<!-- 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_20KGen_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: 0.1022
- Accuracy: 0.9840
- F1: 0.8164
- Precision: 0.8982
- Recall: 0.7482
- Roc Auc Score: 0.8720
- 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 |
|---|---|---|---|---|---|---|---|---|---|
| 0.0758 | 1.0 | 19688 | 0.0958 | 0.9786 | 0.7257 | 0.9311 | 0.5946 | 0.7962 | 0.5118 |
| 0.0634 | 2.0 | 39376 | 0.0682 | 0.9823 | 0.7843 | 0.9367 | 0.6746 | 0.8362 | 0.4936 |
| 0.0515 | 3.0 | 59064 | 0.0760 | 0.9823 | 0.7955 | 0.8855 | 0.7222 | 0.8588 | 0.6002 |
| 0.0372 | 4.0 | 78752 | 0.0951 | 0.9831 | 0.8034 | 0.8979 | 0.7268 | 0.8613 | 0.0 |
| 0.0339 | 5.0 | 98440 | 0.1022 | 0.9840 | 0.8164 | 0.8982 | 0.7482 | 0.8720 | 0.0 |
Framework versions
- Transformers 4.29.1
- Pytorch 1.9.0+cu111
- Datasets 2.10.1
- Tokenizers 0.13.2
