OpenRS-GRPO / all_results.json
jmkim89's picture
Model save
9360627 verified
{
"total_flos": 0.0,
"train_loss": 0.12157149085606943,
"train_runtime": 48026.4516,
"train_samples": 7000,
"train_samples_per_second": 0.75,
"train_steps_per_second": 0.01
}