<!-- 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. -->
kuglerk_adapted_bert-base-cased
This model is a fine-tuned version of bert-base-cased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.8087
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: 4e-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 25
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.4035 | 1.0 | 84 | 2.1206 |
| 2.1438 | 2.0 | 168 | 1.9904 |
| 2.0971 | 3.0 | 252 | 2.0585 |
| 1.9539 | 4.0 | 336 | 1.9030 |
| 1.9094 | 5.0 | 420 | 1.8884 |
| 1.73 | 6.0 | 504 | 1.8904 |
| 1.7158 | 7.0 | 588 | 1.8781 |
| 1.5977 | 8.0 | 672 | 1.8708 |
| 1.5389 | 9.0 | 756 | 1.8401 |
| 1.5116 | 10.0 | 840 | 1.8857 |
| 1.4251 | 11.0 | 924 | 1.9454 |
| 1.4667 | 12.0 | 1008 | 1.8755 |
| 1.3729 | 13.0 | 1092 | 1.8515 |
| 1.2514 | 14.0 | 1176 | 1.8990 |
| 1.2987 | 15.0 | 1260 | 1.8410 |
| 1.1944 | 16.0 | 1344 | 1.8475 |
| 1.2191 | 17.0 | 1428 | 1.9417 |
| 1.1865 | 18.0 | 1512 | 1.9362 |
| 1.2222 | 19.0 | 1596 | 1.9161 |
| 1.1874 | 20.0 | 1680 | 1.9455 |
| 1.1469 | 21.0 | 1764 | 1.9746 |
| 1.0914 | 22.0 | 1848 | 1.8935 |
| 1.0565 | 23.0 | 1932 | 1.9497 |
| 1.123 | 24.0 | 2016 | 1.8756 |
| 1.1232 | 25.0 | 2100 | 1.9511 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu117
- Datasets 2.14.3
- Tokenizers 0.13.3
