| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 6.0, |
| "global_step": 4260, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.7, |
| "learning_rate": 4.413145539906103e-05, |
| "loss": 0.9331, |
| "step": 500 |
| }, |
| { |
| "epoch": 1.41, |
| "learning_rate": 3.826291079812207e-05, |
| "loss": 0.521, |
| "step": 1000 |
| }, |
| { |
| "epoch": 2.11, |
| "learning_rate": 3.23943661971831e-05, |
| "loss": 0.3464, |
| "step": 1500 |
| }, |
| { |
| "epoch": 2.82, |
| "learning_rate": 2.6525821596244134e-05, |
| "loss": 0.2114, |
| "step": 2000 |
| }, |
| { |
| "epoch": 3.52, |
| "learning_rate": 2.0657276995305167e-05, |
| "loss": 0.1467, |
| "step": 2500 |
| }, |
| { |
| "epoch": 4.23, |
| "learning_rate": 1.4788732394366198e-05, |
| "loss": 0.1109, |
| "step": 3000 |
| }, |
| { |
| "epoch": 4.93, |
| "learning_rate": 8.92018779342723e-06, |
| "loss": 0.0767, |
| "step": 3500 |
| }, |
| { |
| "epoch": 5.63, |
| "learning_rate": 3.051643192488263e-06, |
| "loss": 0.0504, |
| "step": 4000 |
| }, |
| { |
| "epoch": 6.0, |
| "step": 4260, |
| "total_flos": 72510721228800.0, |
| "train_loss": 0.28417864718907315, |
| "train_runtime": 1315.8778, |
| "train_samples_per_second": 12.936, |
| "train_steps_per_second": 3.237 |
| } |
| ], |
| "max_steps": 4260, |
| "num_train_epochs": 6, |
| "total_flos": 72510721228800.0, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
