Anxiety_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: 0.7937
- Accuracy: 0.6837
- Precision: 0.6473
- Recall: 0.8055
- F1: 0.7178
- Auc: 0.7751
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 | 118 | 0.5902 | 0.6899 | 0.7275 | 0.6060 | 0.6612 | 0.7615 |
| No log | 2.0 | 236 | 0.5518 | 0.7123 | 0.7471 | 0.6409 | 0.6899 | 0.7906 |
| No log | 3.0 | 354 | 0.5580 | 0.7210 | 0.8149 | 0.5711 | 0.6716 | 0.8060 |
| No log | 4.0 | 472 | 0.6352 | 0.6999 | 0.6569 | 0.8354 | 0.7355 | 0.7923 |
| 0.5423 | 5.0 | 590 | 0.7219 | 0.6999 | 0.6860 | 0.7357 | 0.7100 | 0.7836 |
| 0.5423 | 6.0 | 708 | 0.7937 | 0.6837 | 0.6473 | 0.8055 | 0.7178 | 0.7751 |
Framework versions
- Transformers 4.44.1
- Pytorch 1.11.0
- Datasets 2.12.0
- Tokenizers 0.19.1