| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 5.0, | |
| "global_step": 388675, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 2.57, | |
| "learning_rate": 2.4280954524988745e-05, | |
| "loss": 1.8998, | |
| "step": 200000 | |
| }, | |
| { | |
| "epoch": 2.57, | |
| "eval_loss": 1.6605522632598877, | |
| "eval_runtime": 1064.795, | |
| "eval_samples_per_second": 129.786, | |
| "eval_steps_per_second": 8.112, | |
| "step": 200000 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "step": 388675, | |
| "total_flos": 2.98603105152047e+17, | |
| "train_loss": 1.7809591078664695, | |
| "train_runtime": 139562.9056, | |
| "train_samples_per_second": 44.559, | |
| "train_steps_per_second": 2.785 | |
| } | |
| ], | |
| "max_steps": 388675, | |
| "num_train_epochs": 5, | |
| "total_flos": 2.98603105152047e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |