| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 4.0, |
| "eval_steps": 500, |
| "global_step": 24, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "entropy": 2.6712906038438953, |
| "epoch": 1.7619047619047619, |
| "grad_norm": 2.296875, |
| "learning_rate": 6.521739130434783e-05, |
| "loss": 3.1348785400390624, |
| "mean_token_accuracy": 0.45456858986132853, |
| "num_tokens": 20134.0, |
| "step": 10 |
| }, |
| { |
| "entropy": 1.94013451127445, |
| "epoch": 3.380952380952381, |
| "grad_norm": 3.734375, |
| "learning_rate": 2.173913043478261e-05, |
| "loss": 1.86732177734375, |
| "mean_token_accuracy": 0.6232341913615956, |
| "num_tokens": 38365.0, |
| "step": 20 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 24, |
| "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": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 2084233990225920.0, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
