Loading…
Loading…
This model is a fine-tuned version of google/mobilebert-uncased on the GLUE RTE 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 |
|---|---|---|---|---|
| 0.4088 | 1.0 | 20 | 0.3931 | 0.5271 |
| 0.4081 | 2.0 | 40 | 0.3922 | 0.5271 |
| 0.4076 | 3.0 | 60 | 0.3910 | 0.5271 |
| 0.4068 | 4.0 | 80 | 0.3941 | 0.5343 |
| 0.4069 | 5.0 | 100 | 0.3924 | 0.5343 |
| 0.4022 | 6.0 | 120 | 0.3975 | 0.5343 |
| 0.3801 | 7.0 | 140 | 0.4060 | 0.5415 |
| 0.3447 | 8.0 | 160 | 0.5080 | 0.4982 |