This model is a fine-tuned version of gokulsrinivasagan/tinybert_train_book_ent_15p_ra on the GLUE QNLI 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 |
|---|---|---|---|---|
| 0.6589 | 1.0 | 410 | 0.6290 | 0.6297 |
| 0.6141 | 2.0 | 820 | 0.6044 | 0.6551 |
| 0.5687 | 3.0 | 1230 | 0.5987 | 0.6595 |
| 0.5125 | 4.0 | 1640 | 0.6282 | 0.6626 |
| 0.456 | 5.0 | 2050 | 0.6875 | 0.6539 |
| 0.4005 | 6.0 | 2460 | 0.7075 | 0.6621 |
| 0.3524 | 7.0 | 2870 | 0.8620 | 0.6551 |
| 0.3033 | 8.0 | 3280 | 0.8212 | 0.6639 |
model.safetensors 132 MBtraining_args.bin 5.4 kB