| [ |
| { |
| "loss": 0.7327, |
| "grad_norm": 2.7726080417633057, |
| "learning_rate": 3.3333333333333333e-06, |
| "epoch": 0.2857142857142857, |
| "step": 1 |
| }, |
| { |
| "eval_loss": 0.7512667775154114, |
| "eval_accuracy": 0.03412073490813648, |
| "eval_f1": 0.03664921465968587, |
| "eval_precision": 0.018666666666666668, |
| "eval_recall": 1.0, |
| "eval_runtime": 5.3956, |
| "eval_samples_per_second": 70.613, |
| "eval_steps_per_second": 4.448, |
| "epoch": 0.2857142857142857, |
| "step": 1 |
| }, |
| { |
| "eval_loss": 0.7464109659194946, |
| "eval_accuracy": 0.05249343832020997, |
| "eval_f1": 0.037333333333333336, |
| "eval_precision": 0.019021739130434784, |
| "eval_recall": 1.0, |
| "eval_runtime": 5.5933, |
| "eval_samples_per_second": 68.117, |
| "eval_steps_per_second": 4.291, |
| "epoch": 0.5714285714285714, |
| "step": 2 |
| }, |
| { |
| "eval_loss": 0.7368069291114807, |
| "eval_accuracy": 0.08923884514435695, |
| "eval_f1": 0.038781163434903045, |
| "eval_precision": 0.01977401129943503, |
| "eval_recall": 1.0, |
| "eval_runtime": 5.5621, |
| "eval_samples_per_second": 68.5, |
| "eval_steps_per_second": 4.315, |
| "epoch": 0.8571428571428571, |
| "step": 3 |
| }, |
| { |
| "eval_loss": 0.7224730849266052, |
| "eval_accuracy": 0.19160104986876642, |
| "eval_f1": 0.03749999999999999, |
| "eval_precision": 0.019169329073482427, |
| "eval_recall": 0.8571428571428571, |
| "eval_runtime": 5.6279, |
| "eval_samples_per_second": 67.698, |
| "eval_steps_per_second": 4.264, |
| "epoch": 1.1428571428571428, |
| "step": 4 |
| }, |
| { |
| "eval_loss": 0.7036912441253662, |
| "eval_accuracy": 0.3884514435695538, |
| "eval_f1": 0.02510460251046025, |
| "eval_precision": 0.01293103448275862, |
| "eval_recall": 0.42857142857142855, |
| "eval_runtime": 5.703, |
| "eval_samples_per_second": 66.807, |
| "eval_steps_per_second": 4.208, |
| "epoch": 1.4285714285714286, |
| "step": 5 |
| }, |
| { |
| "eval_loss": 0.6806334853172302, |
| "eval_accuracy": 0.6325459317585301, |
| "eval_f1": 0.0, |
| "eval_precision": 0.0, |
| "eval_recall": 0.0, |
| "eval_runtime": 5.773, |
| "eval_samples_per_second": 65.997, |
| "eval_steps_per_second": 4.157, |
| "epoch": 1.7142857142857144, |
| "step": 6 |
| }, |
| { |
| "eval_loss": 0.6538448929786682, |
| "eval_accuracy": 0.868766404199475, |
| "eval_f1": 0.0, |
| "eval_precision": 0.0, |
| "eval_recall": 0.0, |
| "eval_runtime": 5.6817, |
| "eval_samples_per_second": 67.057, |
| "eval_steps_per_second": 4.224, |
| "epoch": 2.0, |
| "step": 7 |
| }, |
| { |
| "eval_loss": 0.6274169683456421, |
| "eval_accuracy": 0.973753280839895, |
| "eval_f1": 0.0, |
| "eval_precision": 0.0, |
| "eval_recall": 0.0, |
| "eval_runtime": 5.8624, |
| "eval_samples_per_second": 64.991, |
| "eval_steps_per_second": 4.094, |
| "epoch": 2.2857142857142856, |
| "step": 8 |
| }, |
| { |
| "eval_loss": 0.6018883585929871, |
| "eval_accuracy": 0.9816272965879265, |
| "eval_f1": 0.0, |
| "eval_precision": 0.0, |
| "eval_recall": 0.0, |
| "eval_runtime": 5.644, |
| "eval_samples_per_second": 67.505, |
| "eval_steps_per_second": 4.252, |
| "epoch": 2.571428571428571, |
| "step": 9 |
| }, |
| { |
| "train_runtime": 101.6832, |
| "train_samples_per_second": 41.698, |
| "train_steps_per_second": 0.59, |
| "total_flos": 2156353020864.0, |
| "train_loss": 0.6984957986407809, |
| "epoch": 2.571428571428571, |
| "step": 9 |
| } |
| ] |
