<!-- 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. -->
Benign10MGPT2_fromB_BFall_30KGen_toP_0.75
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: 0.1066
- Accuracy: 0.9827
- F1: 0.7997
- Precision: 0.8920
- Recall: 0.7248
- Roc Auc Score: 0.8602
- Tpr At Fpr 0.01: 0.0
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: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5.0
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall | Roc Auc Score | Tpr At Fpr 0.01 |
|---|---|---|---|---|---|---|---|---|---|
| 0.0859 | 1.0 | 26250 | 0.0749 | 0.9823 | 0.7832 | 0.9388 | 0.6718 | 0.8348 | 0.5556 |
| 0.074 | 2.0 | 52500 | 0.0810 | 0.9803 | 0.7718 | 0.8628 | 0.6982 | 0.8463 | 0.5496 |
| 0.0534 | 3.0 | 78750 | 0.0735 | 0.9846 | 0.8211 | 0.9211 | 0.7406 | 0.8687 | 0.5882 |
| 0.0374 | 4.0 | 105000 | 0.0877 | 0.9830 | 0.8023 | 0.8976 | 0.7254 | 0.8606 | 0.0 |
| 0.0267 | 5.0 | 131250 | 0.1066 | 0.9827 | 0.7997 | 0.8920 | 0.7248 | 0.8602 | 0.0 |
Framework versions
- Transformers 4.29.1
- Pytorch 1.9.0+cu111
- Datasets 2.10.1
- Tokenizers 0.13.2
