distilbert-base-uncased-finetuned-squac

This model is a fine-tuned version of distilbert-base-uncased on an Extractive QuestionAnswering dataset(SQuAC). It achieves the following results on the evaluation set:

• Loss: 2.0973

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: 32
• eval_batch_size: 32
• 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
3.0135	1.0	842	2.2648
2.1735	2.0	1684	2.1575
1.9441	3.0	2526	2.0973

Framework versions

• Transformers 4.31.0
• Pytorch 2.0.1+cu117
• Datasets 2.14.4
• Tokenizers 0.13.3