Persian-QA-Bert-V1 / README.md
SeyedAli's picture
Update README.md
8fce4b0
metadata
license: apache-2.0
base_model: HooshvareLab/bert-fa-base-uncased
tags:
  - generated_from_trainer
model-index:
  - name: result
    results: []
language:
  - fa
datasets:
  - SeyedAli/Persian-Text-QA

result

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

  • Loss: 5.0331

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: 10

Training results

Training Loss Epoch Step Validation Loss
2.3247 1.0 1126 1.7615
1.4445 2.0 2252 1.8002
0.7653 3.0 3378 2.0806
0.4247 4.0 4504 2.6624
0.2502 5.0 5630 3.2961
0.168 6.0 6756 3.7767
0.0809 7.0 7882 4.3288
0.0544 8.0 9008 4.8516
0.0398 9.0 10134 4.9091
0.0102 10.0 11260 5.0331

Framework versions

  • Transformers 4.33.1
  • Pytorch 2.0.1+cu118
  • Datasets 2.14.5
  • Tokenizers 0.13.3