distilroberta-base-mrpc-glu-cristian-agudelo

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

• Loss: 0.9131
• Accuracy: 0.8211
• F1: 0.8713

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
0.285	1.09	500	0.8959	0.8407	0.8845
0.2653	2.18	1000	0.9131	0.8211	0.8713

Framework versions

• Transformers 4.26.0
• Pytorch 1.13.1+cu116
• Datasets 2.8.0
• Tokenizers 0.13.2