|
--- |
|
library_name: transformers |
|
license: mit |
|
base_model: xlnet/xlnet-large-cased |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- f1 |
|
- accuracy |
|
model-index: |
|
- name: UIT-xlnet-large-cased-finetuned |
|
results: [] |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# UIT-xlnet-large-cased-finetuned |
|
|
|
This model is a fine-tuned version of [xlnet/xlnet-large-cased](https://huggingface.co./xlnet/xlnet-large-cased) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.7544 |
|
- F1: 0.7191 |
|
- Roc Auc: 0.7866 |
|
- Accuracy: 0.4765 |
|
|
|
## 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 | |
|
|:-------------:|:-----:|:----:|:---------------:|:------:|:-------:|:--------:| |
|
| 0.6047 | 1.0 | 139 | 0.5968 | 0.1435 | 0.5 | 0.1300 | |
|
| 0.551 | 2.0 | 278 | 0.5818 | 0.1393 | 0.4981 | 0.1318 | |
|
| 0.549 | 3.0 | 417 | 0.5342 | 0.3274 | 0.5764 | 0.1931 | |
|
| 0.4438 | 4.0 | 556 | 0.5083 | 0.4820 | 0.6362 | 0.3105 | |
|
| 0.3647 | 5.0 | 695 | 0.4219 | 0.6477 | 0.7325 | 0.4043 | |
|
| 0.3083 | 6.0 | 834 | 0.4281 | 0.6663 | 0.7489 | 0.4079 | |
|
| 0.2307 | 7.0 | 973 | 0.4171 | 0.6962 | 0.7756 | 0.4404 | |
|
| 0.1962 | 8.0 | 1112 | 0.4786 | 0.6985 | 0.7706 | 0.4242 | |
|
| 0.1404 | 9.0 | 1251 | 0.5594 | 0.6960 | 0.7769 | 0.4152 | |
|
| 0.0739 | 10.0 | 1390 | 0.5989 | 0.7033 | 0.7768 | 0.4567 | |
|
| 0.0604 | 11.0 | 1529 | 0.6251 | 0.7028 | 0.7758 | 0.4603 | |
|
| 0.0357 | 12.0 | 1668 | 0.6687 | 0.7077 | 0.7822 | 0.4531 | |
|
| 0.0198 | 13.0 | 1807 | 0.7097 | 0.6973 | 0.7701 | 0.4422 | |
|
| 0.0339 | 14.0 | 1946 | 0.7104 | 0.6992 | 0.7732 | 0.4531 | |
|
| 0.0228 | 15.0 | 2085 | 0.7339 | 0.7150 | 0.7842 | 0.4765 | |
|
| 0.0147 | 16.0 | 2224 | 0.7418 | 0.6941 | 0.7734 | 0.4711 | |
|
| 0.0078 | 17.0 | 2363 | 0.7514 | 0.7130 | 0.7833 | 0.4765 | |
|
| 0.0069 | 18.0 | 2502 | 0.7544 | 0.7191 | 0.7866 | 0.4765 | |
|
| 0.0067 | 19.0 | 2641 | 0.7570 | 0.7146 | 0.7845 | 0.4693 | |
|
| 0.005 | 20.0 | 2780 | 0.7579 | 0.7134 | 0.7834 | 0.4729 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.48.1 |
|
- Pytorch 2.4.0 |
|
- Datasets 3.0.1 |
|
- Tokenizers 0.21.0 |
|
|
