Beta
Explore
Marketplace
Neural Labs
Playground
Wallet
Docs
qwen3-8b-belebele-lora-urd-arab – AI Model by xummer | AlphaNeural AI
You can deploy this model and start earning money today!
xummer
/
qwen3-8b-belebele-lora-urd-arab
like
0
peft
safetensors
adapter
llama-factory
lora
transformers
text-generation
conversational
Qwen/Qwen3-8B
other
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
belebele_urd_Arab
This model is a fine-tuned version of
Qwen/Qwen3-8B
on the belebele_urd_Arab_train dataset. It achieves the following results on the evaluation set:
Loss: 0.0452
Accuracy: 0.9771
Mcq Accuracy: 0.8654
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: 16
eval_batch_size: 16
seed: 42
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: cosine
lr_scheduler_warmup_steps: 0.1
num_epochs: 5.0
Training results
Training Loss
Epoch
Step
Validation Loss
Accuracy
Mcq Accuracy
0.0520
2.0
40
0.0423
0.9748
0.8462
0.0317
4.0
80
0.0425
0.9777
0.8654
Framework versions
PEFT 0.18.1
Transformers 5.2.0
Pytorch 2.10.0+cu128
Datasets 4.0.0
Tokenizers 0.22.2
