|
|
--- |
|
|
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-np |
|
|
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-np |
|
|
|
|
|
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: 0.2560 |
|
|
- Accuracy: 0.938 |
|
|
- Auc: 0.977 |
|
|
|
|
|
## 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: 5 |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Auc | |
|
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:-----:| |
|
|
| 0.6111 | 1.0 | 132 | 0.4996 | 0.924 | 0.968 | |
|
|
| 0.4567 | 2.0 | 264 | 0.3629 | 0.916 | 0.973 | |
|
|
| 0.3502 | 3.0 | 396 | 0.3241 | 0.88 | 0.976 | |
|
|
| 0.2987 | 4.0 | 528 | 0.2722 | 0.92 | 0.977 | |
|
|
| 0.2816 | 5.0 | 660 | 0.2560 | 0.938 | 0.977 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.49.0 |
|
|
- Pytorch 2.6.0+cu124 |
|
|
- Datasets 3.4.1 |
|
|
- Tokenizers 0.21.1 |
|
|
|
