Edit model card

sapbert-from-pubmedbert-squad2

This model is a fine-tuned version of cambridgeltl/SapBERT-from-PubMedBERT-fulltext on the squad_v2 dataset. It achieves the following results on the evaluation set:

  • Loss: 1.2582

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: 5

Training results

Training Loss Epoch Step Validation Loss
1.035 1.0 8298 0.9545
0.8053 2.0 16596 0.9988
0.5949 3.0 24894 0.9909
0.4878 4.0 33192 1.1428
0.3932 5.0 41490 1.2582

Framework versions

  • Transformers 4.7.0
  • Pytorch 1.8.0
  • Datasets 1.4.1
  • Tokenizers 0.10.2
Downloads last month
16
Hosted inference API
Question Answering
Examples
Examples
This model can be loaded on the Inference API on-demand.

Dataset used to train bigwiz83/sapbert-from-pubmedbert-squad2