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: 1.2751
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 |
|---|---|---|---|
| 2.3494 | 1.0 | 291 | 1.8032 |
| 1.7514 | 2.0 | 582 | 1.5877 |
| 1.587 | 3.0 | 873 | 1.4322 |
| 1.4774 | 4.0 | 1164 | 1.4187 |
| 1.4037 | 5.0 | 1455 | 1.2945 |
| 1.3534 | 6.0 | 1746 | 1.4275 |
| 1.2994 | 7.0 | 2037 | 1.3524 |
| 1.2719 | 8.0 | 2328 | 1.3865 |
| 1.2286 | 9.0 | 2619 | 1.2797 |
| 1.2039 | 10.0 | 2910 | 1.2218 |
| 1.1924 | 11.0 | 3201 | 1.1750 |
| 1.1774 | 12.0 | 3492 | 1.2321 |
| 1.1526 | 13.0 | 3783 | 1.2489 |
| 1.1409 | 14.0 | 4074 | 1.2568 |
| 1.1367 | 15.0 | 4365 | 1.2646 |
| 1.1273 | 16.0 | 4656 | 1.2751 |
Framework versions
- Transformers 4.50.0.dev0
- Pytorch 2.6.0+cu124
- Datasets 3.3.2
- Tokenizers 0.21.0