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

{
    "total_flos": 0.0,
    "train_loss": 1.7066374281421304,
    "train_runtime": 5498.7014,
    "train_samples": 11300,
    "train_samples_per_second": 2.055,
    "train_steps_per_second": 0.004
}