Loading…
Loading…
This model is a fine-tuned version of google/mobilebert-uncased on the GLUE COLA 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 | Matthews Correlation |
|---|---|---|---|---|
| 0.6155 | 1.0 | 67 | 0.6180 | 0.0 |
| 0.6079 | 2.0 | 134 | 0.6180 | 0.0 |
| 0.6074 | 3.0 | 201 | 0.6181 | 0.0 |
| 0.607 | 4.0 | 268 | 0.6173 | 0.0 |
| 0.6064 | 5.0 | 335 | 0.6180 | 0.0 |
| 0.6021 | 6.0 | 402 | 0.6077 | 0.0 |
| 0.5484 | 7.0 | 469 | 0.6393 | 0.0688 |
| 0.4961 | 8.0 | 536 | 0.6882 | 0.0851 |
| 0.4656 | 9.0 | 603 | 0.6623 | 0.1116 |
| 0.448 | 10.0 | 670 | 0.7584 | 0.1089 |
| 0.4358 | 11.0 | 737 | 0.7178 | 0.1299 |