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 |
|---|---|---|---|---|
| 0.8228 | 1.0 | 67 | 0.6863 | 0.0 |
| 0.7969 | 2.0 | 134 | 0.6870 | 0.0 |
| 0.7965 | 3.0 | 201 | 0.6834 | 0.0 |
| 0.795 | 4.0 | 268 | 0.6835 | 0.0 |
| 0.7939 | 5.0 | 335 | 0.6807 | 0.0 |
| 0.7451 | 6.0 | 402 | 0.6986 | 0.0672 |
| 0.6395 | 7.0 | 469 | 0.7051 | 0.0875 |
| 0.6042 | 8.0 | 536 | 0.7293 | 0.1094 |
| 0.5756 | 9.0 | 603 | 0.7376 | 0.1173 |
| 0.5558 | 10.0 | 670 | 0.7879 | 0.1123 |