Qwen3-8B-Chess-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. -->

Model description

This model is the SFT stage two model of paper https://arxiv.org/abs/2509.24239.

Training and evaluation data

Training dataset: https://huggingface.co/datasets/ljcnju/ChessArena_Training_Dataset

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 5e-06
• 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 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 4.52.4
• Pytorch 2.8.0+cu128
• Datasets 3.6.0
• Tokenizers 0.21.1