| [ |
| { |
| "step": 10, |
| "epoch": 0.04, |
| "event": "log", |
| "loss": 0.7243, |
| "grad_norm": 6.450088024139404, |
| "learning_rate": 1.5000000000000002e-05 |
| }, |
| { |
| "step": 20, |
| "epoch": 0.08, |
| "event": "log", |
| "loss": 0.6547, |
| "grad_norm": 3.5925912857055664, |
| "learning_rate": 1e-05 |
| }, |
| { |
| "step": 20, |
| "epoch": 0.08, |
| "event": "log", |
| "eval_loss": 0.6500738263130188, |
| "eval_accuracy": 0.61, |
| "eval_precision": 0.6197183098591549, |
| "eval_recall": 0.5365853658536586, |
| "eval_f1": 0.5751633986928104, |
| "eval_runtime": 217.136, |
| "eval_samples_per_second": 2.303, |
| "eval_steps_per_second": 0.29 |
| }, |
| { |
| "step": 20, |
| "epoch": 0.08, |
| "event": "evaluate", |
| "eval_loss": 0.6500738263130188, |
| "eval_accuracy": 0.61, |
| "eval_precision": 0.6197183098591549, |
| "eval_recall": 0.5365853658536586, |
| "eval_f1": 0.5751633986928104, |
| "eval_runtime": 217.136, |
| "eval_samples_per_second": 2.303, |
| "eval_steps_per_second": 0.29 |
| }, |
| { |
| "step": 30, |
| "epoch": 0.12, |
| "event": "log", |
| "loss": 0.6126, |
| "grad_norm": 8.919687271118164, |
| "learning_rate": 5e-06 |
| }, |
| { |
| "step": 40, |
| "epoch": 0.16, |
| "event": "log", |
| "loss": 0.6193, |
| "grad_norm": 4.9131340980529785, |
| "learning_rate": 0.0 |
| }, |
| { |
| "step": 40, |
| "epoch": 0.16, |
| "event": "log", |
| "eval_loss": 0.6279698014259338, |
| "eval_accuracy": 0.652, |
| "eval_precision": 0.74, |
| "eval_recall": 0.45121951219512196, |
| "eval_f1": 0.5606060606060606, |
| "eval_runtime": 219.921, |
| "eval_samples_per_second": 2.274, |
| "eval_steps_per_second": 0.286 |
| }, |
| { |
| "step": 40, |
| "epoch": 0.16, |
| "event": "evaluate", |
| "eval_loss": 0.6279698014259338, |
| "eval_accuracy": 0.652, |
| "eval_precision": 0.74, |
| "eval_recall": 0.45121951219512196, |
| "eval_f1": 0.5606060606060606, |
| "eval_runtime": 219.921, |
| "eval_samples_per_second": 2.274, |
| "eval_steps_per_second": 0.286 |
| }, |
| { |
| "step": 40, |
| "epoch": 0.16, |
| "event": "log", |
| "train_runtime": 998.1872, |
| "train_samples_per_second": 0.321, |
| "train_steps_per_second": 0.04, |
| "total_flos": 21048884428800.0, |
| "train_loss": 0.652720320224762 |
| }, |
| { |
| "step": 50, |
| "epoch": 0.2, |
| "event": "log", |
| "loss": 0.5908, |
| "grad_norm": 6.924829006195068, |
| "learning_rate": 7.500000000000001e-06 |
| }, |
| { |
| "step": 60, |
| "epoch": 0.24, |
| "event": "log", |
| "loss": 0.642, |
| "grad_norm": 6.8762526512146, |
| "learning_rate": 5e-06 |
| }, |
| { |
| "step": 60, |
| "epoch": 0.24, |
| "event": "log", |
| "eval_loss": 0.5808247327804565, |
| "eval_accuracy": 0.7, |
| "eval_precision": 0.7608695652173914, |
| "eval_recall": 0.5691056910569106, |
| "eval_f1": 0.6511627906976745, |
| "eval_runtime": 227.7185, |
| "eval_samples_per_second": 2.196, |
| "eval_steps_per_second": 0.277 |
| }, |
| { |
| "step": 60, |
| "epoch": 0.24, |
| "event": "evaluate", |
| "eval_loss": 0.5808247327804565, |
| "eval_accuracy": 0.7, |
| "eval_precision": 0.7608695652173914, |
| "eval_recall": 0.5691056910569106, |
| "eval_f1": 0.6511627906976745, |
| "eval_runtime": 227.7185, |
| "eval_samples_per_second": 2.196, |
| "eval_steps_per_second": 0.277 |
| }, |
| { |
| "step": 70, |
| "epoch": 0.28, |
| "event": "log", |
| "loss": 0.5337, |
| "grad_norm": 8.56165885925293, |
| "learning_rate": 2.5e-06 |
| }, |
| { |
| "step": 80, |
| "epoch": 0.32, |
| "event": "log", |
| "loss": 0.5653, |
| "grad_norm": 6.879608631134033, |
| "learning_rate": 0.0 |
| }, |
| { |
| "step": 80, |
| "epoch": 0.32, |
| "event": "log", |
| "eval_loss": 0.5539242029190063, |
| "eval_accuracy": 0.736, |
| "eval_precision": 0.7435897435897436, |
| "eval_recall": 0.7073170731707317, |
| "eval_f1": 0.725, |
| "eval_runtime": 233.0561, |
| "eval_samples_per_second": 2.145, |
| "eval_steps_per_second": 0.27 |
| }, |
| { |
| "step": 80, |
| "epoch": 0.32, |
| "event": "evaluate", |
| "eval_loss": 0.5539242029190063, |
| "eval_accuracy": 0.736, |
| "eval_precision": 0.7435897435897436, |
| "eval_recall": 0.7073170731707317, |
| "eval_f1": 0.725, |
| "eval_runtime": 233.0561, |
| "eval_samples_per_second": 2.145, |
| "eval_steps_per_second": 0.27 |
| }, |
| { |
| "step": 80, |
| "epoch": 0.32, |
| "event": "log", |
| "train_runtime": 1023.5544, |
| "train_samples_per_second": 0.625, |
| "train_steps_per_second": 0.078, |
| "total_flos": 42097768857600.0, |
| "train_loss": 0.29147855639457704 |
| }, |
| { |
| "step": 80, |
| "epoch": 0.32, |
| "event": "log", |
| "eval_loss": 0.5539242029190063, |
| "eval_accuracy": 0.736, |
| "eval_precision": 0.7435897435897436, |
| "eval_recall": 0.7073170731707317, |
| "eval_f1": 0.725, |
| "eval_runtime": 243.0385, |
| "eval_samples_per_second": 2.057, |
| "eval_steps_per_second": 0.259 |
| }, |
| { |
| "step": 80, |
| "epoch": 0.32, |
| "event": "evaluate", |
| "eval_loss": 0.5539242029190063, |
| "eval_accuracy": 0.736, |
| "eval_precision": 0.7435897435897436, |
| "eval_recall": 0.7073170731707317, |
| "eval_f1": 0.725, |
| "eval_runtime": 243.0385, |
| "eval_samples_per_second": 2.057, |
| "eval_steps_per_second": 0.259 |
| } |
| ] |
