distilbert_multiple_choice
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: 1.3817
- Accuracy: 0.55
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-06
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 100
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.4774 | 1.0 | 3207 | 1.3041 | 0.46 |
| 1.3316 | 2.0 | 6414 | 1.2338 | 0.5 |
| 1.2152 | 3.0 | 9621 | 1.1776 | 0.54 |
| 1.0913 | 4.0 | 12828 | 1.1776 | 0.555 |
| 0.9688 | 5.0 | 16035 | 1.1628 | 0.535 |
| 0.8511 | 6.0 | 19242 | 1.1800 | 0.545 |
| 0.7474 | 7.0 | 22449 | 1.2173 | 0.52 |
| 0.6581 | 8.0 | 25656 | 1.2490 | 0.555 |
| 0.577 | 9.0 | 28863 | 1.3253 | 0.555 |
| 0.5052 | 10.0 | 32070 | 1.3817 | 0.55 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu117
- Datasets 2.14.4
- Tokenizers 0.13.3