| --- |
| library_name: transformers |
| license: apache-2.0 |
| base_model: google/electra-base-discriminator |
| tags: |
| - generated_from_trainer |
| metrics: |
| - accuracy |
| model-index: |
| - name: electra-problematic-classifier |
| results: [] |
| --- |
| |
| <!-- This model card has been generated automatically according to the information the Trainer had access to. You |
| should probably proofread and complete it, then remove this comment. --> |
|
|
| # electra-problematic-classifier |
|
|
| This model is a fine-tuned version of [google/electra-base-discriminator](https://huggingface.co/google/electra-base-discriminator) on an unknown dataset. |
| It achieves the following results on the evaluation set: |
| - Loss: 0.1953 |
| - Accuracy: 0.931 |
| - Auc: 0.98 |
|
|
| ## 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: 5e-05 |
| - train_batch_size: 8 |
| - eval_batch_size: 8 |
| - 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 | Accuracy | Auc | |
| |:-------------:|:-----:|:----:|:---------------:|:--------:|:-----:| |
| | 0.5987 | 1.0 | 263 | 0.4602 | 0.862 | 0.942 | |
| | 0.4339 | 2.0 | 526 | 0.3387 | 0.873 | 0.957 | |
| | 0.3674 | 3.0 | 789 | 0.2844 | 0.896 | 0.966 | |
| | 0.3266 | 4.0 | 1052 | 0.2732 | 0.891 | 0.972 | |
| | 0.2931 | 5.0 | 1315 | 0.2235 | 0.92 | 0.975 | |
| | 0.287 | 6.0 | 1578 | 0.2233 | 0.92 | 0.977 | |
| | 0.2784 | 7.0 | 1841 | 0.2101 | 0.931 | 0.979 | |
| | 0.2689 | 8.0 | 2104 | 0.2008 | 0.929 | 0.979 | |
| | 0.2601 | 9.0 | 2367 | 0.2005 | 0.931 | 0.98 | |
| | 0.2558 | 10.0 | 2630 | 0.1953 | 0.931 | 0.98 | |
|
|
|
|
| ### Framework versions |
|
|
| - Transformers 4.49.0 |
| - Pytorch 2.6.0+cu124 |
| - Datasets 3.4.1 |
| - Tokenizers 0.21.1 |
|
|
