| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9625962596259626, | |
| "global_step": 1750, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 5e-06, | |
| "loss": 2.368, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 5e-06, | |
| "loss": 2.2031, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 5e-06, | |
| "loss": 2.1764, | |
| "step": 1500 | |
| } | |
| ], | |
| "max_steps": 2000, | |
| "num_train_epochs": 2, | |
| "total_flos": 4.42314986480468e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |