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 |
|---|---|---|---|---|
| 0.524 | 1.0 | 535 | 0.5547 | 0.3891 |
| 0.3463 | 2.0 | 1070 | 0.5250 | 0.5011 |
| 0.2329 | 3.0 | 1605 | 0.6321 | 0.5239 |
| 0.1677 | 4.0 | 2140 | 0.7752 | 0.5372 |
| 0.1197 | 5.0 | 2675 | 0.8455 | 0.5536 |
pytorch_model.bin 268 MBtraining_args.bin 2.9 kB