andstor/Qwen-Qwen2.5-Coder-14B-unit-test-prompt-tuning

output

This model is a fine-tuned version of Qwen/Qwen2.5-Coder-14B on the andstor/methods2test_small fm+fc+c+m+f+t+tc dataset. It achieves the following results on the evaluation set:

• Loss: 0.7242
• Accuracy: 0.7336

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: 0.003
• train_batch_size: 1
• eval_batch_size: 1
• seed: 42
• distributed_type: multi-GPU
• num_devices: 2
• gradient_accumulation_steps: 8
• total_train_batch_size: 16
• total_eval_batch_size: 2
• optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 3.0

Training results

Framework versions

• PEFT 0.15.2
• Transformers 4.56.2
• Pytorch 2.8.0+cu128
• Datasets 4.1.1
• Tokenizers 0.22.1