<!-- 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_30KGen_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: 0.0617
- Accuracy: 0.9926
- F1: 0.9162
- Precision: 0.9998
- Recall: 0.8456
- Roc Auc Score: 0.9228
- Tpr At Fpr 0.01: 0.8956
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 |
|---|---|---|---|---|---|---|---|---|---|
| 0.005 | 1.0 | 26250 | 0.0392 | 0.9921 | 0.9101 | 0.9983 | 0.8362 | 0.9181 | 0.838 |
| 0.0015 | 2.0 | 52500 | 0.0749 | 0.9909 | 0.8940 | 0.9978 | 0.8098 | 0.9049 | 0.8144 |
| 0.0007 | 3.0 | 78750 | 0.0421 | 0.9952 | 0.9471 | 0.9989 | 0.9004 | 0.9502 | 0.9072 |
| 0.0013 | 4.0 | 105000 | 0.0393 | 0.9941 | 0.9344 | 0.9998 | 0.877 | 0.9385 | 0.9138 |
| 0.0003 | 5.0 | 131250 | 0.0617 | 0.9926 | 0.9162 | 0.9998 | 0.8456 | 0.9228 | 0.8956 |
Framework versions
- Transformers 4.29.1
- Pytorch 1.9.0+cu111
- Datasets 2.10.1
- Tokenizers 0.13.2
