distilroberta-base-mrpc-glue

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

• Loss: 0.9245
• Accuracy: 0.8333
• F1: 0.8828

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: 4

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
0.3364	1.0893	500	0.9526	0.7966	0.8449
0.2097	2.1786	1000	0.9513	0.8235	0.8737
0.1005	3.2680	1500	0.9245	0.8333	0.8828

Framework versions

• Transformers 4.41.1
• Pytorch 2.3.0+cu121
• Datasets 2.19.2
• Tokenizers 0.19.1