|
|
--- |
|
|
license: mit |
|
|
base_model: indobenchmark/indobart-v2 |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
metrics: |
|
|
- bleu |
|
|
model-index: |
|
|
- name: nmt-bert |
|
|
results: [] |
|
|
--- |
|
|
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
|
|
# nmt-bert |
|
|
|
|
|
This model is a fine-tuned version of [indobenchmark/indobart-v2](https://huggingface.co/indobenchmark/indobart-v2) on the None dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 0.5134 |
|
|
- Bleu: 12.5276 |
|
|
- Gen Len: 19.7772 |
|
|
|
|
|
## 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: 2e-05 |
|
|
- train_batch_size: 32 |
|
|
- eval_batch_size: 16 |
|
|
- seed: 42 |
|
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
|
- lr_scheduler_type: linear |
|
|
- num_epochs: 10 |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len | |
|
|
|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:| |
|
|
| 1.0103 | 1.0 | 503 | 0.7001 | 9.036 | 19.7452 | |
|
|
| 0.666 | 2.0 | 1006 | 0.6230 | 10.5729 | 19.7332 | |
|
|
| 0.5776 | 3.0 | 1509 | 0.5784 | 11.1366 | 19.7648 | |
|
|
| 0.5245 | 4.0 | 2012 | 0.5548 | 11.6349 | 19.7713 | |
|
|
| 0.4821 | 5.0 | 2515 | 0.5389 | 11.903 | 19.769 | |
|
|
| 0.4513 | 6.0 | 3018 | 0.5299 | 12.2062 | 19.7618 | |
|
|
| 0.4269 | 7.0 | 3521 | 0.5215 | 12.3633 | 19.7713 | |
|
|
| 0.4097 | 8.0 | 4024 | 0.5165 | 12.4102 | 19.7787 | |
|
|
| 0.3976 | 9.0 | 4527 | 0.5144 | 12.4693 | 19.7792 | |
|
|
| 0.3897 | 10.0 | 5030 | 0.5134 | 12.5276 | 19.7772 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.33.3 |
|
|
- Pytorch 2.0.1+cu118 |
|
|
- Datasets 2.14.5 |
|
|
- Tokenizers 0.13.3 |
|
|
|
