distilroberta-base-mrpc-glue-GraciaK

This model is a fine-tuned version of bert-base-uncased on the glue and the mrpc datasets. It achieves the following results on the evaluation set:

• Loss: 0.5641
• Accuracy: 0.8505
• F1: 0.8946

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: 8
• eval_batch_size: 8
• seed: 42
• 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
0.4802	1.09	500	0.5641	0.8505	0.8946
0.261	2.18	1000	0.6596	0.8407	0.8845

Framework versions

• Transformers 4.30.2
• Pytorch 2.0.1+cu118
• Datasets 2.13.1
• Tokenizers 0.13.3