| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 5000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 5e-05, | |
| "loss": 4.7743, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 4.4444444444444447e-05, | |
| "loss": 4.246, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 3.888888888888889e-05, | |
| "loss": 4.0284, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 3.8618, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 2.777777777777778e-05, | |
| "loss": 3.7563, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 2.2222222222222223e-05, | |
| "loss": 3.7115, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 3.6593, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 1.1111111111111112e-05, | |
| "loss": 3.5533, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 5.555555555555556e-06, | |
| "loss": 3.5842, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 0.0, | |
| "loss": 3.5502, | |
| "step": 5000 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 5000, | |
| "num_train_epochs": 1, | |
| "save_steps": 500, | |
| "total_flos": 2612920320000000.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |