willccbb

# train_grpo.py
#
# See https://github.com/willccbb/verifiers for ongoing developments
#
"""
citation:

@misc{brown2025grpodemo,
  title={Granular Format Rewards for Eliciting Mathematical Reasoning Capabilities in Small Language Models},
  author={Brown, William},

makinde

!function() {
  var doc     = document,
      htm     = doc.documentElement,
      lct     = null,   // last click target                                              
      nearest = function(elm, tag) {
        while (elm && elm.nodeName != tag) {
          elm = elm.parentNode;
        }
        return elm;
  };