hkp24

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: 1.1619

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
1.2249	1.0	5533	1.1675
0.961	2.0	11066	1.1376
0.7581	3.0	16599	1.1619

Framework versions

• Transformers 4.19.1
• Pytorch 1.11.0+cu113
• Datasets 2.2.1
• Tokenizers 0.12.1