FairnessReciprocity_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: 1.2473
- Accuracy: 0.5642
- Precision: 0.5517
- Recall: 0.6845
- F1: 0.6110
- Auc: 0.5834
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 | 110 | 0.6826 | 0.5735 | 0.6078 | 0.4144 | 0.4928 | 0.5987 |
| No log | 2.0 | 220 | 0.6867 | 0.5775 | 0.5690 | 0.6390 | 0.6020 | 0.6111 |
| No log | 3.0 | 330 | 0.6893 | 0.6003 | 0.6081 | 0.5642 | 0.5853 | 0.6258 |
| No log | 4.0 | 440 | 0.8264 | 0.5481 | 0.5328 | 0.7807 | 0.6334 | 0.6041 |
| 0.5891 | 5.0 | 550 | 1.1041 | 0.5428 | 0.5287 | 0.7888 | 0.6330 | 0.5841 |
| 0.5891 | 6.0 | 660 | 1.2473 | 0.5642 | 0.5517 | 0.6845 | 0.6110 | 0.5834 |
Framework versions
- Transformers 4.44.1
- Pytorch 1.11.0
- Datasets 2.12.0
- Tokenizers 0.19.1