<!-- 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-PINA-dfnew-tuning
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: 0.3403
- Accuracy: 0.9438
- Precision: 0.8528
- Recall: 0.8454
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 |
---|---|---|---|---|---|---|
0.8484 | 1.0 | 1436 | 0.4963 | 0.8896 | 0.7918 | 0.7575 |
0.3783 | 2.0 | 2872 | 0.4298 | 0.9114 | 0.8288 | 0.7918 |
0.2649 | 3.0 | 4308 | 0.3808 | 0.9302 | 0.8484 | 0.8148 |
0.1951 | 4.0 | 5744 | 0.3627 | 0.9363 | 0.8631 | 0.8205 |
0.149 | 5.0 | 7180 | 0.3403 | 0.9438 | 0.8528 | 0.8454 |
0.1061 | 6.0 | 8616 | 0.3415 | 0.9455 | 0.8571 | 0.8366 |
0.0745 | 7.0 | 10052 | 0.3441 | 0.9467 | 0.8554 | 0.8418 |
0.0452 | 8.0 | 11488 | 0.3850 | 0.9500 | 0.8697 | 0.8711 |
0.0273 | 9.0 | 12924 | 0.3941 | 0.9506 | 0.8546 | 0.8469 |
0.0166 | 10.0 | 14360 | 0.4046 | 0.9525 | 0.8621 | 0.8492 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.0.1+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3