roberta-base-mrpc-glue

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

• Loss: 0.3949
• Accuracy: 0.8529
• F1: 0.8966

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: 1e-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
0.5289	1.0893	500	0.3949	0.8529	0.8966
0.3665	2.1786	1000	0.4265	0.8505	0.8856

Framework versions

• Transformers 4.43.3
• Pytorch 2.3.1
• Datasets 2.20.0
• Tokenizers 0.19.1