初始化项目,由ModelHub XC社区提供模型

Model: modrill/qwen3-4b-think-s1-ep23-full-sft
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-09-26 09:49:16 +08:00
commit 07a669f2ad
11 changed files with 457 additions and 0 deletions

8
train_results.json Normal file
View File

@@ -0,0 +1,8 @@
{
"epoch": 2.0,
"total_flos": 1116023864426496.0,
"train_loss": 0.5415504160306311,
"train_runtime": 61158.2606,
"train_samples_per_second": 0.631,
"train_steps_per_second": 0.01
}