roberta-base-finetuned-mnli
This model is a fine-tuned version of roberta-base on the glue dataset. It achieves the following results on the evaluation set:
- Matched Accuracy: 0.8780
- Missmatched Accuracy: 0.8778
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- weight_decay: 0.01
- num_epochs: 3
- Downloads last month
- 2
Dataset used to train rambodazimi/roberta-base-finetuned-FFT-MNLI
Evaluation results
- Matched Accuracy on glueself-reported0.878
- Missmatched Accuracy on glueself-reported0.878