openr1_codeforces / all_results.json
sedrickkeh's picture
End of training
3e6a223 verified
{
"epoch": 4.994492525570417,
"total_flos": 5.954272714247897e+18,
"train_loss": 0.5234080795045907,
"train_runtime": 72319.3947,
"train_samples_per_second": 2.811,
"train_steps_per_second": 0.022
}