Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
Qweni – AI Model by sunjisen | AlphaNeural AI
You can deploy this model and start earning money today!
sunjisen
/
Qweni
like
0
safetensors
qwen2
llama-factory
freeze
generated_from_trainer
Qwen/Qwen2.5-1.5B-Instruct
finetune
other
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
output
This model is a fine-tuned version of Qwen2.5-1.5B-Instruct on the alpaca_zh_demo dataset. It achieves the following results on the evaluation set:
Loss: 1.9959
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: 0.0001
train_batch_size: 1
eval_batch_size: 1
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 2
optimizer: Use 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_ratio: 0.1
num_epochs: 3.0
mixed_precision_training: Native AMP
Training results
Training Loss
Epoch
Step
Validation Loss
1.0102
1.1111
500
1.7723
0.5375
2.2222
1000
1.9768
Framework versions
Transformers 4.46.1
Pytorch 2.3.0+cu121
Datasets 3.0.2
Tokenizers 0.20.3
