nllb-200-600M-dzo-eng

This model is a fine-tuned version of facebook/nllb-200-distilled-600M on kinleyrabgay/dz_to_en dataset. It achieves the following results on the evaluation set:

  • Loss: 0.0774
  • Bleu: 59.5127

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: 3e-05
  • train_batch_size: 4
  • eval_batch_size: 4
  • seed: 42
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 8
  • 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
  • num_epochs: 5
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Bleu
0.0765 1.0 1250 0.0746 58.0373
0.0576 2.0 2500 0.0728 58.5746
0.0465 3.0 3750 0.0735 59.3099
0.0381 4.0 5000 0.0758 59.2493
0.033 5.0 6250 0.0774 59.5127

Framework versions

  • Transformers 4.52.4
  • Pytorch 2.6.0+cu124
  • Datasets 3.6.0
  • Tokenizers 0.21.1

Usage

from transformers import pipeline

translator = pipeline(
    "translation",
    model="kinleyrabgay/nllb-200-600M-dzo-eng",
    src_lang="dzo_Tibt",
    tgt_lang="eng_Latn"
)

dz_text = "ག་ནི་བ་ ཡིད་ཕྲོག"
translation = translator(dz_text)
print(translation[0]['translation_text'])
Downloads last month
72
Safetensors
Model size
615M params
Tensor type
F32
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 1 Ask for provider support

Model tree for kinleyrabgay/nllb-200-600M-dzo-eng

Unable to build the model tree, the base model loops to the model itself. Learn more.