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: 1.7582
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: 7
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.4041 | 1.0 | 8 | 1.8568 |
| 2.1982 | 2.0 | 16 | 2.0790 |
| 1.7184 | 3.0 | 24 | 1.9246 |
| 1.7248 | 4.0 | 32 | 1.8485 |
| 1.5016 | 5.0 | 40 | 1.8484 |
| 1.4943 | 6.0 | 48 | 1.8691 |
| 1.526 | 7.0 | 56 | 1.7582 |
Framework versions
- Transformers 4.21.2
- Pytorch 1.12.1+cu113
- Datasets 2.4.0
- Tokenizers 0.12.1