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: 1.2444
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 |
|---|---|---|---|
| 2.1037 | 1.0 | 291 | 1.6984 |
| 1.631 | 2.0 | 582 | 1.5150 |
| 1.4964 | 3.0 | 873 | 1.3496 |
| 1.3943 | 4.0 | 1164 | 1.3321 |
| 1.3299 | 5.0 | 1455 | 1.2334 |
| 1.2829 | 6.0 | 1746 | 1.3579 |
| 1.2299 | 7.0 | 2037 | 1.3037 |
| 1.2022 | 8.0 | 2328 | 1.3453 |
| 1.1665 | 9.0 | 2619 | 1.2221 |
| 1.139 | 10.0 | 2910 | 1.1740 |
| 1.1281 | 11.0 | 3201 | 1.1469 |
| 1.1093 | 12.0 | 3492 | 1.1860 |
| 1.0891 | 13.0 | 3783 | 1.2281 |
| 1.0763 | 14.0 | 4074 | 1.2051 |
| 1.0718 | 15.0 | 4365 | 1.2307 |
| 1.0643 | 16.0 | 4656 | 1.2444 |
Framework versions
- Transformers 4.57.1
- Pytorch 2.8.0+cu126
- Datasets 4.0.0
- Tokenizers 0.22.1
- Downloads last month
- 14
Model tree for JamesLemo/bert-base-uncased-issues-128
Base model
google-bert/bert-base-uncased