feedback-grpo-reasoning-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-grpo-feedback-sft-reasoning

This model is a fine-tuned version of formalmathatepfl/qwen3-sft-feedback-with-proof-repair-rl-125-unmasked on the lean_reasoning_sft_feedback 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: 8
• total_train_batch_size: 8
• total_eval_batch_size: 64
• 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: cosine
• lr_scheduler_warmup_ratio: 0.05
• num_epochs: 2.0

Training results

Framework versions

• Transformers 4.57.3
• Pytorch 2.9.0+cu128
• Datasets 4.0.0
• Tokenizers 0.22.2