electra-small-discriminator-finetuned-HC3-mix
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: 0.1812
- F1: 0.9206
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: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 |
|---|---|---|---|---|
| 0.1116 | 1.0 | 8956 | 0.2602 | 0.8838 |
| 0.0826 | 2.0 | 17912 | 0.1812 | 0.9206 |
| 0.0692 | 3.0 | 26868 | 0.2226 | 0.9143 |
| 0.0539 | 4.0 | 35824 | 0.2544 | 0.9126 |
| 0.0492 | 5.0 | 44780 | 0.2500 | 0.9175 |
Framework versions
- Transformers 4.26.0
- Pytorch 1.13.1+cu116
- Datasets 2.9.0
- Tokenizers 0.13.2