| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.0, |
| "eval_steps": 500, |
| "global_step": 27, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "entropy": 1.180859375, |
| "epoch": 0.37037037037037035, |
| "grad_norm": 1.9087318181991577, |
| "learning_rate": 0.00019886154122075343, |
| "loss": 1.3855, |
| "mean_token_accuracy": 0.709491191804409, |
| "num_tokens": 20480.0, |
| "step": 10 |
| }, |
| { |
| "entropy": 0.77197265625, |
| "epoch": 0.7407407407407407, |
| "grad_norm": 1.5744595527648926, |
| "learning_rate": 0.00018990881137654258, |
| "loss": 0.8126, |
| "mean_token_accuracy": 0.8044520571827889, |
| "num_tokens": 40960.0, |
| "step": 20 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_entropy": 0.666015625, |
| "eval_loss": 0.664973795413971, |
| "eval_mean_token_accuracy": 0.8258317112922668, |
| "eval_num_tokens": 55296.0, |
| "eval_runtime": 104.8748, |
| "eval_samples_per_second": 0.114, |
| "eval_steps_per_second": 0.019, |
| "step": 27 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 108, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 4, |
| "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": 2374105735102464.0, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
