| { |
| "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": 22.141286849975586, |
| "learning_rate": 4.5e-06, |
| "loss": 6.0086, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.975609756097561, |
| "grad_norm": 10.527143478393555, |
| "learning_rate": 9.5e-06, |
| "loss": 3.7945, |
| "step": 20 |
| }, |
| { |
| "epoch": 1.4390243902439024, |
| "grad_norm": 6.946624755859375, |
| "learning_rate": 1.45e-05, |
| "loss": 2.2198, |
| "step": 30 |
| }, |
| { |
| "epoch": 1.9268292682926829, |
| "grad_norm": 4.248944282531738, |
| "learning_rate": 1.9500000000000003e-05, |
| "loss": 1.037, |
| "step": 40 |
| }, |
| { |
| "epoch": 2.3902439024390243, |
| "grad_norm": 4.16041898727417, |
| "learning_rate": 2.45e-05, |
| "loss": 0.5752, |
| "step": 50 |
| }, |
| { |
| "epoch": 2.8780487804878048, |
| "grad_norm": 4.716129302978516, |
| "learning_rate": 2.95e-05, |
| "loss": 0.5495, |
| "step": 60 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 63, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "save_steps": 100, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 127771803648000.0, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
