Qwen2.5-1.5B-Open-R1-GRPO / train_results.json
taozihuahua's picture
Model save
44254b8 verified
{
"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
}