bert-base-uncased-git-issues-300
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: 1.1053
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 |
|---|---|---|---|
| 1.8844 | 1.0 | 292 | 1.5801 |
| 1.4336 | 2.0 | 584 | 1.3511 |
| 1.3005 | 3.0 | 876 | 1.3213 |
| 1.2259 | 4.0 | 1168 | 1.3135 |
| 1.1555 | 5.0 | 1460 | 1.2115 |
| 1.1244 | 6.0 | 1752 | 1.1086 |
| 1.0804 | 7.0 | 2044 | 1.1925 |
| 1.0563 | 8.0 | 2336 | 1.1238 |
| 1.028 | 9.0 | 2628 | 1.1172 |
| 1.0075 | 10.0 | 2920 | 1.0936 |
| 0.9868 | 11.0 | 3212 | 1.0710 |
| 0.9761 | 12.0 | 3504 | 1.1149 |
| 0.9529 | 13.0 | 3796 | 1.0510 |
| 0.9476 | 14.0 | 4088 | 1.0389 |
| 0.9407 | 15.0 | 4380 | 1.0905 |
| 0.9362 | 16.0 | 4672 | 1.1053 |
Framework versions
- Transformers 4.32.1
- Pytorch 2.2.0.dev20231111
- Datasets 2.14.6
- Tokenizers 0.13.3
- Downloads last month
- 3
Model tree for ClementPoirier/bert-base-uncased-git-issues-300
Base model
google-bert/bert-base-uncased