electra_hongkongese_small_pos_wiki_lihkg_cc100
This model is a fine-tuned version of toastynews/electra-hongkongese-small-discriminator on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1796
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: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.232 | 0.3000 | 6123 | 0.2192 |
| 0.2465 | 0.6000 | 12246 | 0.2052 |
| 0.2396 | 0.9000 | 18369 | 0.1906 |
| 0.2128 | 1.2001 | 24492 | 0.1897 |
| 0.2007 | 1.5001 | 30615 | 0.1883 |
| 0.2019 | 1.8001 | 36738 | 0.1832 |
| 0.1864 | 2.1001 | 42861 | 0.1813 |
| 0.2051 | 2.4001 | 48984 | 0.1799 |
| 0.1837 | 2.7001 | 55107 | 0.1796 |
Framework versions
- Transformers 4.44.0
- Pytorch 2.2.1
- Datasets 2.21.0
- Tokenizers 0.19.1