Agree_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: 0.7163
- Accuracy: 0.7584
- Precision: 0.7161
- Recall: 0.8554
- F1: 0.7795
- Auc: 0.8416
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 | 0.5045 | 0.7572 | 0.7077 | 0.8753 | 0.7826 | 0.8287 |
| No log | 2.0 | 236 | 0.5149 | 0.7435 | 0.6750 | 0.9377 | 0.7850 | 0.8398 |
| No log | 3.0 | 354 | 0.5549 | 0.7634 | 0.7017 | 0.9152 | 0.7944 | 0.8423 |
| No log | 4.0 | 472 | 0.6183 | 0.7733 | 0.7345 | 0.8554 | 0.7903 | 0.8422 |
| 0.4071 | 5.0 | 590 | 0.7163 | 0.7584 | 0.7161 | 0.8554 | 0.7795 | 0.8416 |
Framework versions
- Transformers 4.44.1
- Pytorch 1.11.0
- Datasets 2.12.0
- Tokenizers 0.19.1