| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.014666089800467848, |
| "eval_steps": 50, |
| "global_step": 1000, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.0, |
| "learning_rate": 2.3869346733668342e-05, |
| "loss": 0.1414, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.0, |
| "learning_rate": 2.2613065326633167e-05, |
| "loss": 0.1297, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.0, |
| "learning_rate": 2.135678391959799e-05, |
| "loss": 0.132, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.0, |
| "learning_rate": 2.0100502512562815e-05, |
| "loss": 0.1323, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.0, |
| "learning_rate": 1.884422110552764e-05, |
| "loss": 0.1292, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.0, |
| "learning_rate": 1.7587939698492464e-05, |
| "loss": 0.1279, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.01, |
| "learning_rate": 1.6331658291457288e-05, |
| "loss": 0.1275, |
| "step": 350 |
| }, |
| { |
| "epoch": 0.01, |
| "learning_rate": 1.507537688442211e-05, |
| "loss": 0.1265, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.01, |
| "learning_rate": 1.3819095477386935e-05, |
| "loss": 0.1261, |
| "step": 450 |
| }, |
| { |
| "epoch": 0.01, |
| "learning_rate": 1.2562814070351759e-05, |
| "loss": 0.1233, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.01, |
| "learning_rate": 1.1306532663316583e-05, |
| "loss": 0.1221, |
| "step": 550 |
| }, |
| { |
| "epoch": 0.01, |
| "learning_rate": 1.0050251256281408e-05, |
| "loss": 0.1211, |
| "step": 600 |
| }, |
| { |
| "epoch": 0.01, |
| "learning_rate": 8.793969849246232e-06, |
| "loss": 0.1221, |
| "step": 650 |
| }, |
| { |
| "epoch": 0.01, |
| "learning_rate": 7.537688442211055e-06, |
| "loss": 0.1224, |
| "step": 700 |
| }, |
| { |
| "epoch": 0.01, |
| "learning_rate": 6.2814070351758795e-06, |
| "loss": 0.1192, |
| "step": 750 |
| }, |
| { |
| "epoch": 0.01, |
| "learning_rate": 5.025125628140704e-06, |
| "loss": 0.1207, |
| "step": 800 |
| }, |
| { |
| "epoch": 0.01, |
| "learning_rate": 3.7688442211055276e-06, |
| "loss": 0.1205, |
| "step": 850 |
| }, |
| { |
| "epoch": 0.01, |
| "learning_rate": 2.512562814070352e-06, |
| "loss": 0.1198, |
| "step": 900 |
| }, |
| { |
| "epoch": 0.01, |
| "learning_rate": 1.256281407035176e-06, |
| "loss": 0.1188, |
| "step": 950 |
| }, |
| { |
| "epoch": 0.01, |
| "learning_rate": 0.0, |
| "loss": 0.1211, |
| "step": 1000 |
| } |
| ], |
| "logging_steps": 50, |
| "max_steps": 1000, |
| "num_train_epochs": 1, |
| "save_steps": 50, |
| "total_flos": 1.75274075357184e+17, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
