Qwen2.5-1.5B-Open-R1-Code-GRPO / all_results.json
AmberYifan's picture
Model save
80fa5df verified
{
"total_flos": 0.0,
"train_loss": 0.003590845608123345,
"train_runtime": 14235.1126,
"train_samples": 35735,
"train_samples_per_second": 2.248,
"train_steps_per_second": 0.035
}