Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
qwen3-8b-belebele-lora-kir-cyrl – AI Model by xummer | AlphaNeural AI
You can deploy this model and start earning money today!
xummer
/
qwen3-8b-belebele-lora-kir-cyrl
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_kir_Cyrl
This model is a fine-tuned version of
Qwen/Qwen3-8B
on the belebele_kir_Cyrl_train dataset. It achieves the following results on the evaluation set:
Loss: 0.0862
Accuracy: 0.9624
Mcq Accuracy: 0.6364
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
0.0738
2.1053
40
0.0730
0.9611
0.5909
0.0361
4.2105
80
0.0843
0.9628
0.6591
Framework versions
PEFT 0.18.1
Transformers 5.2.0
Pytorch 2.10.0+cu128
Datasets 4.0.0
Tokenizers 0.22.2
