初始化项目,由ModelHub XC社区提供模型

Model: NarendraK1/Qwen2.5-1.5B-Open-R1-Distill
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-09-21 16:54:28 +08:00
commit 46429eb692
16 changed files with 155032 additions and 0 deletions

8
train_results.json Normal file
View File

@@ -0,0 +1,8 @@
{
"total_flos": 1146505946202112.0,
"train_loss": 0.522347574165645,
"train_runtime": 14437.3811,
"train_samples": 93733,
"train_samples_per_second": 6.492,
"train_steps_per_second": 0.135
}