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: 1.3698
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 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 |
|---|---|---|---|
| 2.0909 | 1.0 | 295 | 1.6480 |
| 1.6279 | 2.0 | 590 | 1.6236 |
| 1.4722 | 3.0 | 885 | 1.5969 |
| 1.4032 | 4.0 | 1180 | 1.4823 |
| 1.3255 | 5.0 | 1475 | 1.3741 |
| 1.263 | 6.0 | 1770 | 1.2698 |
| 1.2314 | 7.0 | 2065 | 1.3721 |
| 1.2053 | 8.0 | 2360 | 1.3309 |
| 1.165 | 9.0 | 2655 | 1.3520 |
| 1.1399 | 10.0 | 2950 | 1.3054 |
| 1.121 | 11.0 | 3245 | 1.3506 |
| 1.1044 | 12.0 | 3540 | 1.2868 |
| 1.0783 | 13.0 | 3835 | 1.2446 |
| 1.0734 | 14.0 | 4130 | 1.2747 |
| 1.0549 | 15.0 | 4425 | 1.2977 |
| 1.041 | 16.0 | 4720 | 1.3698 |
Framework versions
- Transformers 4.57.1
- Pytorch 2.6.0+cu124
- Datasets 4.1.1
- Tokenizers 0.22.1
- Downloads last month
- 4
Model tree for swamimanish/bert-base-uncased-issues-128
Base model
google-bert/bert-base-uncased