bart-qg-finetuned-hotpotqa

This model is a fine-tuned version of p208p2002/bart-squad-qg-hl on the hotpot_qa dataset. It achieves the following results on the evaluation set:

  • Loss: 1.0817
  • Rouge1: 46.2814
  • Rouge2: 30.4609
  • Rougel: 42.3385
  • Rougelsum: 42.3741

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: 5.6e-05
  • train_batch_size: 8
  • eval_batch_size: 8
  • 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 Rouge1 Rouge2 Rougel Rougelsum
1.3949 1.0 2500 1.1812 44.0967 28.022 40.0397 40.0403
1.0883 2.0 5000 1.1141 44.9629 29.1863 41.1078 41.1684
0.8677 3.0 7500 1.0817 46.2814 30.4609 42.3385 42.3741

Framework versions

  • Transformers 4.24.0
  • Pytorch 1.12.1+cu113
  • Datasets 2.7.1
  • Tokenizers 0.13.2
Downloads last month
14
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Dataset used to train jjjunyeong/bart-qg-finetuned-hotpotqa

Evaluation results