formalmathatepfl/classic-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. -->

grpo-classic-qwen3-cpt-lean-sft-reasoning

This model is a fine-tuned version of formalmathatepfl/qwen3-8b-classic-grpo on the leanreasoningsft 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
• —trainbatchsize: 1
• —evalbatchsize: 8
• —seed: 42
• —distributed_type: multi-GPU
• —num_devices: 8
• —totaltrainbatch_size: 8
• —totalevalbatch_size: 64
• —optimizer: Use OptimizerNames.ADAMWTORCHFUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• —lrschedulertype: cosine
• —lrschedulerwarmup_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