electra-base-discriminator-answerable-or-not
This model is a fine-tuned version of google/electra-base-discriminator on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0461
- Accuracy: 0.9949
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Use adamw_torch_fused with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 50
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.0845 | 1.0 | 198 | 0.0633 | 0.9797 |
| 0.0023 | 2.0 | 396 | 0.0718 | 0.9899 |
| 0.0678 | 3.0 | 594 | 0.0615 | 0.9899 |
| 0.0006 | 4.0 | 792 | 0.0638 | 0.9899 |
| 0.0004 | 5.0 | 990 | 0.0697 | 0.9873 |
| 0.0216 | 6.0 | 1188 | 0.0575 | 0.9924 |
| 0.0406 | 7.0 | 1386 | 0.0461 | 0.9949 |
| 0.0002 | 8.0 | 1584 | 0.0649 | 0.9899 |
| 0.0002 | 9.0 | 1782 | 0.0639 | 0.9899 |
| 0.0002 | 10.0 | 1980 | 0.0637 | 0.9899 |
Framework versions
- Transformers 5.2.0
- Pytorch 2.10.0+cu128
- Datasets 4.5.0
- Tokenizers 0.22.2