Eladio's picture
Update README.md
78ecfaa verified
metadata
license: cc-by-4.0
base_model: deepset/tinyroberta-squad2
tags:
  - generated_from_trainer
model-index:
  - name: tinyroberta-squad2-finetuned-emrqa-msquad
    results: []
datasets:
  - Eladio/emrqa-msquad
language:
  - en
metrics:
  - exact_match
  - f1
  - precision
  - recall
  - bleu
  - rouge
pipeline_tag: question-answering

tinyroberta-squad2-finetuned-emrqa-msquad

This model is a fine-tuned version of deepset/tinyroberta-squad2 on medical dataset Eladio/emrqa-msquad. It achieves the following results on the evaluation set:

  • Loss: 0.0435

Model description

deepset/tinyroberta-squad2 on medical dataset Eladio/emrqa-msquad

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
0.2736 1.0 15878 0.1806
0.1034 2.0 31756 0.0803
0.0475 3.0 47634 0.0435

Framework versions

  • Transformers 4.38.2
  • Pytorch 2.1.0+cu121
  • Datasets 2.18.0
  • Tokenizers 0.15.2