secmlr/SWE-BENCH-5k-first-2000-claude-search-replace-generation-qwen_3_14b

SWE-BENCH-5k-first-2000-claude-search-replace-generation_qwen_3_14b

This model is a fine-tuned version of Qwen/Qwen3-14B on the SWE-BENCH-5k-first-2000-claude-search-replace-generation dataset.

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: 1
• eval_batch_size: 8
• seed: 42
• distributed_type: multi-GPU
• num_devices: 4
• gradient_accumulation_steps: 12
• total_train_batch_size: 48
• total_eval_batch_size: 32
• 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_ratio: 0.1
• num_epochs: 3.0

Training results

Framework versions

• Transformers 4.51.3
• Pytorch 2.5.1+cu124
• Datasets 2.21.0
• Tokenizers 0.21.0