Qwen2.5-1.5B-Open-R1-GRPO / train_results.json
lzy337's picture
Model save
cb776e2 verified
raw
history blame contribute delete
199 Bytes
{
"total_flos": 0.0,
"train_loss": 2.2585060952830793,
"train_runtime": 36118.4141,
"train_samples": 72441,
"train_samples_per_second": 2.006,
"train_steps_per_second": 0.01
}