| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 4500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 8.888888888888888e-06, | |
| "loss": 2.4115, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 7.77777777777778e-06, | |
| "loss": 1.8379, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 6.666666666666667e-06, | |
| "loss": 1.548, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 5.555555555555557e-06, | |
| "loss": 1.462, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 4.444444444444444e-06, | |
| "loss": 1.4512, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 3.3333333333333333e-06, | |
| "loss": 1.4267, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 2.222222222222222e-06, | |
| "loss": 1.3252, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 1.111111111111111e-06, | |
| "loss": 1.3507, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 0.0, | |
| "loss": 1.3253, | |
| "step": 4500 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 4500, | |
| "num_train_epochs": 1, | |
| "save_steps": 300, | |
| "total_flos": 2.024400132027187e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |