Indonesian RoBERTa Large

Indonesian RoBERTa Large is a masked language model based on the RoBERTa model. It was trained on the OSCAR dataset, specifically the unshuffled_deduplicated_id subset. The model was trained from scratch and achieved an evaluation loss of 4.801 and an evaluation accuracy of 29.8%.

This model was trained using HuggingFace's Flax framework and is part of the JAX/Flax Community Week organized by HuggingFace. All training was done on a TPUv3-8 VM, sponsored by the Google Cloud team.

All necessary scripts used for training could be found in the Files and versions tab, as well as the Training metrics logged via Tensorboard.

Model

Model #params Arch. Training/Validation data (text)
indonesian-roberta-large 355M RoBERTa OSCAR unshuffled_deduplicated_id Dataset

Evaluation Results

The model was trained for 10 epochs and the following is the final result once the training ended.

train loss valid loss valid accuracy total time
5.19 4.801 0.298 2:8:32:28

How to Use

As Masked Language Model

from transformers import pipeline

pretrained_name = "flax-community/indonesian-roberta-large"

fill_mask = pipeline(
    "fill-mask",
    model=pretrained_name,
    tokenizer=pretrained_name
)

fill_mask("Budi sedang <mask> di sekolah.")

Feature Extraction in PyTorch

from transformers import RobertaModel, RobertaTokenizerFast

pretrained_name = "flax-community/indonesian-roberta-large"
model = RobertaModel.from_pretrained(pretrained_name)
tokenizer = RobertaTokenizerFast.from_pretrained(pretrained_name)

prompt = "Budi sedang berada di sekolah."
encoded_input = tokenizer(prompt, return_tensors='pt')
output = model(**encoded_input)

Team Members

Downloads last month
24
Hosted inference API
Fill-Mask
Examples
Examples
Mask token: <mask>
This model can be loaded on the Inference API on-demand.