Qwen2.5-1.5B-Open-R1-GRPO-math-v1/train_results.json

{
    "total_flos": 0.0,
    "train_loss": 0.003398028112404372,
    "train_runtime": 273585.6306,
    "train_samples_per_second": 1.028,
    "train_steps_per_second": 0.006
}