<!-- 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. -->
bert-base-uncased-guilt-detection
This model is a fine-tuned version of bert-base-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.6646
- Accuracy: 0.7831
- F1: 0.7830
- Precision: 0.7836
- Recall: 0.7831
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: 5e-05
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 10
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
---|---|---|---|---|---|---|---|
0.45 | 1.0 | 2042 | 0.4409 | 0.7979 | 0.7979 | 0.7979 | 0.7979 |
0.3824 | 2.0 | 4084 | 0.4561 | 0.7990 | 0.7989 | 0.7993 | 0.7990 |
0.2573 | 3.0 | 6126 | 0.5581 | 0.7900 | 0.7895 | 0.7930 | 0.7900 |
0.1548 | 4.0 | 8168 | 0.6646 | 0.7831 | 0.7830 | 0.7836 | 0.7831 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1+cu116
- Datasets 2.10.1
- Tokenizers 0.13.2