初始化项目,由ModelHub XC社区提供模型

Model: hahayhe/DReP-SFT-Qwen3-4B-Thinking-2507
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-08-02 18:35:18 +08:00
commit 0ad9c1ff06
20 changed files with 159022 additions and 0 deletions

8
train_results.json Normal file
View File

@@ -0,0 +1,8 @@
{
"epoch": 4.0,
"total_flos": 2.006101437057283e+19,
"train_loss": 0.5864963867131946,
"train_runtime": 153073.7159,
"train_samples_per_second": 0.687,
"train_steps_per_second": 0.005
}