初始化项目,由ModelHub XC社区提供模型

Model: rl-rag/qwen3-8B-sft-mix-v20250921-plus-v20251001-onpolicy-rs-longform_0921
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-06-26 16:23:11 +08:00
commit 548bbcc0ee
22 changed files with 152545 additions and 0 deletions

8
train_results.json Normal file
View File

@@ -0,0 +1,8 @@
{
"epoch": 5.0,
"total_flos": 274293220966400.0,
"train_loss": 0.3892772012286716,
"train_runtime": 9724.0454,
"train_samples_per_second": 1.139,
"train_steps_per_second": 0.009
}