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 |
|---|---|---|---|---|
| 0.5246 | 1.0 | 535 | 0.5219 | 0.4442 |
| 0.3506 | 2.0 | 1070 | 0.5133 | 0.5127 |
| 0.2395 | 3.0 | 1605 | 0.6590 | 0.5291 |
| 0.17 | 4.0 | 2140 | 0.7683 | 0.5456 |
| 0.1297 | 5.0 | 2675 | 0.8374 | 0.5573 |
pytorch_model.bin 268 MBtraining_args.bin 3.1 kB