初始化项目,由ModelHub XC社区提供模型

Model: edbeeching/Qwen3-4B-Thinking-2507-SFT-tr5
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-06-20 17:34:31 +08:00
commit ace6e29fbe
12 changed files with 5322 additions and 0 deletions

9
train_results.json Normal file
View File

@@ -0,0 +1,9 @@
{
"epoch": 4.6268656716417915,
"total_flos": 829282868854784.0,
"train_loss": 0.02679153286641644,
"train_runtime": 1845.6941,
"train_samples": 4281,
"train_samples_per_second": 10.749,
"train_steps_per_second": 0.336
}