CS221-xlm-roberta-base-amh-noaug-finetuned-amh-tapt
This model is a fine-tuned version of Kuongan/xlm-roberta-base-amh-noaug on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1361
- F1: 0.7860
- Roc Auc: 0.8699
- Accuracy: 0.7692
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 |
|---|---|---|---|---|---|---|
| 0.1718 | 1.0 | 221 | 0.1361 | 0.7860 | 0.8699 | 0.7692 |
| 0.1614 | 2.0 | 442 | 0.1363 | 0.7598 | 0.8680 | 0.7566 |
| 0.1413 | 3.0 | 663 | 0.1390 | 0.7758 | 0.8842 | 0.7464 |
| 0.1124 | 4.0 | 884 | 0.1582 | 0.7558 | 0.8585 | 0.7177 |
Framework versions
- Transformers 4.47.0
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0