nllb-3.3B-wolof-v8 – AI Model by mogu98 | AlphaNeural AI

You can deploy this model and start earning money today!

mogu98/
nllb-3.3B-wolof-v8

like

0

text2text-generation

generated_from_trainer

facebook/nllb-200-3.3B

endpoints_compatible

Views

No views yet

nllb-3.3B-wolof-v8

This model is a fine-tuned version of facebook/nllb-200-3.3B on the None dataset. It achieves the following results on the evaluation set:

Loss: 1.2000
Bleu: 28.4841

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: 8
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 32
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: 1

Training results

Training Loss	Epoch	Step	Validation Loss	Bleu
5.8718	0.1232	1500	1.4402	24.4060
5.4223	0.2465	3000	1.3488	25.5368
5.1987	0.3697	4500	1.2952	26.3876
5.0114	0.4929	6000	1.2641	27.0547
4.5170	0.6162	7500	1.2358	28.0915
4.5984	0.7394	9000	1.2161	28.5358
4.5581	0.8626	10500	1.2063	28.4373
4.6235	0.9858	12000	1.2001	28.4446
4.7048	1.0	12173	1.2000	28.4841

Framework versions

Transformers 5.10.2
Pytorch 2.8.0+cu128
Datasets 5.0.0
Tokenizers 0.22.2