<!-- 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_20KGen_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: 0.0667
- Accuracy: 0.9940
- F1: 0.9325
- Precision: 0.9993
- Recall: 0.874
- Roc Auc Score: 0.9370
- Tpr At Fpr 0.01: 0.8984
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 |
|---|---|---|---|---|---|---|---|---|---|
| 0.0038 | 1.0 | 19688 | 0.0511 | 0.9926 | 0.9158 | 0.9991 | 0.8454 | 0.9227 | 0.8744 |
| 0.0028 | 2.0 | 39376 | 0.0423 | 0.9946 | 0.9405 | 0.9951 | 0.8916 | 0.9457 | 0.884 |
| 0.0006 | 3.0 | 59064 | 0.0510 | 0.9940 | 0.9325 | 0.9975 | 0.8754 | 0.9376 | 0.875 |
| 0.0 | 4.0 | 78752 | 0.0355 | 0.9958 | 0.9536 | 0.9987 | 0.9124 | 0.9562 | 0.9172 |
| 0.0 | 5.0 | 98440 | 0.0667 | 0.9940 | 0.9325 | 0.9993 | 0.874 | 0.9370 | 0.8984 |
Framework versions
- Transformers 4.29.1
- Pytorch 1.9.0+cu111
- Datasets 2.10.1
- Tokenizers 0.13.2
