eanderson's picture
Update README.md
b144cd2 verified
metadata
license: cc-by-4.0
base_model: NbAiLab/nb-bert-base
tags:
  - generated_from_trainer
model-index:
  - name: nb-bert-base-qa-norquad
    results: []
datasets:
  - eanderson/NorQuAD
language:
  - 'no'
metrics:
  - squad

nb-bert-base-qa-norquad

This model is a fine-tuned version of NbAiLab/nb-bert-base on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 1.9546

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

model : eanderson/nb-bert-base-qa-norquad language : norwegian

dataset: eanderson/NorQuAD["text"] dataset_size: 472

exact_match : 59.110169491525426, f1 : 71.37800143052715

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 2e-05
  • train_batch_size: 1
  • eval_batch_size: 1
  • 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
1.5595 1.0 3808 1.6062
0.9856 2.0 7616 1.7905
0.4723 3.0 11424 1.9546

Framework versions

  • Transformers 4.31.0
  • Pytorch 2.1.0+cu118
  • Datasets 2.14.5
  • Tokenizers 0.13.3