Qwen3-Codeforces-GRPO / train_results.json
yarin-shaked's picture
Model save
2b23d24 verified
{
"total_flos": 0.0,
"train_loss": 0.0,
"train_runtime": 1.5617,
"train_samples": 16676,
"train_samples_per_second": 10.245,
"train_steps_per_second": 0.64
}