IndoT5 Machine Translation
Collection
Fine-tuned mT5 models on languages of Indonesia. Based on Many-to-Many Multilingual Translation Model for Languages of Indonesia (Wongso et al., 2023)
•
4 items
•
Updated
indo-t5-base-nusax
This model is a fine-tuned version of lazarus-project/indo-t5-base on the lazarus-project/NusaX-MT dataset. It achieves the following results on the evaluation set:
- Loss: 2.2604
- Bleu: 19.701
- Gen Len: 48.7964
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0002
- train_batch_size: 32
- eval_batch_size: 16
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- total_train_batch_size: 256
- total_eval_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- training_steps: 500
Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
|---|---|---|---|---|---|
| 1.8951 | 3.01 | 250 | 2.2655 | 3.9246 | 18.6281 |
| 1.5435 | 6.02 | 500 | 2.2604 | 4.1139 | 18.6052 |
Framework versions
- Transformers 4.27.1
- Pytorch 2.0.0+cu117
- Datasets 2.9.0
- Tokenizers 0.13.2
- Downloads last month
- 68
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.