Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
Qwen2-0.5B-Reward – AI Model by sadmankiba | AlphaNeural AI
You can deploy this model and start earning money today!
sadmankiba
/
Qwen2-0.5B-Reward
like
0
transformers
tensorboard
safetensors
qwen2
text-classification
trl
reward-trainer
generated_from_trainer
Qwen/Qwen2-0.5B-Instruct
finetune
apache-2.0
autotrain_compatible
text-generation-inference
endpoints_compatible
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
Qwen2-0.5B-Reward
This model is a fine-tuned version of
Qwen/Qwen2-0.5B-Instruct
on an unknown dataset. It achieves the following results on the evaluation set:
Loss: 0.8210
Accuracy: 0.614
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: 8
eval_batch_size: 8
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 0.1
Training results
Training Loss
Epoch
Step
Validation Loss
Accuracy
1.27
0.04
50
1.0332
0.573
0.8568
0.08
100
0.8349
0.603
Framework versions
Transformers 4.45.2
Pytorch 2.5.0+cu124
Datasets 3.0.2
Tokenizers 0.20.1
