| { |
| "best_global_step": 9, |
| "best_metric": 0.26666666666666666, |
| "best_model_checkpoint": "./cheese-text-classifier/checkpoint-9", |
| "epoch": 1.0, |
| "eval_steps": 500, |
| "global_step": 9, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.5555555555555556, |
| "grad_norm": 2.245687246322632, |
| "learning_rate": 8.000000000000001e-06, |
| "loss": 1.3897, |
| "step": 5 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.26666666666666666, |
| "eval_loss": 1.3788894414901733, |
| "eval_runtime": 15.3581, |
| "eval_samples_per_second": 0.977, |
| "eval_steps_per_second": 0.13, |
| "step": 9 |
| } |
| ], |
| "logging_steps": 5, |
| "max_steps": 90, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 10, |
| "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": 9273048637440.0, |
| "train_batch_size": 8, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
