Files
Qwen2.5-3B-Open-R1-GRPO/train_results.json

8 lines
203 B
JSON
Raw Permalink Normal View History

{
"total_flos": 0.0,
"train_loss": 0.00015187089497744325,
"train_runtime": 1302.9313,
"train_samples": 93733,
"train_samples_per_second": 71.94,
"train_steps_per_second": 2.249
}