| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.8832391713747647, |
| "eval_steps": 500, |
| "global_step": 500, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.3766478342749529, |
| "grad_norm": 0.4676072597503662, |
| "learning_rate": 0.0002, |
| "loss": 0.4573, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.7532956685499058, |
| "grad_norm": 0.45285171270370483, |
| "learning_rate": 0.00019615384615384615, |
| "loss": 0.3447, |
| "step": 200 |
| }, |
| { |
| "epoch": 1.1299435028248588, |
| "grad_norm": 0.3083706498146057, |
| "learning_rate": 0.00019230769230769233, |
| "loss": 0.3145, |
| "step": 300 |
| }, |
| { |
| "epoch": 1.5065913370998116, |
| "grad_norm": 0.40702226758003235, |
| "learning_rate": 0.00018846153846153847, |
| "loss": 0.2603, |
| "step": 400 |
| }, |
| { |
| "epoch": 1.8832391713747647, |
| "grad_norm": 0.48795807361602783, |
| "learning_rate": 0.00018461538461538463, |
| "loss": 0.2729, |
| "step": 500 |
| } |
| ], |
| "logging_steps": 100, |
| "max_steps": 5300, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 20, |
| "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": 1.609310372141138e+17, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
