distilroberta_optionsChoose

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

• Loss: 0.7727
• Accuracy: 0.7381

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: 16
• eval_batch_size: 16
• 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
0.9344	1.0	4597	0.7569	0.6907
0.6714	2.0	9194	0.7102	0.7233
0.4522	3.0	13791	0.7727	0.7381

Framework versions

• Transformers 4.32.0.dev0
• Pytorch 2.0.1+cu118
• Datasets 2.13.1
• Tokenizers 0.13.3