Files
Qwen2.5-7B-Open-R1-GRPO-mat…/all_results.json
ModelHub XC 9f04346d79 初始化项目,由ModelHub XC社区提供模型
Model: Lansechen/Qwen2.5-7B-Open-R1-GRPO-math-lighteval-1epochstop-withformat
Source: Original Platform
2026-06-07 22:56:24 +08:00

8 lines
200 B
JSON

{
"total_flos": 0.0,
"train_loss": 0.02949339959234225,
"train_runtime": 14062.8623,
"train_samples": 7500,
"train_samples_per_second": 0.533,
"train_steps_per_second": 0.005
}