VieBahnar-Synonym-Freeze

FiveC/VieBahnar-Synonym-Freeze

VieBahnar-Synonym-Freeze is a machine learning model from FiveC. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for transformers. The card lists the license as mit.

should probably proofread and complete it, then remove this comment. --

Downloads · 30 days

9% of all-time downloads

All-time downloads

Public

Parameters

396M

4.8 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors1.6 GB · 100%

At a glance

Library: transformers
License: mit
Model type: mbart
Access: Public
Created: Jan 5, 2026
Updated: Jan 5, 2026
SHA: 9042889d

Base models

Model card

From the Hugging Face model README

VieBahnar-Synonym-Freeze

This model is a fine-tuned version of IAmSkyDra/BARTBana_v5 on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 1.8400
Sacrebleu: 0.7258
Meteor: 0.0803

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: 2e-05
train_batch_size: 64
eval_batch_size: 64
seed: 42
optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
num_epochs: 3
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Sacrebleu	Meteor
0.9567	1.0	10585	1.7067	0.6032	0.0728
0.7848	2.0	21170	1.8016	0.7278	0.0800
0.7257	3.0	31755	1.8400	0.7258	0.0803

Framework versions

Transformers 4.57.3
Pytorch 2.9.0+cu126
Datasets 4.0.0
Tokenizers 0.22.1

Library: transformers
Type: mbart
License: mit
Created: Jan 5, 2026
Updated: Jan 5, 2026