| { |
| "best_global_step": 14, |
| "best_metric": 0.06818181818181818, |
| "best_model_checkpoint": "font-identifier/checkpoint-14", |
| "epoch": 1.0, |
| "eval_steps": 500, |
| "global_step": 14, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.7272727272727273, |
| "grad_norm": 9.430075645446777, |
| "learning_rate": 6.428571428571429e-06, |
| "loss": 3.3213, |
| "step": 10 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.06818181818181818, |
| "eval_loss": 3.2453081607818604, |
| "eval_runtime": 2.4333, |
| "eval_samples_per_second": 90.411, |
| "eval_steps_per_second": 5.753, |
| "step": 14 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 700, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 50, |
| "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": 8891925806776320.0, |
| "train_batch_size": 16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|