Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
qwen_finetuned_arabic_culture_2 – AI Model by Walid2025 | AlphaNeural AI
You can deploy this model and start earning money today!
Walid2025
/
qwen_finetuned_arabic_culture_2
like
0
transformers
tensorboard
safetensors
qwen2
text-generation
generated_from_trainer
conversational
Qwen/Qwen2.5-3B-Instruct
finetune
other
autotrain_compatible
text-generation-inference
endpoints_compatible
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
qwen_finetuned_arabic_culture_2
This model is a fine-tuned version of
Qwen/Qwen2.5-3B-Instruct
on the None dataset. It achieves the following results on the evaluation set:
Loss: 1.4461
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: 1e-05
train_batch_size: 1
eval_batch_size: 1
seed: 42
gradient_accumulation_steps: 8
total_train_batch_size: 8
optimizer: Use OptimizerNames.ADAMW_TORCH 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: 50
num_epochs: 20
Training results
Training Loss
Epoch
Step
Validation Loss
1.2167
4.0
1000
1.4461
1.0331
8.0
2000
1.5088
0.9632
12.0
3000
1.5632
Framework versions
Transformers 4.54.0
Pytorch 2.6.0+cu124
Datasets 4.0.0
Tokenizers 0.21.2
