deberta-v3-large-finetuned-synthetic-generated-only
This model is a fine-tuned version of microsoft/deberta-v3-large on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0094
- F1: 0.9839
- Precision: 0.9849
- Recall: 0.9828
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: 6e-06
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 50
- num_epochs: 3
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 | Precision | Recall |
|---|---|---|---|---|---|---|
| 0.009 | 1.0 | 10387 | 0.0104 | 0.9722 | 0.9919 | 0.9533 |
| 0.0013 | 2.0 | 20774 | 0.0067 | 0.9825 | 0.9844 | 0.9805 |
| 0.0006 | 3.0 | 31161 | 0.0077 | 0.9843 | 0.9902 | 0.9786 |
Framework versions
- Transformers 4.18.0
- Pytorch 1.11.0
- Datasets 2.1.0
- Tokenizers 0.12.1