<!-- 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_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: 0.0480
- Accuracy: 0.9944
- F1: 0.9378
- Precision: 0.9998
- Recall: 0.883
- Roc Auc Score: 0.9415
- Tpr At Fpr 0.01: 0.91
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 |
|---|---|---|---|---|---|---|---|---|---|
| 0.0059 | 1.0 | 32813 | 0.0405 | 0.9934 | 0.9250 | 0.9991 | 0.8612 | 0.9306 | 0.8928 |
| 0.0036 | 2.0 | 65626 | 0.0503 | 0.9929 | 0.9193 | 0.9998 | 0.8508 | 0.9254 | 0.8914 |
| 0.001 | 3.0 | 98439 | 0.0706 | 0.9908 | 0.8936 | 0.9995 | 0.808 | 0.9040 | 0.8702 |
| 0.0011 | 4.0 | 131252 | 0.0564 | 0.9943 | 0.9363 | 0.9986 | 0.8812 | 0.9406 | 0.8958 |
| 0.0 | 5.0 | 164065 | 0.0480 | 0.9944 | 0.9378 | 0.9998 | 0.883 | 0.9415 | 0.91 |
Framework versions
- Transformers 4.29.1
- Pytorch 1.9.0+cu111
- Datasets 2.10.1
- Tokenizers 0.13.2
