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: 1.2434
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 |
|---|---|---|---|
| 2.1059 | 1.0 | 291 | 1.6941 |
| 1.6323 | 2.0 | 582 | 1.5158 |
| 1.4958 | 3.0 | 873 | 1.3616 |
| 1.3924 | 4.0 | 1164 | 1.3312 |
| 1.3289 | 5.0 | 1455 | 1.2266 |
| 1.2833 | 6.0 | 1746 | 1.3695 |
| 1.2319 | 7.0 | 2037 | 1.2930 |
| 1.2032 | 8.0 | 2328 | 1.3480 |
| 1.167 | 9.0 | 2619 | 1.2298 |
| 1.1407 | 10.0 | 2910 | 1.1770 |
| 1.1285 | 11.0 | 3201 | 1.1327 |
| 1.1086 | 12.0 | 3492 | 1.1888 |
| 1.0877 | 13.0 | 3783 | 1.2157 |
| 1.0755 | 14.0 | 4074 | 1.2055 |
| 1.073 | 15.0 | 4365 | 1.2192 |
| 1.064 | 16.0 | 4656 | 1.2434 |
Framework versions
- Transformers 4.57.3
- Pytorch 2.8.0
- Datasets 3.6.0
- Tokenizers 0.22.1
- Downloads last month
- 9
Model tree for KwCCCC/bert-base-uncased-issues-128
Base model
google-bert/bert-base-uncased