| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 10.0, | |
| "global_step": 3950, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 4.367088607594937e-05, | |
| "loss": 2.4363, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "learning_rate": 3.7341772151898736e-05, | |
| "loss": 1.116, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 3.8, | |
| "learning_rate": 3.10126582278481e-05, | |
| "loss": 1.01, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 5.06, | |
| "learning_rate": 2.468354430379747e-05, | |
| "loss": 0.9391, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 6.33, | |
| "learning_rate": 1.8354430379746836e-05, | |
| "loss": 0.8992, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 7.59, | |
| "learning_rate": 1.2025316455696203e-05, | |
| "loss": 0.8633, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 8.86, | |
| "learning_rate": 5.69620253164557e-06, | |
| "loss": 0.8607, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "step": 3950, | |
| "total_flos": 2202692316364800.0, | |
| "train_loss": 1.1242135581487342, | |
| "train_runtime": 508.9786, | |
| "train_samples_per_second": 124.131, | |
| "train_steps_per_second": 7.761 | |
| } | |
| ], | |
| "max_steps": 3950, | |
| "num_train_epochs": 10, | |
| "total_flos": 2202692316364800.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |