CS221-xlnet-large-cased-finetuned-semeval-NT
This model is a fine-tuned version of xlnet-large-cased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.5889
- F1: 0.4593
- Roc Auc: 0.6262
- Accuracy: 0.1516
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: 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 |
|---|---|---|---|---|---|---|
| 0.5715 | 1.0 | 139 | 0.5889 | 0.4593 | 0.6262 | 0.1516 |
| 0.5684 | 2.0 | 278 | 0.5823 | 0.4593 | 0.6262 | 0.1516 |
| 0.5765 | 3.0 | 417 | 0.5804 | 0.4593 | 0.6262 | 0.1516 |
| 0.5568 | 4.0 | 556 | 0.5788 | 0.4593 | 0.6262 | 0.1516 |
Framework versions
- Transformers 4.47.1
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0