Qwen2.5-1.5B-Open-R1-Code-GRPO / all_results.json
CM's picture
Model save
fa33b89 verified
{
"total_flos": 0.0,
"train_loss": 0.059448377258595884,
"train_runtime": 22252.9361,
"train_samples": 1800,
"train_samples_per_second": 1.258,
"train_steps_per_second": 0.022
}