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: 1.1776
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 |
|---|---|---|---|
| 2.1103 | 1.0 | 291 | 1.6937 |
| 1.6335 | 2.0 | 582 | 1.3744 |
| 1.4812 | 3.0 | 873 | 1.4336 |
| 1.3971 | 4.0 | 1164 | 1.4362 |
| 1.3464 | 5.0 | 1455 | 1.2699 |
| 1.2876 | 6.0 | 1746 | 1.3192 |
| 1.2284 | 7.0 | 2037 | 1.2069 |
| 1.2096 | 8.0 | 2328 | 1.2780 |
| 1.1787 | 9.0 | 2619 | 1.2831 |
| 1.1493 | 10.0 | 2910 | 1.2099 |
| 1.1242 | 11.0 | 3201 | 1.2721 |
| 1.1006 | 12.0 | 3492 | 1.1517 |
| 1.0914 | 13.0 | 3783 | 1.1563 |
| 1.0782 | 14.0 | 4074 | 1.0730 |
| 1.0647 | 15.0 | 4365 | 1.2635 |
| 1.0702 | 16.0 | 4656 | 1.1776 |
Framework versions
- Transformers 4.34.0
- Pytorch 1.13.1+cu117
- Datasets 2.14.5
- Tokenizers 0.14.1