Qwen2.5-1.5B-Open-R1-GRPO / all_results.json
kppkkp's picture
End of training
6bb8ad7 verified
{
"eval_loss": 0.018681298941373825,
"eval_runtime": 92.7094,
"eval_samples": 99,
"eval_samples_per_second": 1.068,
"eval_steps_per_second": 0.011,
"total_flos": 0.0,
"train_loss": 0.040519028099076065,
"train_runtime": 54178.7039,
"train_samples": 72441,
"train_samples_per_second": 1.337,
"train_steps_per_second": 0.005
}