Cautiousness_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: 0.7344
- Accuracy: 0.6862
- Precision: 0.6866
- Recall: 0.6866
- F1: 0.6866
- Auc: 0.7269
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 | 0.6249 | 0.6787 | 0.7081 | 0.6095 | 0.6551 | 0.7365 |
| No log | 2.0 | 236 | 0.6079 | 0.6887 | 0.6939 | 0.6766 | 0.6851 | 0.7493 |
| No log | 3.0 | 354 | 0.6309 | 0.6862 | 0.6812 | 0.7015 | 0.6912 | 0.7491 |
| No log | 4.0 | 472 | 0.6528 | 0.6874 | 0.7068 | 0.6418 | 0.6728 | 0.7508 |
| 0.5567 | 5.0 | 590 | 0.7344 | 0.6862 | 0.6866 | 0.6866 | 0.6866 | 0.7269 |
Framework versions
- Transformers 4.44.1
- Pytorch 1.11.0
- Datasets 2.12.0
- Tokenizers 0.19.1