You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

Garo-NLLB-En-Grt

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: 0.9170
Bleu: 35.5935

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 5e-05
train_batch_size: 8
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 32
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
lr_scheduler_warmup_steps: 500
num_epochs: 5

Framework versions

Transformers 5.16.0
Pytorch 2.13.0+cu130
Datasets 5.0.1
Tokenizers 0.23.1

Downloads last month: 8

Safetensors

Model size

0.6B params

Tensor type

F32

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for Bapynshngain/English-Garo

Base model

facebook/nllb-200-distilled-600M

Finetuned

(424)

this model