<!-- 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_40KGen_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: 0.0185
- Accuracy: 0.9973
- F1: 0.9712
- Precision: 0.9996
- Recall: 0.9444
- Roc Auc Score: 0.9722
- Tpr At Fpr 0.01: 0.9588
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 |
|---|---|---|---|---|---|---|---|---|---|
| 0.0052 | 1.0 | 91875 | 0.0700 | 0.9904 | 0.8876 | 0.9995 | 0.7982 | 0.8991 | 0.7842 |
| 0.0055 | 2.0 | 183750 | 0.0208 | 0.9968 | 0.9652 | 0.9985 | 0.934 | 0.9670 | 0.9362 |
| 0.0029 | 3.0 | 275625 | 0.0209 | 0.9970 | 0.9674 | 0.9991 | 0.9376 | 0.9688 | 0.9544 |
| 0.0006 | 4.0 | 367500 | 0.0290 | 0.9962 | 0.9579 | 0.9996 | 0.9196 | 0.9598 | 0.9528 |
| 0.001 | 5.0 | 459375 | 0.0185 | 0.9973 | 0.9712 | 0.9996 | 0.9444 | 0.9722 | 0.9588 |
Framework versions
- Transformers 4.29.1
- Pytorch 1.9.0+cu111
- Datasets 2.10.1
- Tokenizers 0.13.2
