| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0, | |
| "global_step": 3207, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 2.532273152478952e-06, | |
| "loss": 0.4213, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 2.0645463049579046e-06, | |
| "loss": 0.3452, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 1.5968194574368567e-06, | |
| "loss": 0.2744, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 1.1290926099158092e-06, | |
| "loss": 0.2548, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "learning_rate": 6.613657623947614e-07, | |
| "loss": 0.2152, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 2.81, | |
| "learning_rate": 1.9363891487371378e-07, | |
| "loss": 0.1992, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "step": 3207, | |
| "total_flos": 5976749164543488.0, | |
| "train_loss": 0.27882336008983644, | |
| "train_runtime": 1049.1554, | |
| "train_samples_per_second": 24.451, | |
| "train_steps_per_second": 3.057 | |
| } | |
| ], | |
| "max_steps": 3207, | |
| "num_train_epochs": 3, | |
| "total_flos": 5976749164543488.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |