This model is a fine-tuned version of distilbert-base-uncased on the glue 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 |
|---|---|---|---|---|
| 0.5261 | 1.0 | 535 | 0.5509 | 0.3827 |
| 0.3498 | 2.0 | 1070 | 0.4936 | 0.5295 |
| 0.2369 | 3.0 | 1605 | 0.6505 | 0.5248 |
| 0.1637 | 4.0 | 2140 | 0.8107 | 0.5396 |
| 0.1299 | 5.0 | 2675 | 0.8738 | 0.5387 |
pytorch_model.bin 268 MBtraining_args.bin 2.9 kB