|
|
--- |
|
|
library_name: transformers |
|
|
license: apache-2.0 |
|
|
datasets: |
|
|
- indonlp/indonlu |
|
|
language: |
|
|
- id |
|
|
metrics: |
|
|
- f1 |
|
|
- accuracy |
|
|
- recall |
|
|
base_model: |
|
|
- FacebookAI/xlm-roberta-base |
|
|
--- |
|
|
|
|
|
# Model Card for Model ID |
|
|
|
|
|
Sentiment analysis model for Indonesian language. Built from [xlm-roberta-base](https://huggingface.co/FacebookAI/xlm-roberta-base) using [indonlp/indonlu](https://huggingface.co/datasets/indonlp/indonlu) dataset. |
|
|
|
|
|
## Model Details |
|
|
|
|
|
### Model Description |
|
|
|
|
|
<!-- Provide a longer summary of what this model is. --> |
|
|
|
|
|
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](https://arcleife.github.io/portfolio/) |
|
|
- **Model type:** [RoBERTa](https://huggingface.co/docs/transformers/en/model_doc/roberta) |
|
|
- **Language(s) (NLP):** [Indonesian] |
|
|
- **License:** [Apache license 2.0](https://www.apache.org/licenses/LICENSE-2.0) |
|
|
- **Finetuned from model:** [xlm-roberta-base](https://huggingface.co/FacebookAI/xlm-roberta-base) |
|
|
|
|
|
## Training Details |
|
|
|
|
|
### Training Data |
|
|
|
|
|
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> |
|
|
|
|
|
[Sentiment analysis dataset on indolu](https://huggingface.co/datasets/indonlp/indonlu) created by indonlp. |
|
|
|
|
|
### Training |
|
|
|
|
|
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> |
|
|
|
|
|
Refer [here](https://github.com/arcleife/notebooks/blob/main/sentiment_finetuning.py). |
|
|
|
|
|
**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 |
|
|
|
|
|
<!-- This section describes the evaluation protocols and provides the results. --> |
|
|
|
|
|
|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 | |
