distilroberta-base-mrpc-glue-alejandro-arroyo

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: 0.4766
• Accuracy: 0.8456
• F1: 0.8877

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
0.5133	1.09	500	0.4766	0.8456	0.8877
0.3289	2.18	1000	0.6813	0.8529	0.8913
0.1676	3.27	1500	0.8878	0.8456	0.8923

Framework versions

• Transformers 4.33.2
• Pytorch 2.0.1+cu118
• Datasets 2.14.5
• Tokenizers 0.13.3