初始化项目,由ModelHub XC社区提供模型

Model: promotion/qwen3-8b-ronpo-full-expect-s42
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-07-29 01:20:10 +08:00
commit 27ea6f94f0
14 changed files with 765 additions and 0 deletions

9
train_results.json Normal file
View File

@@ -0,0 +1,9 @@
{
"epoch": 0.06652991073903643,
"total_flos": 0.0,
"train_loss": 1.094520975748698,
"train_runtime": 689.8738,
"train_samples": 18037,
"train_samples_per_second": 1.739,
"train_steps_per_second": 0.109
}