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: 1.2283
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 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 |
|---|---|---|---|
| 2.0993 | 1.0 | 291 | 1.7072 |
| 1.6343 | 2.0 | 582 | 1.4999 |
| 1.4973 | 3.0 | 873 | 1.3487 |
| 1.3941 | 4.0 | 1164 | 1.3365 |
| 1.3301 | 5.0 | 1455 | 1.2322 |
| 1.2875 | 6.0 | 1746 | 1.3580 |
| 1.2324 | 7.0 | 2037 | 1.3062 |
| 1.2051 | 8.0 | 2328 | 1.3315 |
| 1.1638 | 9.0 | 2619 | 1.2213 |
| 1.141 | 10.0 | 2910 | 1.1727 |
| 1.1298 | 11.0 | 3201 | 1.1251 |
| 1.1116 | 12.0 | 3492 | 1.1758 |
| 1.086 | 13.0 | 3783 | 1.2267 |
| 1.0769 | 14.0 | 4074 | 1.2108 |
| 1.0725 | 15.0 | 4365 | 1.2226 |
| 1.0597 | 16.0 | 4656 | 1.2283 |
Framework versions
- Transformers 4.49.0
- Pytorch 2.7.0.dev20250218+cu128
- Datasets 3.3.2
- Tokenizers 0.21.0
- Downloads last month
- 4
Model tree for abkds/bert-base-uncased-issues-128
Base model
google-bert/bert-base-uncased