Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
nllb-cantonese-mandarin-v1 – AI Model by baikai1022 | AlphaNeural AI
You can deploy this model and start earning money today!
baikai1022
/
nllb-cantonese-mandarin-v1
like
0
transformers
tensorboard
safetensors
m2m_100
text2text-generation
generated_from_trainer
facebook/nllb-200-distilled-600M
finetune
cc-by-nc-4.0
endpoints_compatible
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
nllb-cantonese-mandarin-v1
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: 0.3608
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: 4
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 16
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
0.5168
1.0
1361
0.4253
0.4844
2.0
2722
0.3727
0.4124
3.0
4083
0.3608
Framework versions
Transformers 4.57.3
Pytorch 2.9.0+cu126
Datasets 4.0.0
Tokenizers 0.22.1
