Consc_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: 0.5621
- Accuracy: 0.7559
- Precision: 0.7204
- Recall: 0.8354
- F1: 0.7737
- Auc: 0.8421
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 | 0.5627 | 0.6949 | 0.8095 | 0.5087 | 0.6248 | 0.8117 |
| No log | 2.0 | 236 | 0.6050 | 0.6936 | 0.6307 | 0.9327 | 0.7525 | 0.8089 |
| No log | 3.0 | 354 | 0.5123 | 0.7509 | 0.7014 | 0.8728 | 0.7778 | 0.8400 |
| No log | 4.0 | 472 | 0.5966 | 0.7148 | 0.6525 | 0.9177 | 0.7627 | 0.8393 |
| 0.5227 | 5.0 | 590 | 0.5621 | 0.7559 | 0.7204 | 0.8354 | 0.7737 | 0.8421 |
Framework versions
- Transformers 4.44.1
- Pytorch 1.11.0
- Datasets 2.12.0
- Tokenizers 0.19.1