| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.19991202990983065, |
| "eval_steps": 500, |
| "global_step": 3636, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.027490653177919506, |
| "grad_norm": 7.844790935516357, |
| "learning_rate": 1.98e-05, |
| "loss": 3.3532, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.05498130635583901, |
| "grad_norm": 7.924389362335205, |
| "learning_rate": 1.9816883693400415e-05, |
| "loss": 2.6056, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.08247195953375852, |
| "grad_norm": 7.497577667236328, |
| "learning_rate": 1.963191772713821e-05, |
| "loss": 2.5447, |
| "step": 1500 |
| }, |
| { |
| "epoch": 0.10996261271167802, |
| "grad_norm": 6.73529577255249, |
| "learning_rate": 1.9446951760876e-05, |
| "loss": 2.4492, |
| "step": 2000 |
| }, |
| { |
| "epoch": 0.13745326588959753, |
| "grad_norm": 6.306326866149902, |
| "learning_rate": 1.9261985794613793e-05, |
| "loss": 2.4463, |
| "step": 2500 |
| }, |
| { |
| "epoch": 0.16494391906751704, |
| "grad_norm": 5.651560306549072, |
| "learning_rate": 1.9077019828351584e-05, |
| "loss": 2.3291, |
| "step": 3000 |
| }, |
| { |
| "epoch": 0.19243457224543656, |
| "grad_norm": 4.0863471031188965, |
| "learning_rate": 1.8892053862089378e-05, |
| "loss": 2.3461, |
| "step": 3500 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 54564, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "save_steps": 1818, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 950057828352000.0, |
| "train_batch_size": 4, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
