<!-- 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_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: 0.0493
- Accuracy: 0.9952
- F1: 0.9474
- Precision: 0.9989
- Recall: 0.901
- Roc Auc Score: 0.9505
- Tpr At Fpr 0.01: 0.9106
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 |
|---|---|---|---|---|---|---|---|---|---|
| 0.0068 | 1.0 | 13125 | 0.0321 | 0.9930 | 0.9209 | 0.9949 | 0.8572 | 0.9285 | 0.821 |
| 0.0041 | 2.0 | 26250 | 0.0398 | 0.9941 | 0.9341 | 0.9973 | 0.8784 | 0.9391 | 0.8602 |
| 0.0011 | 3.0 | 39375 | 0.0646 | 0.9922 | 0.9109 | 0.9990 | 0.837 | 0.9185 | 0.8694 |
| 0.0014 | 4.0 | 52500 | 0.0567 | 0.9929 | 0.9191 | 0.9998 | 0.8504 | 0.9252 | 0.895 |
| 0.0 | 5.0 | 65625 | 0.0493 | 0.9952 | 0.9474 | 0.9989 | 0.901 | 0.9505 | 0.9106 |
Framework versions
- Transformers 4.29.1
- Pytorch 1.9.0+cu111
- Datasets 2.10.1
- Tokenizers 0.13.2
