Qwen2.5-3B-Open-R1-GRPO/all_results.json

{
    "total_flos": 0.0,
    "train_loss": 0.00015187089497744325,
    "train_runtime": 1302.9313,
    "train_samples": 93733,
    "train_samples_per_second": 71.94,
    "train_steps_per_second": 2.249
}