| { |
| "best_metric": 7.352860927581787, |
| "best_model_checkpoint": "./fine-tuned/checkpoint-1000", |
| "epoch": 3.0, |
| "eval_steps": 1000, |
| "global_step": 1182, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 2.54, |
| "learning_rate": 7.698815566835872e-06, |
| "loss": 0.3773, |
| "step": 1000 |
| }, |
| { |
| "epoch": 2.54, |
| "eval_accuracy": 0.05962962962962963, |
| "eval_f1": 0.007503204007922637, |
| "eval_loss": 7.352860927581787, |
| "eval_runtime": 94.3853, |
| "eval_samples_per_second": 57.212, |
| "eval_steps_per_second": 7.152, |
| "step": 1000 |
| }, |
| { |
| "epoch": 3.0, |
| "step": 1182, |
| "total_flos": 2.9295385025163264e+18, |
| "train_loss": 0.3275312578617619, |
| "train_runtime": 1623.2173, |
| "train_samples_per_second": 23.287, |
| "train_steps_per_second": 0.728 |
| } |
| ], |
| "logging_steps": 1000, |
| "max_steps": 1182, |
| "num_train_epochs": 3, |
| "save_steps": 1000, |
| "total_flos": 2.9295385025163264e+18, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
