bert-base-uncased-issues-128
This model is a fine-tuned version of bert-base-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.0348
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: 32
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 16
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.3932 | 1.0 | 1409 | 2.0750 |
| 2.1659 | 2.0 | 2818 | 1.9781 |
| 2.0364 | 3.0 | 4227 | 2.1215 |
| 1.9399 | 4.0 | 5636 | 2.1018 |
| 1.8857 | 5.0 | 7045 | 1.9919 |
| 1.813 | 6.0 | 8454 | 2.2653 |
| 1.7505 | 7.0 | 9863 | 2.0857 |
| 1.7196 | 8.0 | 11272 | 1.9211 |
| 1.672 | 9.0 | 12681 | 1.9853 |
| 1.6379 | 10.0 | 14090 | 2.0391 |
| 1.6037 | 11.0 | 15499 | 1.9305 |
| 1.5699 | 12.0 | 16908 | 2.0291 |
| 1.5363 | 13.0 | 18317 | 2.0492 |
| 1.5155 | 14.0 | 19726 | 1.8807 |
| 1.4999 | 15.0 | 21135 | 1.8604 |
| 1.4784 | 16.0 | 22544 | 2.0348 |
Framework versions
- Transformers 4.18.0
- Pytorch 1.12.1
- Datasets 2.4.0
- Tokenizers 0.12.1