bert-base-uncased-finetuned-mrpc
This model is a fine-tuned version of bert-base-uncased on the GLUE MRPC dataset. It achieves the following results on the evaluation set:
- Loss: 0.4198
- Accuracy: 0.8480
- F1: 0.8924
- Combined Score: 0.8702
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: 8
- 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 | Accuracy | Combined Score | F1 | Validation Loss |
|---|---|---|---|---|---|---|
| 0.5401 | 1.0 | 230 | 0.8358 | 0.8584 | 0.8810 | 0.3958 |
| 0.3312 | 2.0 | 460 | 0.8431 | 0.8662 | 0.8893 | 0.3634 |
| 0.1913 | 3.0 | 690 | 0.8529 | 0.8744 | 0.8958 | 0.4322 |
Framework versions
- Transformers 4.45.0.dev0
- Pytorch 2.4.1+cu121
- Datasets 3.0.0
- Tokenizers 0.19.1
- Downloads last month
- 93
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.
Model tree for w05230505/bert-base-uncased-finetuned-mrpc
Base model
google-bert/bert-base-uncasedDataset used to train w05230505/bert-base-uncased-finetuned-mrpc
Evaluation results
- Accuracy on GLUE MRPCself-reported0.848
- F1 on GLUE MRPCself-reported0.892