加载中…
加载中…
This model is a fine-tuned version of google/mobilebert-uncased on the GLUE WNLI 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 | Accuracy |
|---|---|---|---|---|
| 0.6938 | 1.0 | 5 | 0.6911 | 0.5634 |
| 0.6933 | 2.0 | 10 | 0.6917 | 0.5634 |
| 0.6931 | 3.0 | 15 | 0.6920 | 0.5634 |
| 0.693 | 4.0 | 20 | 0.6915 | 0.5634 |
| 0.693 | 5.0 | 25 | 0.6911 | 0.5634 |
| 0.693 | 6.0 | 30 | 0.6909 | 0.5634 |
| 0.693 | 7.0 | 35 | 0.6907 | 0.5634 |
| 0.693 | 8.0 | 40 | 0.6911 | 0.5634 |
| 0.6931 | 9.0 | 45 | 0.6908 | 0.5634 |
| 0.693 | 10.0 | 50 | 0.6912 | 0.5634 |
| 0.693 | 11.0 | 55 | 0.6918 | 0.5634 |
| 0.693 | 12.0 | 60 | 0.6918 | 0.5634 |