Qwen2.5-1.5B-Open-R1-GRPO / all_results.json
May811's picture
Model save
9afce01 verified
{
"total_flos": 0.0,
"train_loss": 0.06294877494734573,
"train_runtime": 428958.1793,
"train_samples": 72441,
"train_samples_per_second": 0.169,
"train_steps_per_second": 0.003
}