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