distilbert-base-uncased-finetuned-mathQA
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: 0.0752
- Accuracy: 0.9857
- F1: 0.9857
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: 2e-05
- 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: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| 0.3155 | 1.0 | 1865 | 0.0997 | 0.9727 | 0.9727 |
| 0.0726 | 2.0 | 3730 | 0.0813 | 0.9826 | 0.9825 |
| 0.0292 | 3.0 | 5595 | 0.0752 | 0.9857 | 0.9857 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1+cu116
- Datasets 2.10.1
- Tokenizers 0.13.2