<!-- 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_10K_fromB_BFall_30KGen_topP_0.75_noaddedB
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: 0.0595
- Accuracy: 0.9942
- F1: 0.9358
- Precision: 0.9968
- Recall: 0.8818
- Roc Auc Score: 0.9408
- Tpr At Fpr 0.01: 0.8582
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 |
|---|---|---|---|---|---|---|---|---|---|
| 0.0134 | 1.0 | 7500 | 0.0271 | 0.9934 | 0.9272 | 0.9830 | 0.8774 | 0.9383 | 0.7528 |
| 0.0056 | 2.0 | 15000 | 0.0291 | 0.9946 | 0.9406 | 0.9907 | 0.8954 | 0.9475 | 0.8226 |
| 0.0038 | 3.0 | 22500 | 0.0312 | 0.9941 | 0.9341 | 0.9937 | 0.8812 | 0.9405 | 0.8302 |
| 0.0016 | 4.0 | 30000 | 0.0390 | 0.9951 | 0.9463 | 0.9945 | 0.9026 | 0.9512 | 0.852 |
| 0.0 | 5.0 | 37500 | 0.0595 | 0.9942 | 0.9358 | 0.9968 | 0.8818 | 0.9408 | 0.8582 |
Framework versions
- Transformers 4.29.1
- Pytorch 1.9.0+cu111
- Datasets 2.10.1
- Tokenizers 0.13.2
