| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.397428731134712, | |
| "global_step": 5000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 4.767095211477548e-05, | |
| "loss": 1.857, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 4.534190422955096e-05, | |
| "loss": 1.3144, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 4.3012856344326444e-05, | |
| "loss": 1.1611, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 4.068380845910192e-05, | |
| "loss": 1.1358, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 3.83547605738774e-05, | |
| "loss": 1.0834, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 3.602571268865288e-05, | |
| "loss": 1.119, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 3.369666480342836e-05, | |
| "loss": 1.034, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 3.136761691820384e-05, | |
| "loss": 1.0446, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 2.9038569032979318e-05, | |
| "loss": 0.9639, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 2.67095211477548e-05, | |
| "loss": 0.9842, | |
| "step": 5000 | |
| } | |
| ], | |
| "max_steps": 10734, | |
| "num_train_epochs": 3, | |
| "total_flos": 4116025439944704.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |