bert-fa-base-uncased-finetuned-ParsBert

This repo is just a try to learn working with hugging face. This model is a fine-tuned version of HooshvareLab/bert-fa-base-uncased on a very simple handmade dataset from !kaggle datasets download -d miladfa7/persian-wikipedia-dataset. It achieves the following results on the evaluation set:

• Loss: 1.8240 https://colab.research.google.com/drive/1gqE1AHdEDl20QNC5lF548-5NQujjp9zU?usp=sharing

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: 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: 3.0

Training results

Training Loss	Epoch	Step	Validation Loss
No log	1.0	8	2.0729
No log	2.0	16	1.9354
No log	3.0	24	2.0527

Framework versions

• Transformers 4.28.1
• Pytorch 2.0.0+cu118
• Datasets 2.12.0
• Tokenizers 0.13.3