metadata
license: apache-2.0
language:
- id
- en
Fine-tuned IndoBERT
This model is a fine-tuned version of IndoBERT for sentiment analysis.
Model Details
- Model Architecture: BERT (Bidirectional Encoder Representations from Transformers)
- Fine-tuning Objective: Sentiment Analysis
- Dataset: DANA Sentiment Analysis from Playstore Indonesia from Kaggle
Usage
from transformers import AutoModelForSequenceClassification, AutoTokenizer
model = AutoModelForSequenceClassification.from_pretrained("your-username/fine-tuned-indobert")
tokenizer = AutoTokenizer.from_pretrained("your-username/fine-tuned-indobert")
inputs = tokenizer("Your input text", return_tensors="pt")
outputs = model(**inputs)
Training data
The model was trained on a custom dataset for sentiment analysis.
Hyperparameters
- Learning rate: 2e-05
- Train batch size: 6
- Eval batch size: 6
- Epochs: 5
- Optimizer: Adam with betas=(0.9, 0.999) and epsilon=1e-08
- LR scheduler type: Linear
- Seed: 42
- Accuracy: 0.8578