<!-- 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-DSC
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: 0.0576
- Accuracy: 0.9902
- Precision: 0.9902
- Recall: 0.9909
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: 0.0002
- 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: 10
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall |
---|---|---|---|---|---|---|
0.6361 | 1.0 | 295 | 0.1303 | 0.9670 | 0.9702 | 0.9688 |
0.0886 | 2.0 | 590 | 0.0923 | 0.9792 | 0.9788 | 0.9790 |
0.0522 | 3.0 | 885 | 0.0830 | 0.9817 | 0.9828 | 0.9830 |
0.0312 | 4.0 | 1180 | 0.0948 | 0.9817 | 0.9822 | 0.9826 |
0.0272 | 5.0 | 1475 | 0.0860 | 0.9817 | 0.9826 | 0.9829 |
0.0204 | 6.0 | 1770 | 0.0590 | 0.9841 | 0.9849 | 0.9854 |
0.0069 | 7.0 | 2065 | 0.0669 | 0.9878 | 0.9879 | 0.9885 |
0.0095 | 8.0 | 2360 | 0.0576 | 0.9902 | 0.9902 | 0.9909 |
0.0039 | 9.0 | 2655 | 0.0693 | 0.9902 | 0.9900 | 0.9909 |
0.0043 | 10.0 | 2950 | 0.0681 | 0.9902 | 0.9900 | 0.9909 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.3
- Tokenizers 0.13.3