Files
DRA-DR_GRPO/train_results.json
ModelHub XC d889a5ea5a 初始化项目,由ModelHub XC社区提供模型
Model: kangdawei/DRA-DR_GRPO
Source: Original Platform
2026-05-22 11:25:17 +08:00

8 lines
201 B
JSON

{
"total_flos": 0.0,
"train_loss": 0.007517670260873274,
"train_runtime": 53153.3665,
"train_samples": 7000,
"train_samples_per_second": 0.452,
"train_steps_per_second": 0.009
}