<!-- 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-finetuned
This model is a fine-tuned version of distilbert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.5117
- Accuracy: 0.875
- F1: 0.8780
- Precision: 0.8824
- Recall: 0.8738
- Auroc: 0.8750
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-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: 8
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall | Auroc |
---|---|---|---|---|---|---|---|---|
0.6839 | 1.0 | 50 | 0.6843 | 0.665 | 0.6215 | 0.7432 | 0.5340 | 0.6691 |
0.6781 | 2.0 | 100 | 0.6717 | 0.765 | 0.7638 | 0.7917 | 0.7379 | 0.7658 |
0.6552 | 3.0 | 150 | 0.6478 | 0.76 | 0.7857 | 0.7273 | 0.8544 | 0.7571 |
0.6218 | 4.0 | 200 | 0.6124 | 0.785 | 0.8018 | 0.7632 | 0.8447 | 0.7832 |
0.5822 | 5.0 | 250 | 0.5752 | 0.82 | 0.8252 | 0.8252 | 0.8252 | 0.8198 |
0.5357 | 6.0 | 300 | 0.5405 | 0.855 | 0.8599 | 0.8558 | 0.8641 | 0.8547 |
0.5368 | 7.0 | 350 | 0.5192 | 0.875 | 0.8768 | 0.89 | 0.8641 | 0.8753 |
0.5449 | 8.0 | 400 | 0.5117 | 0.875 | 0.8780 | 0.8824 | 0.8738 | 0.8750 |
Framework versions
- Transformers 4.34.1
- Pytorch 2.1.0+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1