| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 10.0, | |
| "global_step": 5460, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 1.816849816849817e-05, | |
| "loss": 0.2816, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 1.633699633699634e-05, | |
| "loss": 0.1677, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.75, | |
| "learning_rate": 1.4505494505494506e-05, | |
| "loss": 0.114, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 3.66, | |
| "learning_rate": 1.2673992673992674e-05, | |
| "loss": 0.0777, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 4.58, | |
| "learning_rate": 1.0842490842490842e-05, | |
| "loss": 0.0569, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 5.49, | |
| "learning_rate": 9.010989010989011e-06, | |
| "loss": 0.04, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 6.41, | |
| "learning_rate": 7.17948717948718e-06, | |
| "loss": 0.0314, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 7.33, | |
| "learning_rate": 5.347985347985348e-06, | |
| "loss": 0.0206, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 8.24, | |
| "learning_rate": 3.516483516483517e-06, | |
| "loss": 0.0171, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 9.16, | |
| "learning_rate": 1.6849816849816852e-06, | |
| "loss": 0.0119, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "step": 5460, | |
| "total_flos": 2.8586235178707456e+17, | |
| "train_loss": 0.07572162915498783, | |
| "train_runtime": 4508.6421, | |
| "train_samples_per_second": 232.316, | |
| "train_steps_per_second": 1.211 | |
| } | |
| ], | |
| "max_steps": 5460, | |
| "num_train_epochs": 10, | |
| "total_flos": 2.8586235178707456e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |