Qwen2.5-1.5B-Open-R1-GRPO / all_results.json
taozihuahua's picture
End of training
73c5e9c verified
{
"eval_loss": 0.005393692292273045,
"eval_runtime": 46.3292,
"eval_samples": 99,
"eval_samples_per_second": 2.137,
"eval_steps_per_second": 0.022,
"total_flos": 0.0,
"train_loss": 0.011041131547906181,
"train_runtime": 4812.1769,
"train_samples": 72441,
"train_samples_per_second": 1.505,
"train_steps_per_second": 0.007
}