finetuned-bert-mrpc
This model is a fine-tuned version of bert-base-cased on the glue dataset. It achieves the following results on the evaluation set:
- Loss: 0.4755
- Accuracy: 0.8456
- F1: 0.8908
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Trained on my local laptop and the training time took 3 hours.
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: 3.0
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| 0.5331 | 1.0 | 230 | 0.3837 | 0.8505 | 0.8943 |
| 0.3023 | 2.0 | 460 | 0.3934 | 0.8505 | 0.8954 |
| 0.1472 | 3.0 | 690 | 0.4755 | 0.8456 | 0.8908 |
Framework versions
- Transformers 4.20.0
- Pytorch 1.11.0+cu113
- Datasets 2.3.2
- Tokenizers 0.12.1
- Downloads last month
- 10
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.
Dataset used to train wiselinjayajos/finetuned-bert-mrpc
Evaluation results
- Accuracy on glueself-reported0.846
- F1 on glueself-reported0.891