| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 16.0, |
| "eval_steps": 500, |
| "global_step": 200, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 2.0, |
| "grad_norm": 0.12720850110054016, |
| "learning_rate": 0.0001953038210948861, |
| "loss": 1.3526, |
| "step": 25 |
| }, |
| { |
| "epoch": 4.0, |
| "grad_norm": 0.1418006867170334, |
| "learning_rate": 0.00017567128158176953, |
| "loss": 1.1521, |
| "step": 50 |
| }, |
| { |
| "epoch": 6.0, |
| "grad_norm": 0.19072043895721436, |
| "learning_rate": 0.00014380476768566824, |
| "loss": 1.0911, |
| "step": 75 |
| }, |
| { |
| "epoch": 8.0, |
| "grad_norm": 0.26865869760513306, |
| "learning_rate": 0.00010485622221144484, |
| "loss": 1.0212, |
| "step": 100 |
| }, |
| { |
| "epoch": 10.0, |
| "grad_norm": 0.4043382704257965, |
| "learning_rate": 6.512255856701177e-05, |
| "loss": 0.9493, |
| "step": 125 |
| }, |
| { |
| "epoch": 12.0, |
| "grad_norm": 0.3770226836204529, |
| "learning_rate": 3.102762227218957e-05, |
| "loss": 0.8919, |
| "step": 150 |
| }, |
| { |
| "epoch": 14.0, |
| "grad_norm": 0.4045465886592865, |
| "learning_rate": 8.083631020418791e-06, |
| "loss": 0.8576, |
| "step": 175 |
| }, |
| { |
| "epoch": 16.0, |
| "grad_norm": 0.36538949608802795, |
| "learning_rate": 0.0, |
| "loss": 0.8455, |
| "step": 200 |
| } |
| ], |
| "logging_steps": 25, |
| "max_steps": 200, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 17, |
| "save_steps": 50, |
| "total_flos": 1.408501775597568e+17, |
| "train_batch_size": 4, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
