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: 0.2274
- F1: 0.9228
- Accuracy: 0.9231
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: 50
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 | Accuracy |
|---|---|---|---|---|---|
| No log | 1.0 | 71 | 0.4753 | 0.8307 | 0.8316 |
| 0.562 | 2.0 | 142 | 0.3420 | 0.8875 | 0.8877 |
| 0.3566 | 3.0 | 213 | 0.3171 | 0.8935 | 0.8940 |
| 0.3566 | 4.0 | 284 | 0.2419 | 0.9189 | 0.9189 |
| 0.2833 | 5.0 | 355 | 0.2132 | 0.9355 | 0.9356 |
| 0.2139 | 6.0 | 426 | 0.1963 | 0.9314 | 0.9314 |
| 0.2139 | 7.0 | 497 | 0.2274 | 0.9228 | 0.9231 |
Framework versions
- Transformers 4.52.4
- Pytorch 2.6.0+cu124
- Datasets 4.0.0
- Tokenizers 0.21.2