distilbert-base-uncased-finetuned-qqp
This model is a fine-tuned version of distilbert-base-uncased on the glue dataset. It achieves the following results on the evaluation set:
- Loss: 0.4957
- Accuracy: 0.9019
- F1: 0.8681
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| 0.2846 | 1.0 | 22741 | 0.2751 | 0.8823 | 0.8451 |
| 0.2198 | 2.0 | 45482 | 0.2744 | 0.8989 | 0.8649 |
| 0.169 | 3.0 | 68223 | 0.3182 | 0.8993 | 0.8675 |
| 0.1281 | 4.0 | 90964 | 0.4432 | 0.9017 | 0.8688 |
| 0.0874 | 5.0 | 113705 | 0.4957 | 0.9019 | 0.8681 |
Framework versions
- Transformers 4.27.4
- Pytorch 2.0.0+cu118
- Datasets 2.11.0
- Tokenizers 0.13.3