| { |
| "best_metric": 1.0, |
| "best_model_checkpoint": "../FINAL/checkpoint-2138", |
| "epoch": 3.0, |
| "eval_steps": 500, |
| "global_step": 6414, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.23, |
| "learning_rate": 2e-05, |
| "loss": 0.3679, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.47, |
| "learning_rate": 1.8758072528564333e-05, |
| "loss": 0.0029, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.7, |
| "learning_rate": 1.7516145057128665e-05, |
| "loss": 0.0006, |
| "step": 1500 |
| }, |
| { |
| "epoch": 0.94, |
| "learning_rate": 1.6274217585692997e-05, |
| "loss": 0.0003, |
| "step": 2000 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 1.0, |
| "eval_f1": 1.0, |
| "eval_loss": 5.122346919961274e-05, |
| "eval_precision": 1.0, |
| "eval_recall": 1.0, |
| "eval_runtime": 1.22, |
| "eval_samples_per_second": 3114.786, |
| "eval_steps_per_second": 195.084, |
| "step": 2138 |
| }, |
| { |
| "epoch": 1.17, |
| "learning_rate": 1.5032290114257329e-05, |
| "loss": 0.0002, |
| "step": 2500 |
| }, |
| { |
| "epoch": 1.4, |
| "learning_rate": 1.379036264282166e-05, |
| "loss": 0.0001, |
| "step": 3000 |
| }, |
| { |
| "epoch": 1.64, |
| "learning_rate": 1.2548435171385993e-05, |
| "loss": 0.0001, |
| "step": 3500 |
| }, |
| { |
| "epoch": 1.87, |
| "learning_rate": 1.1306507699950325e-05, |
| "loss": 0.0001, |
| "step": 4000 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 1.0, |
| "eval_f1": 1.0, |
| "eval_loss": 1.0265763194183819e-05, |
| "eval_precision": 1.0, |
| "eval_recall": 1.0, |
| "eval_runtime": 1.1652, |
| "eval_samples_per_second": 3261.207, |
| "eval_steps_per_second": 204.255, |
| "step": 4276 |
| }, |
| { |
| "epoch": 2.1, |
| "learning_rate": 1.0064580228514655e-05, |
| "loss": 0.0, |
| "step": 4500 |
| }, |
| { |
| "epoch": 2.34, |
| "learning_rate": 8.822652757078988e-06, |
| "loss": 0.0, |
| "step": 5000 |
| }, |
| { |
| "epoch": 2.57, |
| "learning_rate": 7.580725285643319e-06, |
| "loss": 0.0, |
| "step": 5500 |
| }, |
| { |
| "epoch": 2.81, |
| "learning_rate": 6.338797814207651e-06, |
| "loss": 0.0, |
| "step": 6000 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 1.0, |
| "eval_f1": 1.0, |
| "eval_loss": 3.873569767165463e-06, |
| "eval_precision": 1.0, |
| "eval_recall": 1.0, |
| "eval_runtime": 1.1741, |
| "eval_samples_per_second": 3236.562, |
| "eval_steps_per_second": 202.711, |
| "step": 6414 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 8552, |
| "num_train_epochs": 4, |
| "save_steps": 500, |
| "total_flos": 285137632903152.0, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
