metadata

language: hebrew
datasets:
  - squad
widget:
  - text: 123?
    context: '456'
  - text: '789'
    context: 10 11 12
license: apache-2.0

tags: - generated_from_trainer model-index: - name: hebert-finetuned-hebrew-squad results: []

hebert-finetuned-hebrew-squad

This model was fine-tuned heBERT model on Hebrew SQuAD dataset.H

Model description

More information needed

Intended uses & limitations

Hebrew SQuAD

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: 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: 15

Framework versions

Transformers 4.17.0
Pytorch 1.10.0+cu111
Datasets 1.18.4
Tokenizers 0.11.6

About Us

Created by Matan Ben-chorin, May Flaster, Guided by Dr. Oren Mishali. This is our final project as part of computer engineering B.Sc studies in the Faculty of Electrical Engineering combined with Computer Science at Technion, Israel Institute of Technology. For more cooperation, please contact email: Matan Ben-chorin: [email protected] May Flaster: [email protected]