初始化项目,由ModelHub XC社区提供模型

Model: formalmathatepfl/qwen3-8b-sft
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-05-28 10:47:21 +08:00
commit b37738bbeb
24 changed files with 156262 additions and 0 deletions

8
train_results.json Normal file
View File

@@ -0,0 +1,8 @@
{
"epoch": 1.0,
"total_flos": 3995069728161792.0,
"train_loss": 0.10921624170816473,
"train_runtime": 69121.8578,
"train_samples_per_second": 0.955,
"train_steps_per_second": 0.068
}