| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.0, | |
| "global_step": 3690, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 0.00010380487804878049, | |
| "loss": 1.6958, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 8.754471544715447e-05, | |
| "loss": 1.2224, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 7.131707317073172e-05, | |
| "loss": 1.1216, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 5.505691056910569e-05, | |
| "loss": 0.9498, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 3.879674796747968e-05, | |
| "loss": 0.6827, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "learning_rate": 2.2536585365853658e-05, | |
| "loss": 0.67, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 6.308943089430894e-06, | |
| "loss": 0.6376, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "step": 3690, | |
| "total_flos": 3.4696551139946496e+16, | |
| "train_loss": 0.9778929547565739, | |
| "train_runtime": 1893.4781, | |
| "train_samples_per_second": 93.504, | |
| "train_steps_per_second": 1.949 | |
| } | |
| ], | |
| "max_steps": 3690, | |
| "num_train_epochs": 2, | |
| "total_flos": 3.4696551139946496e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |