electra-base-discriminator-DIALOCONAN-CLS
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: 0.3341
- Precision: 0.7056
- Recall: 0.7079
- F1: 0.7066
- Accuracy: 0.9413
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: 3e-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.3817 | 1.0 | 2500 | 0.3988 | 0.6877 | 0.6824 | 0.6831 | 0.9088 |
| 0.2379 | 2.0 | 5000 | 0.3323 | 0.7020 | 0.7044 | 0.7028 | 0.9362 |
| 0.1475 | 3.0 | 7500 | 0.3341 | 0.7056 | 0.7079 | 0.7066 | 0.9413 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3