | |
| "eval_f1": 0.8701998582565557, | |
| "eval_loss": 3.2119336128234863, | |
| "eval_runtime": 16.3349, | |
| "eval_samples_per_second": 61.219, | |
| "eval_steps_per_second": 3.857, | |
| "step": 2252 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 0.0, | |
| "loss": 2.407, | |
| "step": 2815 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.885, | |
| "eval_f1": 0.8788301734570391, | |
| "eval_loss": 3.269321918487549, | |
| "eval_runtime": 16.3269, | |
| "eval_samples_per_second": 61.249, | |
| "eval_steps_per_second": 3.859, | |
| "step": 2815 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "step": 2815, | |
| "total_flos": 4.169197960165814e+16, | |
| "train_loss": 2.8726869085118785, | |
| "train_runtime": 3265.1327, | |
| "train_samples_per_second": 13.782, | |
| "train_steps_per_second": 0.862 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 2815, | |
| "num_train_epochs": 5, | |
| "save_steps": 500, | |
| "total_flos": 4.169197960165814e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |