| { |
| "log_history": [ |
| { |
| "loss": 3.253069430190181, |
| "grad_norm": 8.451900482177734, |
| "learning_rate": 1.3351206434316355e-05, |
| "epoch": 1.0, |
| "step": 373 |
| }, |
| { |
| "eval_loss": 0.5276884436607361, |
| "eval_accuracy": 0.8352668213457076, |
| "eval_precision": 0.8143939393939394, |
| "eval_recall": 0.9806157354618016, |
| "eval_f1": 0.8898085876875323, |
| "eval_runtime": 26.2521, |
| "eval_samples_per_second": 49.253, |
| "eval_steps_per_second": 3.085, |
| "epoch": 1.0, |
| "step": 373 |
| }, |
| { |
| "loss": 2.735222946862433, |
| "grad_norm": 5.377457141876221, |
| "learning_rate": 6.684539767649688e-06, |
| "epoch": 2.0, |
| "step": 746 |
| }, |
| { |
| "eval_loss": 0.5213587880134583, |
| "eval_accuracy": 0.8290796597061099, |
| "eval_precision": 0.8014705882352942, |
| "eval_recall": 0.9942987457240593, |
| "eval_f1": 0.8875318066157761, |
| "eval_runtime": 26.0805, |
| "eval_samples_per_second": 49.577, |
| "eval_steps_per_second": 3.106, |
| "epoch": 2.0, |
| "step": 746 |
| }, |
| { |
| "loss": 2.6189828826658847, |
| "grad_norm": 8.425128936767578, |
| "learning_rate": 1.7873100983020556e-08, |
| "epoch": 3.0, |
| "step": 1119 |
| }, |
| { |
| "eval_loss": 0.5193805694580078, |
| "eval_accuracy": 0.8360402165506574, |
| "eval_precision": 0.8382502543234995, |
| "eval_recall": 0.9395667046750285, |
| "eval_f1": 0.886021505376344, |
| "eval_runtime": 25.9863, |
| "eval_samples_per_second": 49.757, |
| "eval_steps_per_second": 3.117, |
| "epoch": 3.0, |
| "step": 1119 |
| }, |
| { |
| "train_runtime": 2705.0358, |
| "train_samples_per_second": 13.211, |
| "train_steps_per_second": 0.414, |
| "total_flos": 9402536674344960.0, |
| "train_loss": 2.8690917532394997, |
| "epoch": 3.0, |
| "step": 1119 |
| } |
| ] |
| } |
