Aller au contenu
ModelPrésentéExterne
Télécharger

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

Sourcehuggingface.co/cobrayyxx/nllb-indo-en/tree/9cc2a63ee670a4fcaff03679f7a89e240cc19595
TypeText modelModèle de basefacebook/nllb-200-distilled-600MVersionFP32BClasse

Source du modèle

Type
Text model
Taille du fichier
2,29 GB
Modèle de base
facebook/nllb-200-distilled-600M
Version
vFP32
Mis à jour
31 oct. 2026
Téléchargements
41
Source
Hugging Face

Description de la source

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

Sources

1 source
Hugging FacePrincipalVersion 9cc2a63ee670a4fcaff03679f7a89e240cc19595
huggingface.co/cobrayyxx/nllb-indo-en/tree/9cc2a63ee670a4fcaff03679f7a89e240cc19595

Vérifié 31 oct.

Download files

Repository files

File inventory only; completeness is unverified.

Artefacts du modèle

1 artefact

model.safetensors

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

Download file

Extraits de sources

3 extraits
Readme15 aoûthuggingface.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 oct.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 aoûthuggingface.co/cobrayyxx/nllb-indo-en

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