|
--- |
|
base_model: SALT-NLP/FLANG-ELECTRA |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
- f1 |
|
- precision |
|
- recall |
|
model-index: |
|
- name: FLANG-ELECTRA_flang-bert |
|
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. --> |
|
|
|
# FLANG-ELECTRA_flang-bert |
|
|
|
This model is a fine-tuned version of [SALT-NLP/FLANG-ELECTRA](https://huggingface.co/SALT-NLP/FLANG-ELECTRA) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.5930 |
|
- Accuracy: 0.8705 |
|
- F1: 0.8717 |
|
- Precision: 0.8772 |
|
- Recall: 0.8705 |
|
|
|
## 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: 0.0001 |
|
- train_batch_size: 32 |
|
- eval_batch_size: 32 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_steps: 1000 |
|
- num_epochs: 25 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:| |
|
| 0.6377 | 1.0 | 181 | 0.5174 | 0.8003 | 0.7860 | 0.8080 | 0.8003 | |
|
| 0.4035 | 2.0 | 362 | 0.4221 | 0.8580 | 0.8578 | 0.8611 | 0.8580 | |
|
| 0.2395 | 3.0 | 543 | 0.4535 | 0.8580 | 0.8560 | 0.8592 | 0.8580 | |
|
| 0.231 | 4.0 | 724 | 0.4335 | 0.8658 | 0.8657 | 0.8659 | 0.8658 | |
|
| 0.3369 | 5.0 | 905 | 0.5608 | 0.8081 | 0.8057 | 0.8151 | 0.8081 | |
|
| 0.2203 | 6.0 | 1086 | 0.5002 | 0.8705 | 0.8691 | 0.8706 | 0.8705 | |
|
| 0.239 | 7.0 | 1267 | 0.6676 | 0.8128 | 0.8125 | 0.8338 | 0.8128 | |
|
| 0.0938 | 8.0 | 1448 | 0.5930 | 0.8705 | 0.8717 | 0.8772 | 0.8705 | |
|
| 0.1329 | 9.0 | 1629 | 0.5017 | 0.8580 | 0.8571 | 0.8572 | 0.8580 | |
|
| 0.3598 | 10.0 | 1810 | 0.5126 | 0.8690 | 0.8675 | 0.8698 | 0.8690 | |
|
| 0.1615 | 11.0 | 1991 | 0.5945 | 0.8612 | 0.8605 | 0.8606 | 0.8612 | |
|
| 0.0923 | 12.0 | 2172 | 0.8213 | 0.8268 | 0.8292 | 0.8450 | 0.8268 | |
|
| 0.1296 | 13.0 | 2353 | 0.8647 | 0.8580 | 0.8586 | 0.8611 | 0.8580 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.37.0 |
|
- Pytorch 2.1.2 |
|
- Datasets 2.1.0 |
|
- Tokenizers 0.15.1 |
|
|
