Qwen2.5-1.5B-Open-R1-Code-GRPO / train_results.json
chansung's picture
Model save
feb3789 verified
raw
history blame contribute delete
203 Bytes
{
"total_flos": 0.0,
"train_loss": 0.0025880077524270744,
"train_runtime": 10060.4286,
"train_samples": 131188,
"train_samples_per_second": 3.976,
"train_steps_per_second": 0.05
}