| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 37, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "entropy": 1.115849182009697, | |
| "epoch": 0.273972602739726, | |
| "grad_norm": 0.89453125, | |
| "learning_rate": 1.9986141830690626e-05, | |
| "loss": 1.1036, | |
| "mean_token_accuracy": 0.6849135965108871, | |
| "num_tokens": 3403502.0, | |
| "step": 10 | |
| }, | |
| { | |
| "entropy": 0.9511253193020821, | |
| "epoch": 0.547945205479452, | |
| "grad_norm": 0.46484375, | |
| "learning_rate": 1.9740841436914917e-05, | |
| "loss": 0.9169, | |
| "mean_token_accuracy": 0.7195438116788864, | |
| "num_tokens": 6821458.0, | |
| "step": 20 | |
| }, | |
| { | |
| "entropy": 0.9001567244529725, | |
| "epoch": 0.821917808219178, | |
| "grad_norm": 0.376953125, | |
| "learning_rate": 1.9196262851127695e-05, | |
| "loss": 0.8617, | |
| "mean_token_accuracy": 0.7317715749144554, | |
| "num_tokens": 10282466.0, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 185, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 5, | |
| "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": 2.8544478491757773e+17, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |