Qwen2.5-1.5B-Open-R1-GRPO / train_results.json
schwamaths's picture
Model save
3964c9a verified
raw
history blame contribute delete
198 Bytes
{
"total_flos": 0.0,
"train_loss": 0.0029402809985185742,
"train_runtime": 7951.9567,
"train_samples": 891,
"train_samples_per_second": 1.12,
"train_steps_per_second": 0.01
}