Ir para o conteúdo
ModelListadosExterno
Baixar

Nllb Indo En

This model is a fine-tuned version of facebook/nllb-200-distilled-600M on Fleurs Dataset without duplication of ids. It achieves the following results on the evaluation set: Loss: 0.3048

Fontehuggingface.co/cobrayyxx/nllb-indo-en/tree/9cc2a63ee670a4fcaff03679f7a89e240cc19595
TipoText modelModelo basefacebook/nllb-200-distilled-600MVersãoFP32Bnota

Fonte do modelo

Tipo
Text model
Tamanho do arquivo
2,29 GB
Modelo base
facebook/nllb-200-distilled-600M
Versão
vFP32
Atualizado
31 de out. de 2026
Downloads
41
Fonte
Hugging Face

Descrição da fonte

nllb-indo-en

This model is a fine-tuned version of facebook/nllb-200-distilled-600M on Fleurs Dataset without duplication of ids. It achieves the following results on the evaluation set:

  • Loss: 0.3048

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 5e-05
  • train_batch_size: 2
  • eval_batch_size: 2
  • seed: 42
  • gradient_accumulation_steps: 8
  • total_train_batch_size: 16
  • optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
  • lr_scheduler_type: linear
  • training_steps: 1000
  • mixed_precision_training: Native AMP

Training results

Training LossEpochStepValidation Loss
No log1.0964.3318
53.12742.01922.0475
25.76343.02880.4936
8.43884.03840.2444
1.78965.04800.2407
0.88536.05760.2626
0.55837.06720.2793
0.43538.07680.2936
0.34979.08640.2992
0.296910.09600.3038
0.271310.419910000.3048

Model Evaluation

The performance of this model was evaluated using BLEU and CHRF metrics on validation dataset.

BLEUCHRF
40.9466.46

Framework versions

  • Transformers 4.47.1
  • Pytorch 2.5.1+cu121
  • Datasets 3.2.0
  • Tokenizers 0.21.0

Fontes

1 fonte
Hugging FacePrimárioVersão 9cc2a63ee670a4fcaff03679f7a89e240cc19595
huggingface.co/cobrayyxx/nllb-indo-en/tree/9cc2a63ee670a4fcaff03679f7a89e240cc19595

Verificado 31 de out.

Download files

Repository files

File inventory only; completeness is unverified.

Artefatos de modelo

1 artefato

model.safetensors

safetensors · FP32 (unverified) · 2,29 GB · SHA-256 83e9a6803b15…bc24 · Hugging Face

Download file

Trechos de fonte

3 trechos
Readme15 de ago.huggingface.co/cobrayyxx/nllb-indo-en

--- library_name: transformers license: cc-by-nc-4.0 base_model: facebook/nllb-200-distilled-600M tags: - generated_from_trainer model-index: - name: nllb-indo-en-cleaned results: [] datasets: - cobrayyxx/FLEURS_INDO-ENG_Speech_Translation_No_Duplicate language: - id - en metrics: - bleu - chrf pipeline_tag: audio-text-to-text --- <!-- 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. --> # nllb-indo-en This model is a fine-tuned version of [facebook/nllb-200-distilled-600M](https://huggingface.co/facebook/nllb-200-distilled-600M) on [Fleurs Dataset](https://huggingface.co/datasets/cobrayyxx/FLEURS_INDO-ENG_Speech_Translation_No_Duplicate) without duplication of `id`s. It achieves the following results on the evaluation set: - Loss: 0.3048 ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-05 - train_batch_size: 2 - eval_batch_size: 2 - seed: 42 - gradient_accumulation_steps: 8 - total_train_batch_size: 16 - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments - lr_scheduler_type: linear - training_steps: 1000 - mixed_precision_training: Native AMP ### Training results | Training Loss | Epoch | Step | Validation Loss | |:-------------:|:-------:|:----:|:---------------:| | No log | 1.0 | 96 | 4.3318 | | 53.1274 | 2.0 | 192 | 2.0475 | | 25.7634 | 3.0 | 288 | 0.4936 | | 8.4388 | 4.0 | 384 | 0.2444 | | 1.7896 | 5.0 | 480 | 0.2407 | | 0.8853 | 6.0 | 576 | 0.2626 | | 0.5583 | 7.0 | 672 | 0.2793 | | 0.4353 | 8.0 | 768 | 0.2936 | | 0.3497 | 9.0 | 864 | 0.2992 | | 0.2969 | 10.0 | 960 | 0.3038 | | 0.2713 | 10.4199 | 1000 | 0.3048 | ## Model Evaluation The performance of this model was evaluated using BLEU and CHRF metrics on validation dataset. | BLEU | CHRF | |:----:|:-----:| | 40.94| 66.46 | ### Framework versions - Transformers 4.47.1 - Pytorch 2.5.1+cu121 - Datasets 3.2.0 - Tokenizers 0.21.0

Note31 de out.huggingface.co/cobrayyxx/nllb-indo-en

Source context: 41 downloads · 0 likes · Pipeline audio-text-to-text · Library transformers · Repo cobrayyxx/nllb-indo-en

Note15 de ago.huggingface.co/cobrayyxx/nllb-indo-en

Source context: 9 downloads · 0 likes · Pipeline audio-text-to-text · Library transformers · Repo cobrayyxx/nllb-indo-en