Qwen2.5-1.5B-Open-R1-GRPO / all_results.json
schwamaths's picture
End of training
cb3c595 verified
raw
history blame contribute delete
363 Bytes
{
"eval_loss": 0.012486881576478481,
"eval_runtime": 79.6968,
"eval_samples": 223,
"eval_samples_per_second": 2.798,
"eval_steps_per_second": 0.1,
"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
}