Qwen2.5-1.5B-Open-R1-Code-GRPO/train_results.json

{
    "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
}