CS221-xlm-roberta-base-orm-noaug-finetuned-orm-tapt
This model is a fine-tuned version of Kuongan/xlm-roberta-base-orm-noaug on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1390
- F1: 0.6484
- Roc Auc: 0.7975
- Accuracy: 0.7777
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: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 100
- num_epochs: 20
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 | Roc Auc | Accuracy |
|---|---|---|---|---|---|---|
| 0.1488 | 1.0 | 144 | 0.1282 | 0.6019 | 0.7611 | 0.7768 |
| 0.149 | 2.0 | 288 | 0.1222 | 0.6447 | 0.7869 | 0.8038 |
| 0.1253 | 3.0 | 432 | 0.1391 | 0.5918 | 0.7669 | 0.7559 |
| 0.135 | 4.0 | 576 | 0.1390 | 0.6484 | 0.7975 | 0.7777 |
| 0.1245 | 5.0 | 720 | 0.1524 | 0.6398 | 0.8035 | 0.7507 |
| 0.1309 | 6.0 | 864 | 0.1465 | 0.6385 | 0.7858 | 0.7681 |
| 0.0773 | 7.0 | 1008 | 0.1445 | 0.6336 | 0.7944 | 0.7759 |
Framework versions
- Transformers 4.47.0
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0