| { |
| "config": { |
| "epochs": 30, |
| "lr": 0.0003, |
| "warmup_steps": 667, |
| "grad_accum_steps": 4, |
| "grad_clip": 1.0 |
| }, |
| "train": [ |
| { |
| "epoch": 1, |
| "avg_loss": 7.425536, |
| "lr": 0.0002998625141045411, |
| "step": 1113, |
| "time_s": 5022.7 |
| }, |
| { |
| "epoch": 2, |
| "avg_loss": 6.084101, |
| "lr": 0.000298322988234269, |
| "step": 2226, |
| "time_s": 5041.5 |
| }, |
| { |
| "epoch": 3, |
| "avg_loss": 5.6477, |
| "lr": 0.00029509154537521725, |
| "step": 3339, |
| "time_s": 5047.8 |
| }, |
| { |
| "epoch": 4, |
| "avg_loss": 5.394878, |
| "lr": 0.00029020504652335535, |
| "step": 4452, |
| "time_s": 5048.9 |
| }, |
| { |
| "epoch": 5, |
| "avg_loss": 5.222645, |
| "lr": 0.0002837192318611158, |
| "step": 5565, |
| "time_s": 5051.5 |
| } |
| ], |
| "val": [ |
| { |
| "epoch": 1, |
| "avg_loss": 6.385433 |
| }, |
| { |
| "epoch": 2, |
| "avg_loss": 5.7099 |
| }, |
| { |
| "epoch": 3, |
| "avg_loss": 5.391578 |
| }, |
| { |
| "epoch": 4, |
| "avg_loss": 5.185818 |
| }, |
| { |
| "epoch": 5, |
| "avg_loss": 5.030019 |
| } |
| ], |
| "sanity": [] |
| } |
