<!-- 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-new
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: 0.1017
- Accuracy: 0.9902
- Precision: 0.9910
- 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 |
---|---|---|---|---|---|---|
0.4743 | 1.0 | 618 | 0.1856 | 0.9633 | 0.9672 | 0.9647 |
0.0946 | 2.0 | 1236 | 0.1577 | 0.9707 | 0.9749 | 0.9733 |
0.0851 | 3.0 | 1854 | 0.1081 | 0.9853 | 0.9869 | 0.9858 |
0.0633 | 4.0 | 2472 | 0.1449 | 0.9841 | 0.9851 | 0.9837 |
0.0258 | 5.0 | 3090 | 0.1155 | 0.9829 | 0.9838 | 0.9829 |
0.022 | 6.0 | 3708 | 0.1089 | 0.9890 | 0.9899 | 0.9897 |
0.0147 | 7.0 | 4326 | 0.1092 | 0.9878 | 0.9885 | 0.9875 |
0.0043 | 8.0 | 4944 | 0.1017 | 0.9902 | 0.9910 | 0.9909 |
0.0041 | 9.0 | 5562 | 0.1033 | 0.9878 | 0.9885 | 0.9874 |
0.0012 | 10.0 | 6180 | 0.1093 | 0.9878 | 0.9885 | 0.9874 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3