chat-indogpt / README.md
abdiharyadi's picture
Add dataset, language, and how-to-use information on README.md
175aac3 verified
metadata
license: mit
base_model: indobenchmark/indogpt
tags:
  - generated_from_trainer
model-index:
  - name: chat-indogpt
    results: []
datasets:
  - indonesian-nlp/eli5_id
language:
  - id

chat-indogpt

This model is a fine-tuned version of indobenchmark/indogpt on indonesian-nlp/eli5_id dataset.

Model description

More information needed

Intended uses & limitations

Please use this repository to use this model.

Limitation: This model can't understand the prompt well enough.

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 1e-05
  • train_batch_size: 4
  • eval_batch_size: 8
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 1

Training results

Framework versions

  • Transformers 4.40.2
  • Pytorch 2.3.0+cu121
  • Datasets 2.19.1
  • Tokenizers 0.19.1