<!-- 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_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: 0.0189
- Accuracy: 0.9972
- F1: 0.9700
- Precision: 0.9994
- Recall: 0.9424
- Roc Auc Score: 0.9712
- Tpr At Fpr 0.01: 0.9544
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 |
|---|---|---|---|---|---|---|---|---|---|
| 0.0051 | 1.0 | 78750 | 0.0225 | 0.9964 | 0.9605 | 0.9961 | 0.9274 | 0.9636 | 0.9226 |
| 0.0044 | 2.0 | 157500 | 0.0219 | 0.9963 | 0.9593 | 0.9985 | 0.923 | 0.9615 | 0.933 |
| 0.0018 | 3.0 | 236250 | 0.0216 | 0.9969 | 0.9669 | 0.9991 | 0.9366 | 0.9683 | 0.9496 |
| 0.0012 | 4.0 | 315000 | 0.0233 | 0.9967 | 0.9646 | 0.9994 | 0.9322 | 0.9661 | 0.9448 |
| 0.0011 | 5.0 | 393750 | 0.0189 | 0.9972 | 0.9700 | 0.9994 | 0.9424 | 0.9712 | 0.9544 |
Framework versions
- Transformers 4.29.1
- Pytorch 1.9.0+cu111
- Datasets 2.10.1
- Tokenizers 0.13.2
