| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 3.0, |
| "eval_steps": 500, |
| "global_step": 63, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.4878048780487805, |
| "grad_norm": 115.25006140527131, |
| "learning_rate": 4.984280524733107e-07, |
| "loss": 5.2043, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.975609756097561, |
| "grad_norm": 84.87063005578057, |
| "learning_rate": 4.4545787061700746e-07, |
| "loss": 4.0637, |
| "step": 20 |
| }, |
| { |
| "epoch": 1.4390243902439024, |
| "grad_norm": 33.3888085423518, |
| "learning_rate": 3.325697654887918e-07, |
| "loss": 1.8658, |
| "step": 30 |
| }, |
| { |
| "epoch": 1.9268292682926829, |
| "grad_norm": 29.01562610175608, |
| "learning_rate": 1.9436976651092142e-07, |
| "loss": 1.3653, |
| "step": 40 |
| }, |
| { |
| "epoch": 2.3902439024390243, |
| "grad_norm": 15.9037632119475, |
| "learning_rate": 7.322330470336313e-08, |
| "loss": 1.1986, |
| "step": 50 |
| }, |
| { |
| "epoch": 2.8780487804878048, |
| "grad_norm": 20.223663761700873, |
| "learning_rate": 6.268021954544095e-09, |
| "loss": 1.0622, |
| "step": 60 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 63, |
| "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": 17799052296192.0, |
| "train_batch_size": 4, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
