| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 263.1578947368421, | |
| "global_step": 5000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 26.32, | |
| "learning_rate": 2.5e-05, | |
| "loss": 0.2555, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 52.63, | |
| "learning_rate": 2.2222222222222223e-05, | |
| "loss": 0.1603, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 78.95, | |
| "learning_rate": 1.9444444444444445e-05, | |
| "loss": 0.1074, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 105.26, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 0.0881, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 131.58, | |
| "learning_rate": 1.388888888888889e-05, | |
| "loss": 0.0761, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 157.89, | |
| "learning_rate": 1.1111111111111112e-05, | |
| "loss": 0.0678, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 184.21, | |
| "learning_rate": 8.333333333333334e-06, | |
| "loss": 0.0619, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 210.53, | |
| "learning_rate": 5.555555555555556e-06, | |
| "loss": 0.0583, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 236.84, | |
| "learning_rate": 2.777777777777778e-06, | |
| "loss": 0.0549, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 263.16, | |
| "learning_rate": 0.0, | |
| "loss": 0.0543, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 263.16, | |
| "step": 5000, | |
| "total_flos": 3.53160818688e+16, | |
| "train_runtime": 2716.3773, | |
| "train_samples_per_second": 1.841 | |
| } | |
| ], | |
| "max_steps": 5000, | |
| "num_train_epochs": 264, | |
| "total_flos": 3.53160818688e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |