| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.09984871406959153, |
| "eval_steps": 100, |
| "global_step": 33, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.030257186081694403, |
| "grad_norm": 19.446511460556057, |
| "learning_rate": 1.796093065705644e-05, |
| "loss": 6.9188, |
| "mean_token_accuracy": 0.14323783591389655, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.060514372163388806, |
| "grad_norm": 10.827592460467098, |
| "learning_rate": 8.382180034472353e-06, |
| "loss": 5.3359, |
| "mean_token_accuracy": 0.19127428904175758, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.0907715582450832, |
| "grad_norm": 8.615023934478028, |
| "learning_rate": 5.234682881719766e-07, |
| "loss": 4.7375, |
| "mean_token_accuracy": 0.2355961874127388, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.09984871406959153, |
| "mean_token_accuracy": 0.2397766982515653, |
| "step": 33, |
| "total_flos": 541940076511232.0, |
| "train_loss": 5.5710227272727275, |
| "train_runtime": 94.1692, |
| "train_samples_per_second": 11.226, |
| "train_steps_per_second": 0.35 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 33, |
| "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": false, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 541940076511232.0, |
| "train_batch_size": 8, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
