---

license: apache-2.0 tags:

• generated_from_trainer datasets:
• squad model-index:
• name: distilbert-base-uncased-finetuned-squad results: [] We

distilbert-base-uncased-finetuned-squad

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

• Loss: 1.1487

Model description

F1 score: 85.1341

Intended uses & limitations

More information needed

Training and evaluation data

SQUAD 2.0

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
1.2118	1.0	5533	1.1484
0.9424	2.0	11066	1.1121
0.7441	3.0	16599	1.1487

Framework versions

• Transformers 4.20.1
• Pytorch 1.12.0+cu113
• Datasets 2.3.2
• Tokenizers 0.12.1