初始化项目,由ModelHub XC社区提供模型

Model: modrill/qwen3-4b-think-baseline-full-sft
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-07-26 22:34:10 +08:00
commit 84ba2b4166
11 changed files with 493 additions and 0 deletions

8
train_results.json Normal file
View File

@@ -0,0 +1,8 @@
{
"epoch": 2.0,
"total_flos": 1548137571287040.0,
"train_loss": 0.6697529787664481,
"train_runtime": 98109.4565,
"train_samples_per_second": 0.546,
"train_steps_per_second": 0.009
}