CS221-xlm-roberta-base-finetuned-arq
This model is a fine-tuned version of xlm-roberta-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.5808
- F1: 0.2870
- Roc Auc: 0.5609
- Accuracy: 0.09
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: 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: cosine
- lr_scheduler_warmup_steps: 100
- num_epochs: 20
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 | Roc Auc | Accuracy |
|---|---|---|---|---|---|---|
| 0.5876 | 1.0 | 113 | 0.6066 | 0.0 | 0.5 | 0.12 |
| 0.5673 | 2.0 | 226 | 0.5784 | 0.0081 | 0.5021 | 0.12 |
| 0.554 | 3.0 | 339 | 0.5780 | 0.0081 | 0.5021 | 0.12 |
| 0.6036 | 4.0 | 452 | 0.5756 | 0.0880 | 0.5215 | 0.14 |
| 0.5756 | 5.0 | 565 | 0.5796 | 0.1288 | 0.5288 | 0.1 |
| 0.5387 | 6.0 | 678 | 0.5680 | 0.2431 | 0.5481 | 0.11 |
| 0.5177 | 7.0 | 791 | 0.5686 | 0.2086 | 0.5469 | 0.14 |
| 0.5119 | 8.0 | 904 | 0.5808 | 0.2870 | 0.5609 | 0.09 |
| 0.5182 | 9.0 | 1017 | 0.5769 | 0.2439 | 0.5494 | 0.13 |
| 0.5092 | 10.0 | 1130 | 0.5799 | 0.2715 | 0.5621 | 0.14 |
| 0.4283 | 11.0 | 1243 | 0.5928 | 0.2675 | 0.5629 | 0.14 |
Framework versions
- Transformers 4.47.1
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0