<!-- 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_30KGen_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: 0.0196
- Accuracy: 0.9968
- F1: 0.9656
- Precision: 0.9994
- Recall: 0.934
- Roc Auc Score: 0.9670
- Tpr At Fpr 0.01: 0.9596
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 |
|---|---|---|---|---|---|---|---|---|---|
| 0.0021 | 1.0 | 85313 | 0.0313 | 0.9952 | 0.9469 | 0.9984 | 0.9004 | 0.9502 | 0.9028 |
| 0.0031 | 2.0 | 170626 | 0.0236 | 0.9970 | 0.9671 | 0.9987 | 0.9374 | 0.9687 | 0.9466 |
| 0.0039 | 3.0 | 255939 | 0.0182 | 0.9971 | 0.9688 | 0.9981 | 0.9412 | 0.9706 | 0.9394 |
| 0.002 | 4.0 | 341252 | 0.0199 | 0.9973 | 0.9709 | 0.9987 | 0.9446 | 0.9723 | 0.9508 |
| 0.001 | 5.0 | 426565 | 0.0196 | 0.9968 | 0.9656 | 0.9994 | 0.934 | 0.9670 | 0.9596 |
Framework versions
- Transformers 4.29.1
- Pytorch 1.9.0+cu111
- Datasets 2.10.1
- Tokenizers 0.13.2
