<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
distilbert-base-uncased-issues-128
This model is a fine-tuned version of distilbert-base-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.2728
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: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 16
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.2526 | 1.0 | 292 | 1.8647 |
| 1.7421 | 2.0 | 584 | 1.6379 |
| 1.5862 | 3.0 | 876 | 1.5838 |
| 1.5041 | 4.0 | 1168 | 1.5427 |
| 1.4371 | 5.0 | 1460 | 1.4806 |
| 1.3826 | 6.0 | 1752 | 1.3648 |
| 1.3487 | 7.0 | 2044 | 1.4458 |
| 1.3292 | 8.0 | 2336 | 1.3345 |
| 1.2779 | 9.0 | 2628 | 1.3367 |
| 1.2599 | 10.0 | 2920 | 1.3373 |
| 1.2454 | 11.0 | 3212 | 1.3694 |
| 1.2239 | 12.0 | 3504 | 1.2550 |
| 1.2057 | 13.0 | 3796 | 1.3154 |
| 1.1792 | 14.0 | 4088 | 1.2952 |
| 1.1838 | 15.0 | 4380 | 1.3406 |
| 1.1739 | 16.0 | 4672 | 1.2728 |
Framework versions
- Transformers 4.34.0
- Pytorch 2.0.1+cu117
- Datasets 2.14.5
- Tokenizers 0.14.1
