| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.9996300406955235, |
| "eval_steps": 500, |
| "global_step": 1351, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.3699593044765076, |
| "grad_norm": 0.8689717159201097, |
| "learning_rate": 1.2598075499629904e-05, |
| "loss": 0.7857, |
| "mean_token_accuracy": 0.7653137772977352, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.7399186089530152, |
| "grad_norm": 0.7820960132849989, |
| "learning_rate": 5.196150999259808e-06, |
| "loss": 0.738, |
| "mean_token_accuracy": 0.7752673602104188, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.9996300406955235, |
| "step": 1351, |
| "total_flos": 76966677970944.0, |
| "train_loss": 0.0, |
| "train_runtime": 0.0024, |
| "train_samples_per_second": 1311423.218, |
| "train_steps_per_second": 81677.455 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 196, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "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": 76966677970944.0, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
