Files
Qwen2.5-1.5B-GRPO-v5/train_results.json
ModelHub XC 457e0cfd8d 初始化项目,由ModelHub XC社区提供模型
Model: dekangli/Qwen2.5-1.5B-GRPO-v5
Source: Original Platform
2026-08-21 08:47:18 +08:00

8 lines
189 B
JSON

{
"total_flos": 0.0,
"train_loss": 0.0,
"train_runtime": 1.9027,
"train_samples": 93733,
"train_samples_per_second": 197054.689,
"train_steps_per_second": 8209.473
}