|
--- |
|
library_name: transformers |
|
license: apache-2.0 |
|
datasets: |
|
- carant-ai/indonesian_sentiment_dataset |
|
- carant-ai/english_sentiment_dataset |
|
language: |
|
- en |
|
- id |
|
metrics: |
|
- accuracy |
|
pipeline_tag: text-classification |
|
--- |
|
### Model Description |
|
Finetuned xlm-roberta-large for Sentiment Analysis in English and Bahasa Indonesia |
|
### Training results |
|
Trained on TPU VM v4-8 for ~5 hours |
|
|epoch|step|train_accuracy|train_loss|val_accuracy|val_loss| |
|
| --- | --- | --- | --- | --- | --- | |
|
|0|10782|0.964588165|0.095930442|0.967545867|0.08873909| |
|
|1|21565|0.970602274|0.079982288|0.968977571|0.08539474| |
|
### Training procedure |
|
For replication, go to [GitHub page](https://github.com/carant-ai/tpu-sentiment-trainer/tree/main) |
|
### Acknowledgement |
|
1. Google’s TPU Research Cloud (TRC) for providing Cloud TPU VM. |
|
2. [carlesoctav](https://huggingface.co/carlesoctav) for making the training script on TPU VM |
|
3. [thonyyy](https://huggingface.co/thonyyy) for gathering the sentiment dataset |
|
|
|
|
