| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.0, |
| "eval_steps": 500, |
| "global_step": 115, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "entropy": 1.5443342211842537, |
| "epoch": 0.2176278563656148, |
| "grad_norm": 0.055419921875, |
| "learning_rate": 0.00018440244840299506, |
| "loss": 1.5704032897949218, |
| "mean_token_accuracy": 0.6370699141919612, |
| "num_tokens": 160909.0, |
| "step": 25 |
| }, |
| { |
| "entropy": 1.1008353152126074, |
| "epoch": 0.4352557127312296, |
| "grad_norm": 0.109375, |
| "learning_rate": 0.00012928227712765504, |
| "loss": 1.0481930541992188, |
| "mean_token_accuracy": 0.7331653463840485, |
| "num_tokens": 326278.0, |
| "step": 50 |
| }, |
| { |
| "entropy": 0.6921453317627311, |
| "epoch": 0.6528835690968444, |
| "grad_norm": 0.13671875, |
| "learning_rate": 6.010346486845837e-05, |
| "loss": 0.6511263275146484, |
| "mean_token_accuracy": 0.8276160681247711, |
| "num_tokens": 488512.0, |
| "step": 75 |
| }, |
| { |
| "entropy": 0.46901930367574096, |
| "epoch": 0.8705114254624592, |
| "grad_norm": 0.12451171875, |
| "learning_rate": 1.0079278510416313e-05, |
| "loss": 0.4208272171020508, |
| "mean_token_accuracy": 0.8860271820425987, |
| "num_tokens": 651559.0, |
| "step": 100 |
| } |
| ], |
| "logging_steps": 25, |
| "max_steps": 115, |
| "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": 6.330634898384486e+16, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
