| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "global_step": 31, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.00012858017786751834, | |
| "loss": 2.7498, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 0.00010488693110842961, | |
| "loss": 2.6566, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 7.207453298233569e-05, | |
| "loss": 2.5558, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 3.838896120314628e-05, | |
| "loss": 2.2366, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 1.2295627933180862e-05, | |
| "loss": 2.4233, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 3.519644153159924e-07, | |
| "loss": 2.3992, | |
| "step": 30 | |
| } | |
| ], | |
| "max_steps": 31, | |
| "num_train_epochs": 1, | |
| "total_flos": 32008273920000.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |