Qwen2.5-1.5B-Open-R1-Code-GRPO / all_results.json
Blancy's picture
Model save
6947641 verified
{
"total_flos": 0.0,
"train_loss": 0.008756054809940243,
"train_runtime": 191583.7312,
"train_samples": 15068,
"train_samples_per_second": 1.169,
"train_steps_per_second": 0.003
}