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: 1.2209
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: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 16
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.1048 | 1.0 | 291 | 1.6942 |
| 1.6343 | 2.0 | 582 | 1.5088 |
| 1.4996 | 3.0 | 873 | 1.3541 |
| 1.3963 | 4.0 | 1164 | 1.3353 |
| 1.3343 | 5.0 | 1455 | 1.2418 |
| 1.2852 | 6.0 | 1746 | 1.3667 |
| 1.2326 | 7.0 | 2037 | 1.3002 |
| 1.2052 | 8.0 | 2328 | 1.3470 |
| 1.1693 | 9.0 | 2619 | 1.2118 |
| 1.1421 | 10.0 | 2910 | 1.1772 |
| 1.1244 | 11.0 | 3201 | 1.1246 |
| 1.1114 | 12.0 | 3492 | 1.1815 |
| 1.0923 | 13.0 | 3783 | 1.2266 |
| 1.0762 | 14.0 | 4074 | 1.2137 |
| 1.0700 | 15.0 | 4365 | 1.2337 |
| 1.0621 | 16.0 | 4656 | 1.2209 |
Framework versions
- Transformers 5.12.0
- Pytorch 2.7.0+cu128
- Datasets 4.0.0
- Tokenizers 0.22.2