Bert2Bert (Encoder-Decoder) on Liputan6 100k dataset

Dataset source: https://huggingface.co/datasets/fajrikoto/id_liputan6
Model used for Fine Tuning (Encoder-Decoder):
https://huggingface.co/cahya/bert-base-indonesian-1.5G

Trained on 1x3090 @ 8 epoch (EarlyStopping Callbacks)

Train logs, metrics, and params: https://wandb.ai/willy030125/huggingface/runs/sb2kcuck
https://www.comet.com/willy030125/huggingface/5dd7c19d0c85472abdf4136529f4322c
Eval results and Perplexity: eval_results.json

Usage:

from transformers import AutoTokenizer, EncoderDecoderModel
tokenizer = AutoTokenizer.from_pretrained("Willy030125/Bert2Bert_Liputan6_100k_8epoch")
model = EncoderDecoderModel.from_pretrained("Willy030125/Bert2Bert_Liputan6_100k_8epoch")
Downloads last month
4
Safetensors
Model size
250M params
Tensor type
F32
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.