qwen3-4B-instruct-refiner-sft

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->

qwen3-4B-instruct-refiner-sft

This model is a fine-tuned version of Qwen/Qwen3-4B-Instruct-2507 on the refiner_sft_hard_filtered_train dataset. It achieves the following results on the evaluation set:

• Loss: 1.1232

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: 2
• eval_batch_size: 2
• seed: 42
• gradient_accumulation_steps: 16
• total_train_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: 0.05
• num_epochs: 5

Training results

Framework versions

• Transformers 4.52.4
• Pytorch 2.10.0+cu128
• Datasets 4.8.4
• Tokenizers 0.21.1