| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.509433962264151, |
| "eval_steps": 500, |
| "global_step": 80, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "entropy": 2.27734375, |
| "epoch": 0.18867924528301888, |
| "grad_norm": 1.4095726013183594, |
| "learning_rate": 0.0001999145758387301, |
| "loss": 2.535823440551758, |
| "mean_token_accuracy": 0.4902416098862886, |
| "num_tokens": 36112.0, |
| "step": 10 |
| }, |
| { |
| "entropy": 2.03623046875, |
| "epoch": 0.37735849056603776, |
| "grad_norm": 1.8039652109146118, |
| "learning_rate": 0.00019694002659393305, |
| "loss": 1.8651376724243165, |
| "mean_token_accuracy": 0.5952314671128989, |
| "num_tokens": 72245.0, |
| "step": 20 |
| }, |
| { |
| "entropy": 1.49443359375, |
| "epoch": 0.5660377358490566, |
| "grad_norm": 0.7885380387306213, |
| "learning_rate": 0.0001898390981891979, |
| "loss": 1.5259657859802247, |
| "mean_token_accuracy": 0.6693046040832996, |
| "num_tokens": 108540.0, |
| "step": 30 |
| }, |
| { |
| "entropy": 1.421875, |
| "epoch": 0.7547169811320755, |
| "grad_norm": 0.7279834747314453, |
| "learning_rate": 0.00017891405093963938, |
| "loss": 1.4288103103637695, |
| "mean_token_accuracy": 0.6861812733113766, |
| "num_tokens": 144637.0, |
| "step": 40 |
| }, |
| { |
| "entropy": 1.38642578125, |
| "epoch": 0.9433962264150944, |
| "grad_norm": 0.6967478394508362, |
| "learning_rate": 0.00016462992378609407, |
| "loss": 1.3759333610534668, |
| "mean_token_accuracy": 0.6965034589171409, |
| "num_tokens": 180890.0, |
| "step": 50 |
| }, |
| { |
| "entropy": 1.37880859375, |
| "epoch": 1.1320754716981132, |
| "grad_norm": 0.7058449983596802, |
| "learning_rate": 0.00014759473930370736, |
| "loss": 1.3774614334106445, |
| "mean_token_accuracy": 0.6968415275216102, |
| "num_tokens": 216977.0, |
| "step": 60 |
| }, |
| { |
| "entropy": 1.3544921875, |
| "epoch": 1.320754716981132, |
| "grad_norm": 0.7576785087585449, |
| "learning_rate": 0.00012853362242491053, |
| "loss": 1.3501564979553222, |
| "mean_token_accuracy": 0.699217775464058, |
| "num_tokens": 253285.0, |
| "step": 70 |
| }, |
| { |
| "entropy": 1.35498046875, |
| "epoch": 1.509433962264151, |
| "grad_norm": 0.6370306015014648, |
| "learning_rate": 0.00010825793454723325, |
| "loss": 1.346321201324463, |
| "mean_token_accuracy": 0.7007117375731469, |
| "num_tokens": 288932.0, |
| "step": 80 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 159, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "save_steps": 10, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 905301547360512.0, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
