metadata
license: mit
base_model: xlnet/xlnet-base-cased
tags:
- generated_from_trainer
metrics:
- f1
- accuracy
model-index:
- name: xlnet-base-cased-airlines-news-multi-label
results: []
xlnet-base-cased-airlines-news-multi-label
This model is a fine-tuned version of xlnet/xlnet-base-cased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.2822
- F1: 0.6647
- Roc Auc: 0.8080
- Accuracy: 0.6116
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: 12
- eval_batch_size: 12
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 15
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 | Roc Auc | Accuracy |
|---|---|---|---|---|---|---|
| No log | 1.0 | 150 | 0.2088 | 0.5979 | 0.7399 | 0.6027 |
| No log | 2.0 | 300 | 0.1928 | 0.6596 | 0.7725 | 0.6562 |
| No log | 3.0 | 450 | 0.2049 | 0.6327 | 0.7653 | 0.5982 |
| 0.2167 | 4.0 | 600 | 0.2226 | 0.6506 | 0.8007 | 0.6027 |
| 0.2167 | 5.0 | 750 | 0.2280 | 0.6288 | 0.7666 | 0.5893 |
| 0.2167 | 6.0 | 900 | 0.2418 | 0.6295 | 0.7709 | 0.5938 |
| 0.0812 | 7.0 | 1050 | 0.2610 | 0.6258 | 0.7722 | 0.5982 |
| 0.0812 | 8.0 | 1200 | 0.2756 | 0.6098 | 0.7606 | 0.5804 |
| 0.0812 | 9.0 | 1350 | 0.2822 | 0.6647 | 0.8080 | 0.6116 |
| 0.0325 | 10.0 | 1500 | 0.2908 | 0.6378 | 0.7873 | 0.5938 |
| 0.0325 | 11.0 | 1650 | 0.3050 | 0.6319 | 0.7860 | 0.5938 |
| 0.0325 | 12.0 | 1800 | 0.3044 | 0.6277 | 0.7830 | 0.5804 |
| 0.0325 | 13.0 | 1950 | 0.3030 | 0.6254 | 0.7804 | 0.5804 |
| 0.015 | 14.0 | 2100 | 0.3057 | 0.6319 | 0.7860 | 0.5848 |
| 0.015 | 15.0 | 2250 | 0.3013 | 0.6168 | 0.7744 | 0.5670 |
Framework versions
- Transformers 4.41.0
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1