| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.5741626794258373, |
| "eval_steps": 500, |
| "global_step": 30, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "entropy": 2.35390625, |
| "epoch": 0.19138755980861244, |
| "grad_norm": 1.577696681022644, |
| "learning_rate": 0.0001999145758387301, |
| "loss": 2.517007064819336, |
| "mean_token_accuracy": 0.4835851963609457, |
| "num_tokens": 32923.0, |
| "step": 10 |
| }, |
| { |
| "entropy": 1.953515625, |
| "epoch": 0.3827751196172249, |
| "grad_norm": 1.822049856185913, |
| "learning_rate": 0.00019694002659393305, |
| "loss": 1.814153289794922, |
| "mean_token_accuracy": 0.6044577240943909, |
| "num_tokens": 65628.0, |
| "step": 20 |
| }, |
| { |
| "entropy": 1.36533203125, |
| "epoch": 0.5741626794258373, |
| "grad_norm": 0.8370082974433899, |
| "learning_rate": 0.0001898390981891979, |
| "loss": 1.4171125411987304, |
| "mean_token_accuracy": 0.6942351691424846, |
| "num_tokens": 98592.0, |
| "step": 30 |
| } |
| ], |
| "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": 308065022637312.0, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
