| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 3.0, |
| "eval_steps": 500, |
| "global_step": 33, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.9302325581395349, |
| "grad_norm": 0.5803418159484863, |
| "learning_rate": 4.1379310344827587e-05, |
| "loss": 2.0756296157836913, |
| "step": 10 |
| }, |
| { |
| "epoch": 1.8372093023255816, |
| "grad_norm": 0.9032034873962402, |
| "learning_rate": 2.413793103448276e-05, |
| "loss": 2.049017143249512, |
| "step": 20 |
| }, |
| { |
| "epoch": 2.744186046511628, |
| "grad_norm": 0.7865656614303589, |
| "learning_rate": 6.896551724137932e-06, |
| "loss": 1.9342205047607421, |
| "step": 30 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 33, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 250669380584448.0, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
