metadata
library_name: transformers
license: cc-by-4.0
base_model: sercetexam9/BantuBERTa-vmw-finetuned-vmw-MICRO
tags:
- generated_from_trainer
metrics:
- f1
- accuracy
model-index:
- name: BantuBERTa-vmw-finetuned-vmw-MICRO-finetuned-augmentation-LUNAR-TAPT-micro
results: []
BantuBERTa-vmw-finetuned-vmw-MICRO-finetuned-augmentation-LUNAR-TAPT-micro
This model is a fine-tuned version of sercetexam9/BantuBERTa-vmw-finetuned-vmw-MICRO on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0908
- F1: 0.7896
- Roc Auc: 0.8843
- Accuracy: 0.8544
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 100
- num_epochs: 20
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 | Roc Auc | Accuracy |
|---|---|---|---|---|---|---|
| 0.0976 | 1.0 | 169 | 0.0832 | 0.7877 | 0.8538 | 0.8603 |
| 0.0954 | 2.0 | 338 | 0.0827 | 0.7804 | 0.8586 | 0.8559 |
| 0.0741 | 3.0 | 507 | 0.0908 | 0.7896 | 0.8843 | 0.8544 |
| 0.063 | 4.0 | 676 | 0.1013 | 0.7048 | 0.8015 | 0.8187 |
| 0.0543 | 5.0 | 845 | 0.0973 | 0.7664 | 0.8646 | 0.8410 |
| 0.0546 | 6.0 | 1014 | 0.0998 | 0.7510 | 0.8527 | 0.8321 |
| 0.0516 | 7.0 | 1183 | 0.1034 | 0.7261 | 0.8329 | 0.8202 |
Framework versions
- Transformers 4.45.1
- Pytorch 2.4.0
- Datasets 3.0.1
- Tokenizers 0.20.0