roberta-base-finetuned-mrpc
This model is a fine-tuned version of roberta-base on the glue dataset. It achieves the following results on the evaluation set:
- Loss: 0.3055
- Accuracy: 0.8799
- F1: 0.9104
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: 32
- eval_batch_size: 32
- seed: 60
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
---|---|---|---|---|---|
No log | 1.0 | 115 | 0.3613 | 0.8529 | 0.8889 |
No log | 2.0 | 230 | 0.2917 | 0.8848 | 0.9147 |
No log | 3.0 | 345 | 0.3055 | 0.8799 | 0.9104 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3
- Downloads last month
- 14
Dataset used to train VitaliiVrublevskyi/roberta-base-finetuned-mrpc
Evaluation results
- Accuracy on gluevalidation set self-reported0.880
- F1 on gluevalidation set self-reported0.910