CS221-xlnet-base-cased-finetuned-semeval-NT
This model is a fine-tuned version of xlnet-base-cased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.4252
- F1: 0.7133
- Roc Auc: 0.7762
- Accuracy: 0.4549
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 |
|---|---|---|---|---|---|---|
| 0.5169 | 1.0 | 139 | 0.5128 | 0.3030 | 0.5573 | 0.1986 |
| 0.4052 | 2.0 | 278 | 0.3975 | 0.6320 | 0.7239 | 0.3755 |
| 0.3648 | 3.0 | 417 | 0.3852 | 0.6671 | 0.7442 | 0.4170 |
| 0.2884 | 4.0 | 556 | 0.4045 | 0.6905 | 0.7644 | 0.4278 |
| 0.1952 | 5.0 | 695 | 0.4252 | 0.7133 | 0.7762 | 0.4549 |
| 0.1521 | 6.0 | 834 | 0.4328 | 0.7091 | 0.7715 | 0.4242 |
| 0.1186 | 7.0 | 973 | 0.4609 | 0.6780 | 0.7449 | 0.4134 |
| 0.0942 | 8.0 | 1112 | 0.5017 | 0.6978 | 0.7816 | 0.4477 |
Framework versions
- Transformers 4.47.1
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0