加载中…
加载中…
This model is a fine-tuned version of google/mobilebert-uncased on the GLUE STSB dataset. It achieves the following results on the evaluation set:
More information needed
More information needed
More information needed
The following hyperparameters were used during training:
| Training Loss | Epoch | Step | Validation Loss | Pearson | Spearmanr | Combined Score |
|---|---|---|---|---|---|---|
| 2.524 | 1.0 | 45 | 1.3607 | -0.0066 | -0.0281 | -0.0174 |
| 1.0877 | 2.0 | 90 | 1.1729 | 0.0446 | 0.0497 | 0.0472 |
| 1.0648 | 3.0 | 135 | 1.1505 | 0.0470 | 0.0414 | 0.0442 |
| 1.0737 | 4.0 | 180 | 1.1564 | 0.0472 | 0.0464 | 0.0468 |
| 1.0445 | 5.0 | 225 | 1.1971 | 0.0529 | 0.0575 | 0.0552 |
| 1.0296 | 6.0 | 270 | 1.1723 | 0.0578 | 0.0727 | 0.0652 |
| 1.026 | 7.0 | 315 | 1.2735 | 0.0621 | 0.0606 | 0.0614 |
| 1.0216 | 8.0 | 360 | 1.2214 | 0.0666 | 0.0700 | 0.0683 |