roberta-base-squad2-distilled-small-cuad-1

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

• Loss: 1.0174

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: 2e-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
1.3727	1.0	1125	1.1065
1.0129	2.0	2250	1.0079
0.7974	3.0	3375	1.0174

Framework versions

• Transformers 4.30.2
• Pytorch 2.0.1+cu118
• Datasets 2.13.1
• Tokenizers 0.13.3