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 |
|---|---|---|---|---|
| 0.5284 | 1.0 | 535 | 0.4948 | 0.4093 |
| 0.3529 | 2.0 | 1070 | 0.5135 | 0.4942 |
| 0.2417 | 3.0 | 1605 | 0.6303 | 0.5083 |
| 0.1818 | 4.0 | 2140 | 0.7696 | 0.5136 |
| 0.1302 | 5.0 | 2675 | 0.8774 | 0.5123 |
pytorch_model.bin 268 MBtraining_args.bin 3.1 kB