初始化项目,由ModelHub XC社区提供模型

Model: promotion/ronpo-qwen3-8b-fair-ronpo-full-expect-s42
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-07-18 11:54:12 +08:00
commit aac32a2b1a
18 changed files with 5506 additions and 0 deletions

9
train_results.json Normal file
View File

@@ -0,0 +1,9 @@
{
"epoch": 0.2860548271752086,
"total_flos": 0.0,
"train_loss": 0.430257171690464,
"train_runtime": 7318.8237,
"train_samples": 50340,
"train_samples_per_second": 1.968,
"train_steps_per_second": 0.123
}