lora-Qwen2-0.5B-Instruct_2025-05-28_00-37

• Loss: 2.2044

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

• learning_rate: 2e-05
• train_batch_size: 36
• eval_batch_size: 36
• seed: 42
• gradient_accumulation_steps: 20
• total_train_batch_size: 720
• 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: 10

Training results

Framework versions

• PEFT 0.15.1
• Transformers 4.50.2
• Pytorch 2.6.0+cu124
• Datasets 3.5.0
• Tokenizers 0.21.1