<!-- 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. -->
MixGPT2_100KP_BFall_fromB_10KGen_topP_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: 0.0191
- Accuracy: 0.9977
- F1: 0.9755
- Precision: 0.9990
- Recall: 0.9532
- Roc Auc Score: 0.9766
- Tpr At Fpr 0.01: 0.9616
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 |
|---|---|---|---|---|---|---|---|---|---|
| 0.0017 | 1.0 | 72188 | 0.0194 | 0.9972 | 0.9700 | 0.9960 | 0.9454 | 0.9726 | 0.9264 |
| 0.0017 | 2.0 | 144376 | 0.0220 | 0.9971 | 0.9688 | 0.9991 | 0.9402 | 0.9701 | 0.9466 |
| 0.0022 | 3.0 | 216564 | 0.0258 | 0.9963 | 0.9597 | 0.9994 | 0.923 | 0.9615 | 0.9518 |
| 0.0023 | 4.0 | 288752 | 0.0154 | 0.9973 | 0.9713 | 0.9987 | 0.9454 | 0.9727 | 0.9614 |
| 0.0009 | 5.0 | 360940 | 0.0191 | 0.9977 | 0.9755 | 0.9990 | 0.9532 | 0.9766 | 0.9616 |
Framework versions
- Transformers 4.29.1
- Pytorch 1.9.0+cu111
- Datasets 2.10.1
- Tokenizers 0.13.2
