• Model creator: https://huggingface.co/lchen915/
• Original model: https://huggingface.co/lchen915/Qwen2-0.5B-SFT/

Original model description:

• trl
• sft
• generated_from_trainer datasets:
• generator model-index:
• name: Qwen2-0.5B-SFT results: []

---

Qwen2-0.5B-SFT

• Loss: 1.5691

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

• learning_rate: 2e-05
• train_batch_size: 2
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 8
• total_train_batch_size: 16
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 1.0

Training results

Framework versions

• Transformers 4.46.2
• Pytorch 2.4.1+cu121
• Datasets 3.1.0
• Tokenizers 0.20.3