<!-- 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-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: 0.3693
- Accuracy: 0.8407
- F1: 0.8825
- Combined Score: 0.8616
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 |
---|---|---|---|---|---|---|
0.5716 | 1.0 | 29 | 0.5020 | 0.7475 | 0.8437 | 0.7956 |
0.3969 | 2.0 | 58 | 0.3693 | 0.8407 | 0.8825 | 0.8616 |
0.2182 | 3.0 | 87 | 0.5412 | 0.8235 | 0.88 | 0.8518 |
0.1135 | 4.0 | 116 | 0.5104 | 0.8260 | 0.8748 | 0.8504 |
0.0772 | 5.0 | 145 | 0.6428 | 0.8186 | 0.8655 | 0.8420 |
0.049 | 6.0 | 174 | 0.6366 | 0.8260 | 0.8725 | 0.8493 |
0.0356 | 7.0 | 203 | 0.8414 | 0.8358 | 0.8896 | 0.8627 |
0.0335 | 8.0 | 232 | 0.8573 | 0.8137 | 0.8676 | 0.8407 |
0.0234 | 9.0 | 261 | 0.8893 | 0.8309 | 0.8856 | 0.8582 |
Framework versions
- Transformers 4.26.0
- Pytorch 1.14.0a0+410ce96
- Datasets 2.9.0
- Tokenizers 0.13.2