results
This model is a fine-tuned version of google/electra-small-discriminator on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1960
- F1: 0.9397
- Accuracy: 0.9397
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: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 | Accuracy |
|---|---|---|---|---|---|
| No log | 1.0 | 71 | 0.4747 | 0.8231 | 0.8254 |
| 0.5551 | 2.0 | 142 | 0.3442 | 0.8938 | 0.8940 |
| 0.3465 | 3.0 | 213 | 0.3478 | 0.8695 | 0.8711 |
| 0.3465 | 4.0 | 284 | 0.2578 | 0.9189 | 0.9189 |
| 0.2733 | 5.0 | 355 | 0.2605 | 0.9084 | 0.9085 |
| 0.2125 | 6.0 | 426 | 0.2212 | 0.9272 | 0.9272 |
| 0.2125 | 7.0 | 497 | 0.2177 | 0.9272 | 0.9272 |
| 0.1636 | 8.0 | 568 | 0.2054 | 0.9376 | 0.9376 |
| 0.1535 | 9.0 | 639 | 0.1949 | 0.9418 | 0.9418 |
| 0.1274 | 10.0 | 710 | 0.1960 | 0.9397 | 0.9397 |
Framework versions
- Transformers 4.52.4
- Pytorch 2.6.0+cu124
- Datasets 4.0.0
- Tokenizers 0.21.2