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: 1.2328
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_FUSED 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 | 1.6934 |
| 1.6321 | 2.0 | 582 | 1.5068 |
| 1.4991 | 3.0 | 873 | 1.3577 |
| 1.3971 | 4.0 | 1164 | 1.3399 |
| 1.3343 | 5.0 | 1455 | 1.2283 |
| 1.2882 | 6.0 | 1746 | 1.3563 |
| 1.2348 | 7.0 | 2037 | 1.2993 |
| 1.2033 | 8.0 | 2328 | 1.3485 |
| 1.1685 | 9.0 | 2619 | 1.2150 |
| 1.1422 | 10.0 | 2910 | 1.1714 |
| 1.1260 | 11.0 | 3201 | 1.1260 |
| 1.1110 | 12.0 | 3492 | 1.1844 |
| 1.0884 | 13.0 | 3783 | 1.2116 |
| 1.0769 | 14.0 | 4074 | 1.2125 |
| 1.0755 | 15.0 | 4365 | 1.2225 |
| 1.0622 | 16.0 | 4656 | 1.2328 |
Framework versions
- Transformers 5.15.0
- Pytorch 2.12.1+cu130
- Datasets 5.0.1
- Tokenizers 0.22.2