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: 0.6270
- Accuracy: 0.6838
- F1: 0.8122
- Combined Score: 0.7480
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: 0.0001
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- training_steps: 300
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Combined Score |
---|---|---|---|---|---|---|
0.6764 | 0.07 | 30 | 0.6116 | 0.6838 | 0.8122 | 0.7480 |
0.666 | 0.13 | 60 | 0.6866 | 0.6078 | 0.6787 | 0.6433 |
0.6512 | 0.2 | 90 | 0.6238 | 0.6838 | 0.8122 | 0.7480 |
0.6677 | 0.26 | 120 | 0.6379 | 0.6838 | 0.8122 | 0.7480 |
0.6328 | 0.33 | 150 | 0.6258 | 0.6838 | 0.8122 | 0.7480 |
0.6712 | 0.39 | 180 | 0.6247 | 0.6838 | 0.8122 | 0.7480 |
0.6357 | 0.46 | 210 | 0.6271 | 0.6838 | 0.8122 | 0.7480 |
0.5826 | 0.52 | 240 | 0.6275 | 0.6838 | 0.8122 | 0.7480 |
0.5921 | 0.59 | 270 | 0.6316 | 0.6838 | 0.8122 | 0.7480 |
0.6667 | 0.65 | 300 | 0.6270 | 0.6838 | 0.8122 | 0.7480 |
Framework versions
- Transformers 4.39.2
- Pytorch 2.2.2+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
- Downloads last month
- 8
Inference API (serverless) is not available, repository is disabled.
Model tree for madsci/MRPC
Base model
google-bert/bert-base-uncased
Finetuned
this model
Dataset used to train madsci/MRPC
Evaluation results
- Accuracy on GLUE MRPCself-reported0.684
- F1 on GLUE MRPCself-reported0.812