Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
mbart-nepali-lora – AI Model by binaya17 | AlphaNeural AI
You can deploy this model and start earning money today!
binaya17
/
mbart-nepali-lora
like
0
peft
safetensors
adapter
lora
transformers
facebook/mbart-large-50-many-to-many-mmt
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
mbart-nepali-lora
This model is a fine-tuned version of
facebook/mbart-large-50-many-to-many-mmt
on an unknown dataset. It achieves the following results on the evaluation set:
Loss: 0.5524
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: 0.0002
train_batch_size: 1
eval_batch_size: 1
seed: 42
gradient_accumulation_steps: 8
total_train_batch_size: 8
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
6.2137
1.0
1250
0.5955
4.7906
2.0
2500
0.5607
4.5888
3.0
3750
0.5524
Framework versions
PEFT 0.19.1
Transformers 5.0.0
Pytorch 2.10.0+cu128
Datasets 5.0.0
Tokenizers 0.22.2
