Qwen2.5-1.5B-Open-R1-GRPO / train_results.json
chenggong
Model save
470bd99 verified
raw
history blame contribute delete
199 Bytes
{
"total_flos": 0.0,
"train_loss": 0.0012107762740924954,
"train_runtime": 306.1607,
"train_samples": 100,
"train_samples_per_second": 0.653,
"train_steps_per_second": 0.013
}