psychopathy_binary
This model is a fine-tuned version of microsoft/deberta-v3-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.9904
- Accuracy: 0.6508
- Precision: 0.7300
- Recall: 0.48
- F1: 0.5792
- Auc: 0.7188
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: 1234
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.06
- num_epochs: 8
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 | Auc |
|---|---|---|---|---|---|---|---|---|
| No log | 1.0 | 117 | 0.6148 | 0.6433 | 0.7018 | 0.5 | 0.5839 | 0.7171 |
| No log | 2.0 | 234 | 0.6155 | 0.6458 | 0.7448 | 0.445 | 0.5571 | 0.7453 |
| No log | 3.0 | 351 | 0.6970 | 0.6583 | 0.6440 | 0.71 | 0.6754 | 0.7302 |
| No log | 4.0 | 468 | 0.8320 | 0.6571 | 0.7351 | 0.4925 | 0.5898 | 0.7264 |
| 0.4919 | 5.0 | 585 | 0.9904 | 0.6508 | 0.7300 | 0.48 | 0.5792 | 0.7188 |
Framework versions
- Transformers 4.44.1
- Pytorch 1.11.0
- Datasets 2.12.0
- Tokenizers 0.19.1