distilbert-qa

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

• Loss: 1.4652

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: 4

Training results

Training Loss	Epoch	Step	Validation Loss
1.862	1.0	625	1.5647
1.4457	2.0	1250	1.4875
1.3254	3.0	1875	1.4690
1.0994	4.0	2500	1.4652

Framework versions

• Transformers 4.39.3
• Pytorch 2.1.2
• Datasets 2.18.0
• Tokenizers 0.15.2