<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
bert-base-uncased-qqp
This model is a fine-tuned version of bert-base-uncased on the GLUE QQP dataset. It achieves the following results on the evaluation set:
- Loss: 0.2260
- Accuracy: 0.9067
- F1: 0.8714
- Combined Score: 0.8891
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: 5e-05
- train_batch_size: 128
- eval_batch_size: 128
- seed: 10
- distributed_type: multi-GPU
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 50
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Combined Score |
---|---|---|---|---|---|---|
0.2922 | 1.0 | 2843 | 0.2523 | 0.8943 | 0.8604 | 0.8773 |
0.1837 | 2.0 | 5686 | 0.2260 | 0.9067 | 0.8714 | 0.8891 |
0.1216 | 3.0 | 8529 | 0.2612 | 0.9062 | 0.8747 | 0.8904 |
0.0876 | 4.0 | 11372 | 0.2713 | 0.9084 | 0.8779 | 0.8932 |
0.0669 | 5.0 | 14215 | 0.3178 | 0.9090 | 0.8770 | 0.8930 |
0.0544 | 6.0 | 17058 | 0.3534 | 0.9077 | 0.8737 | 0.8907 |
0.0451 | 7.0 | 19901 | 0.3821 | 0.9081 | 0.8744 | 0.8913 |
0.0387 | 8.0 | 22744 | 0.4164 | 0.9101 | 0.8796 | 0.8948 |
0.0336 | 9.0 | 25587 | 0.4353 | 0.9099 | 0.8790 | 0.8944 |
Framework versions
- Transformers 4.26.0
- Pytorch 1.14.0a0+410ce96
- Datasets 2.9.0
- Tokenizers 0.13.2