# Load model directly
from transformers import AutoTokenizer, AutoModelForSequenceClassification
tokenizer = AutoTokenizer.from_pretrained("arcleife/roberta-sentiment-id")
model = AutoModelForSequenceClassification.from_pretrained("arcleife/roberta-sentiment-id")Quick Links
Model Card for Model ID
Sentiment analysis model for Indonesian language. Built from xlm-roberta-base using indonlp/indonlu dataset.
Model Details
Model Description
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- Developed by: Muhamad Rizky Yanuar
- Model type: RoBERTa
- Language(s) (NLP): [Indonesian]
- License: Apache license 2.0
- Finetuned from model: xlm-roberta-base
Training Details
Training Data
Sentiment analysis dataset on indolu created by indonlp.
Training
Refer here.
Training hyperparameters
- num_train_epochs = 5
- learning_rate = 5e-6
- weight_decay = 1e-1
- per_device_train_batch_size = 16
- per_device_eval_batch_size = 16
- fp16 = True
Evaluation
| Epoch | Training Loss | Validation Loss | F1 | Recall | Precision |
|---|---|---|---|---|---|
| 1 | No log | 0.283834 | 0.908730 | 0.908730 | 0.908730 |
| 2 | No log | 0.248232 | 0.930952 | 0.930952 | 0.930952 |
| 3 | No log | 0.282172 | 0.930952 | 0.930952 | 0.930952 |
| 4 | No log | 0.257302 | 0.936508 | 0.936508 | 0.936508 |
| 5 | No log | 0.271212 | 0.939683 | 0.939683 | 0.939683 |
- Downloads last month
- 1
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="arcleife/roberta-sentiment-id")