You can deploy this model and start earning money today!

ntr2026/
mbart-en-es-ddhh

Name: mbart-en-es-ddhh
Availability: InStock

generated_from_trainer

facebook/mbart-large-50

finetune

mit

endpoints_compatible

Views

No views yet

mbart-en-es-ddhh

This model is a fine-tuned version of facebook/mbart-large-50 on a dataset based on translation EN-ES of Universal Declaration of Human Rights (https://huggingface.co/datasets/ntr2026/DDHH_en-es). It achieves the following results on the evaluation set:

Loss: 4.7211
Bleu: 11.5131
Gen Len: 20.05

Model description

This model has been delivered as part of a class project.

Intended uses & limitations

The model is aim to translating from English to Spanish. As the low BLEU score shows, this model has very low accuracy, given the limitation of the dataset.

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 1e-05
train_batch_size: 4
eval_batch_size: 4
seed: 42
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_ratio: 0.1
num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Bleu	Gen Len
No log	1.0	20	5.7706	3.0459	43.4
No log	2.0	40	5.0240	7.9484	28.65
No log	3.0	60	4.8107	8.1545	16.35
No log	4.0	80	4.7645	12.0661	18.25
No log	5.0	100	4.7211	11.5131	20.05

Framework versions

Transformers 4.51.2
Pytorch 2.10.0+cu128
Datasets 4.7.0
Tokenizers 0.21.4

ntr2026/mbart-en-es-ddhh