| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.8680555555555556, |
| "eval_steps": 500, |
| "global_step": 500, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.1736111111111111, |
| "grad_norm": 15.283892631530762, |
| "learning_rate": 1.885416666666667e-05, |
| "loss": 0.2931, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.3472222222222222, |
| "grad_norm": 0.4524991512298584, |
| "learning_rate": 1.769675925925926e-05, |
| "loss": 0.1401, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.5208333333333334, |
| "grad_norm": 3.380779981613159, |
| "learning_rate": 1.6539351851851852e-05, |
| "loss": 0.1313, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.6944444444444444, |
| "grad_norm": 10.423238754272461, |
| "learning_rate": 1.5381944444444445e-05, |
| "loss": 0.1072, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.8680555555555556, |
| "grad_norm": 1.7568814754486084, |
| "learning_rate": 1.4224537037037038e-05, |
| "loss": 0.1313, |
| "step": 500 |
| } |
| ], |
| "logging_steps": 100, |
| "max_steps": 1728, |
| "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": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 340760208384000.0, |
| "train_batch_size": 16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
