metadata
license: mit
base_model: xlnet-base-cased
tags:
- generated_from_trainer
model-index:
- name: XLNet-Twitter-Analysis
results: []
XLNet-Twitter-Analysis
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: 0.2030
- Rmse: 0.1868
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: 3e-05
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Rmse |
|---|---|---|---|---|
| 0.1889 | 1.0 | 1599 | 0.1784 | 0.1989 |
| 0.1301 | 2.0 | 3198 | 0.1554 | 0.1962 |
| 0.1012 | 3.0 | 4797 | 0.1586 | 0.1859 |
| 0.0784 | 4.0 | 6396 | 0.1731 | 0.1913 |
| 0.0609 | 5.0 | 7995 | 0.1475 | 0.1893 |
| 0.0459 | 6.0 | 9594 | 0.1822 | 0.1847 |
| 0.0413 | 7.0 | 11193 | 0.2089 | 0.1872 |
| 0.0382 | 8.0 | 12792 | 0.1923 | 0.1921 |
| 0.0304 | 9.0 | 14391 | 0.1954 | 0.1893 |
| 0.0261 | 10.0 | 15990 | 0.2030 | 0.1868 |
Framework versions
- Transformers 4.34.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1