初始化项目,由ModelHub XC社区提供模型

Model: promotion/ronpo-qwen3-8b-fair-dpo-s42
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-07-18 16:12:11 +08:00
commit c5827a4516
18 changed files with 4248 additions and 0 deletions

9
all_results.json Normal file
View File

@@ -0,0 +1,9 @@
{
"epoch": 0.8599068434252956,
"total_flos": 0.0,
"train_loss": 0.7066660939322578,
"train_runtime": 7291.0823,
"train_samples": 16746,
"train_samples_per_second": 1.975,
"train_steps_per_second": 0.123
}