|
--- |
|
license: apache-2.0 |
|
base_model: Helsinki-NLP/opus-mt-rw-en |
|
tags: |
|
- translation |
|
- generated_from_trainer |
|
metrics: |
|
- bleu |
|
model-index: |
|
- name: marian-finetuned-multidataset-kin-to-en |
|
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. --> |
|
|
|
# marian-finetuned-multidataset-kin-to-en |
|
|
|
This model is a fine-tuned version of [Helsinki-NLP/opus-mt-rw-en](https://huggingface.co/Helsinki-NLP/opus-mt-rw-en) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.7550 |
|
- Bleu: 36.2717 |
|
|
|
## Model Description |
|
|
|
The model has been fine-tuned to perform machine translation from Kinyarwanda to English. |
|
|
|
## Intended Uses & Limitations |
|
|
|
The primary intended use of this model is for research purposes. |
|
|
|
## Training and Evaluation Data |
|
|
|
The model was fine-tuned using a combination of datasets from the following sources: |
|
- [Digital Umuganda](https://huggingface.co/datasets/DigitalUmuganda/kinyarwanda-english-machine-translation-dataset/tree/main) |
|
- [Masakhane](https://huggingface.co/datasets/masakhane/mafand/viewer/en-kin/validation) |
|
- [Muennighoff](https://huggingface.co/datasets/Muennighoff/flores200) |
|
|
|
For the training of the machine translation model, the dataset underwent the following preprocessing steps: |
|
- Text was converted to lowercase |
|
- Digits were removed |
|
|
|
The combined dataset was divided into training and validation sets, with a split of 90% for training and 10% for validation. |
|
|
|
## Training procedure |
|
|
|
### Training hyperparameters |
|
|
|
The following hyperparameters were used during training: |
|
- learning_rate: 2e-05 |
|
- train_batch_size: 32 |
|
- eval_batch_size: 64 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 3 |
|
|
|
### Training results |
|
|
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.31.0 |
|
- Pytorch 2.0.1+cu118 |
|
- Datasets 2.14.4 |
|
- Tokenizers 0.13.3 |
|
|