metadata
license: mit
base_model: xlnet-base-cased
tags:
- generated_from_trainer
model-index:
- name: XLnet-cased-AS-HU-f1-score
results: []
XLnet-cased-AS-HU-f1-score
This model is a fine-tuned version of xlnet-base-cased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.5247
- F1-score: 0.7609
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: 5e-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 | F1-score |
|---|---|---|---|---|
| 0.7055 | 1.0 | 64 | 0.6796 | 0.3697 |
| 0.6944 | 2.0 | 128 | 0.6786 | 0.3697 |
| 0.7 | 3.0 | 192 | 0.6800 | 0.3697 |
| 0.6818 | 4.0 | 256 | 0.6797 | 0.3697 |
| 0.6848 | 5.0 | 320 | 0.6902 | 0.3697 |
| 0.6898 | 6.0 | 384 | 0.6777 | 0.3697 |
| 0.6877 | 7.0 | 448 | 0.6648 | 0.3697 |
| 0.6805 | 8.0 | 512 | 0.6313 | 0.3697 |
| 0.5873 | 9.0 | 576 | 0.6145 | 0.6381 |
| 0.4984 | 10.0 | 640 | 0.5247 | 0.7609 |
Framework versions
- Transformers 4.41.1
- Pytorch 2.0.1+cu117
- Datasets 2.19.1
- Tokenizers 0.19.1