metadata
library_name: transformers
license: mit
base_model: xlnet-large-cased
tags:
- generated_from_trainer
metrics:
- f1
- accuracy
model-index:
- name: CS221-xlnet-large-cased-finetuned-augmentation
results: []
CS221-xlnet-large-cased-finetuned-augmentation
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: 0.5488
- F1: 0.7778
- Roc Auc: 0.8358
- Accuracy: 0.5486
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 |
|---|---|---|---|---|---|---|
| 0.5737 | 1.0 | 165 | 0.5256 | 0.2747 | 0.5539 | 0.2067 |
| 0.433 | 2.0 | 330 | 0.3995 | 0.5828 | 0.7099 | 0.4027 |
| 0.3391 | 3.0 | 495 | 0.3516 | 0.7006 | 0.7727 | 0.4514 |
| 0.2481 | 4.0 | 660 | 0.3694 | 0.7110 | 0.7813 | 0.5015 |
| 0.1585 | 5.0 | 825 | 0.4033 | 0.7513 | 0.8097 | 0.4985 |
| 0.1021 | 6.0 | 990 | 0.4539 | 0.7405 | 0.7987 | 0.4878 |
| 0.0813 | 7.0 | 1155 | 0.4708 | 0.7430 | 0.7991 | 0.4985 |
| 0.0512 | 8.0 | 1320 | 0.5113 | 0.7554 | 0.8162 | 0.5426 |
| 0.0287 | 9.0 | 1485 | 0.5563 | 0.7598 | 0.8223 | 0.5289 |
| 0.0129 | 10.0 | 1650 | 0.5488 | 0.7778 | 0.8358 | 0.5486 |
| 0.0144 | 11.0 | 1815 | 0.5748 | 0.7595 | 0.8157 | 0.5471 |
| 0.0094 | 12.0 | 1980 | 0.6090 | 0.7557 | 0.8152 | 0.5532 |
| 0.0057 | 13.0 | 2145 | 0.6303 | 0.7592 | 0.8167 | 0.5395 |
Framework versions
- Transformers 4.47.0
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0