初始化项目,由ModelHub XC社区提供模型

Model: leonMW/DeepSeek-R1-Distill-Qwen-7B-GSPO-Basic
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-04-26 01:09:06 +08:00
commit e72c3e4abd
17 changed files with 37106 additions and 0 deletions

8
train_results.json Normal file
View File

@@ -0,0 +1,8 @@
{
"total_flos": 0.0,
"train_loss": 0.10312542560923918,
"train_runtime": 114002.2359,
"train_samples": 3053,
"train_samples_per_second": 0.134,
"train_steps_per_second": 0.017
}