<!-- 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
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: 1.0745
- Accuracy: 0.7628
- Precision: 0.5795
- Recall: 0.5194
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: 10
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall |
---|---|---|---|---|---|---|
2.591 | 1.0 | 234 | 2.2068 | 0.4444 | 0.0523 | 0.0477 |
1.9869 | 2.0 | 468 | 1.7959 | 0.5876 | 0.2023 | 0.1887 |
1.5443 | 3.0 | 702 | 1.5389 | 0.6378 | 0.2921 | 0.2857 |
1.2084 | 4.0 | 936 | 1.3623 | 0.6848 | 0.3983 | 0.3562 |
0.9397 | 5.0 | 1170 | 1.2348 | 0.7244 | 0.4999 | 0.4112 |
0.7445 | 6.0 | 1404 | 1.1657 | 0.7286 | 0.5053 | 0.4481 |
0.6204 | 7.0 | 1638 | 1.1167 | 0.7564 | 0.5773 | 0.4918 |
0.5183 | 8.0 | 1872 | 1.0872 | 0.7607 | 0.5841 | 0.5078 |
0.4468 | 9.0 | 2106 | 1.0782 | 0.7628 | 0.5785 | 0.5172 |
0.4188 | 10.0 | 2340 | 1.0745 | 0.7628 | 0.5795 | 0.5194 |
Framework versions
- Transformers 4.27.4
- Pytorch 2.0.0+cu118
- Datasets 2.11.0
- Tokenizers 0.13.2