qwen3-4b-refiner-codeql-self-nothink-full

This model is a fine-tuned version of Qwen/Qwen3-4B on the /data/better_refiner/codeql/qwen3_nothink/full dataset. It achieves the following results on the evaluation set:

• Loss: 0.3477

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: 2e-05
• train_batch_size: 1
• eval_batch_size: 1
• seed: 42
• distributed_type: multi-GPU
• num_devices: 8
• gradient_accumulation_steps: 4
• total_train_batch_size: 32
• total_eval_batch_size: 8
• optimizer: Use 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

Training results

Training Loss	Epoch	Step	Validation Loss
0.335	1.0	524	0.3371
0.2533	2.0	1048	0.3244
0.1747	3.0	1572	0.3477

Framework versions

• Transformers 4.53.0
• Pytorch 2.7.1+cu126
• Datasets 3.6.0
• Tokenizers 0.21.2