deberta-v3-large-finetuned-synthetic-paraphrase-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: 0.0120
- F1: 0.9768
- Precision: 0.9961
- Recall: 0.9583
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 |
|---|---|---|---|---|---|---|
| 0.0086 | 1.0 | 10205 | 0.0114 | 0.9642 | 0.9846 | 0.9446 |
| 0.0059 | 2.0 | 20410 | 0.0143 | 0.9658 | 0.9961 | 0.9373 |
| 0.0 | 3.0 | 30615 | 0.0141 | 0.9716 | 0.9961 | 0.9483 |
Framework versions
- Transformers 4.20.1
- Pytorch 1.11.0
- Datasets 2.1.0
- Tokenizers 0.12.1