en-vi-nllb-200_TMG301

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

  • Loss: 1.3088
  • Bleu: 35.5708

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: 5e-05
  • train_batch_size: 16
  • eval_batch_size: 16
  • seed: 42
  • optimizer: Use 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: 3

Training results

Training Loss Epoch Step Validation Loss Bleu
No log 0.6000 5000 1.3604 34.3379
No log 1.2000 10000 1.3396 34.7695
No log 1.8001 15000 1.3140 35.3998
No log 2.4001 20000 1.3088 35.5708

Framework versions

  • Transformers 4.47.0
  • Pytorch 2.5.1+cu121
  • Datasets 3.3.1
  • Tokenizers 0.21.0
Downloads last month
13
Safetensors
Model size
615M params
Tensor type
F32
·
Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.

Model tree for nguyenvuhuy/en-vi-nllb-200_TMG301

Finetuned
(108)
this model