This model is a fine-tuned version of distilbert-base-uncased on the massive 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 |
|---|---|---|---|---|
| 1.4555 | 1.0 | 720 | 0.5983 | 0.8426 |
| 0.407 | 2.0 | 1440 | 0.4702 | 0.8775 |
| 0.2095 | 3.0 | 2160 | 0.5319 | 0.8834 |
| 0.1172 | 4.0 | 2880 | 0.5902 | 0.8810 |
| 0.0683 | 5.0 | 3600 | 0.6555 | 0.8810 |
| 0.042 | 6.0 | 4320 | 0.6989 | 0.8879 |
| 0.0253 | 7.0 | 5040 | 0.6963 | 0.8928 |
| 0.0208 | 8.0 | 5760 | 0.7313 | 0.8908 |
| 0.0119 | 9.0 | 6480 | 0.7683 | 0.8923 |
| 0.0093 | 10.0 | 7200 | 0.7693 | 0.8947 |
| 0.0071 | 11.0 | 7920 | 0.7873 | 0.8923 |
| 0.0047 | 12.0 | 8640 | 0.8275 | 0.8893 |
| 0.003 | 13.0 | 9360 | 0.8312 | 0.8928 |
pytorch_model.bin 268 MBtraining_args.bin 3.4 kB