| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 2.830188679245283, |
| "eval_steps": 1, |
| "global_step": 39, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.07547169811320754, |
| "grad_norm": 111.0, |
| "learning_rate": 6e-06, |
| "loss": 1.6151, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.22641509433962265, |
| "grad_norm": 65.0, |
| "learning_rate": 1.8e-05, |
| "loss": 1.5894, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.4528301886792453, |
| "grad_norm": 286.0, |
| "learning_rate": 2.9936012644425518e-05, |
| "loss": 1.9202, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.6792452830188679, |
| "grad_norm": 175.0, |
| "learning_rate": 2.8987083441065335e-05, |
| "loss": 1.5979, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.9056603773584906, |
| "grad_norm": 89.5, |
| "learning_rate": 2.6970258409203596e-05, |
| "loss": 1.4915, |
| "step": 12 |
| }, |
| { |
| "epoch": 1.0754716981132075, |
| "grad_norm": 128.0, |
| "learning_rate": 2.4039519545688848e-05, |
| "loss": 1.0238, |
| "step": 15 |
| }, |
| { |
| "epoch": 1.3018867924528301, |
| "grad_norm": 96.5, |
| "learning_rate": 2.0418624992807297e-05, |
| "loss": 1.2875, |
| "step": 18 |
| }, |
| { |
| "epoch": 1.5283018867924527, |
| "grad_norm": 122.0, |
| "learning_rate": 1.638402539194953e-05, |
| "loss": 1.1833, |
| "step": 21 |
| }, |
| { |
| "epoch": 1.7547169811320755, |
| "grad_norm": 87.5, |
| "learning_rate": 1.2243757232751444e-05, |
| "loss": 1.1228, |
| "step": 24 |
| }, |
| { |
| "epoch": 1.9811320754716981, |
| "grad_norm": 67.0, |
| "learning_rate": 8.313924663351927e-06, |
| "loss": 1.1144, |
| "step": 27 |
| }, |
| { |
| "epoch": 2.150943396226415, |
| "grad_norm": 100.5, |
| "learning_rate": 4.894565345301642e-06, |
| "loss": 0.7711, |
| "step": 30 |
| }, |
| { |
| "epoch": 2.3773584905660377, |
| "grad_norm": 60.25, |
| "learning_rate": 2.2467429640557903e-06, |
| "loss": 1.0037, |
| "step": 33 |
| }, |
| { |
| "epoch": 2.6037735849056602, |
| "grad_norm": 67.5, |
| "learning_rate": 5.726153524077144e-07, |
| "loss": 1.0549, |
| "step": 36 |
| }, |
| { |
| "epoch": 2.830188679245283, |
| "grad_norm": 50.75, |
| "learning_rate": 0.0, |
| "loss": 1.0016, |
| "step": 39 |
| } |
| ], |
| "logging_steps": 3, |
| "max_steps": 39, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": true, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 0.0, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
