README.md

metadata

license: apache-2.0
tags:
  - generated_from_trainer
datasets:
  - persian_qa
model_index:
  - name: bert-fa-QA-v1
    results:
      - task:
          name: Question Answering
          type: question-answering
        dataset:
          name: persian_qa
          type: persian_qa
          args: persian_qa

bert-fa-QA-v1

This model is a fine-tuned version of HooshvareLab/bert-fa-base-uncased on the persian_qa dataset. It achieves the following results on the evaluation set:

• Loss: 4.4213

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: 3e-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: 2

Training results

Training Loss	Epoch	Step	Validation Loss
0.237	1.0	1126	3.9892
0.1135	2.0	2252	4.4213

Framework versions

• Transformers 4.9.0
• Pytorch 1.9.0+cu102
• Datasets 1.10.2
• Tokenizers 0.10.3