ind-to-bbc-nmt-v4

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

  • Loss: 1.2930
  • Sacrebleu: 30.3825
  • Gen Len: 45.3035

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: 32
  • eval_batch_size: 16
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_ratio: 0.1
  • num_epochs: 5
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Sacrebleu Gen Len
5.3256 1.0 207 2.9469 25.3735 44.648
2.2418 2.0 414 1.5816 28.6826 45.3055
1.4644 3.0 621 1.3598 30.2304 45.373
1.2707 4.0 828 1.3034 30.4544 45.2655
1.2046 5.0 1035 1.2930 30.3825 45.3035

Framework versions

  • Transformers 4.41.2
  • Pytorch 2.3.0+cu121
  • Datasets 2.14.6
  • Tokenizers 0.19.1
Downloads last month
13
Safetensors
Model size
615M params
Tensor type
F32
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for kepinsam/ind-to-bbc-nmt-v4

Finetuned
(86)
this model

Evaluation results