Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
3stageDEC17-nllb-1-sentence-punjabi – AI Model by GJATT | AlphaNeural AI
You can deploy this model and start earning money today!
GJATT
/
3stageDEC17-nllb-1-sentence-punjabi
like
0
transformers
tensorboard
safetensors
m2m_100
text2text-generation
generated_from_trainer
GJATT/2stageDEC15-nllb-1-sentence-punjabi
finetune
endpoints_compatible
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
3stageDEC17-nllb-1-sentence-punjabi
This model is a fine-tuned version of
GJATT/2stageDEC15-nllb-1-sentence-punjabi
on an unknown dataset. It achieves the following results on the evaluation set:
Loss: 0.1769
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: 5e-06
train_batch_size: 8
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 2
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
lr_scheduler_warmup_steps: 200
num_epochs: 5
mixed_precision_training: Native AMP
Training results
Training Loss
Epoch
Step
Validation Loss
0.5713
1.0
325
0.3366
0.4136
2.0
650
0.2485
0.4021
3.0
975
0.2045
0.3618
4.0
1300
0.1837
0.3589
5.0
1625
0.1769
Framework versions
Transformers 4.57.3
Pytorch 2.9.0+cu126
Datasets 4.4.1
Tokenizers 0.22.1
