Qwen2.5-1.5B-Open-R1-Code-GRPO / all_results.json
MinhPhuoc's picture
Model save
1ad2387 verified
{
"total_flos": 0.0,
"train_loss": 0.00023389634034174379,
"train_runtime": 1466.2797,
"train_samples": 35735,
"train_samples_per_second": 0.082,
"train_steps_per_second": 0.007
}