初始化项目,由ModelHub XC社区提供模型

Model: leonMW/DeepSeek-R1-Distill-Qwen-1.5B-GSPO-Basic
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-05-29 00:44:31 +08:00
commit 5ba183ae8d
13 changed files with 36750 additions and 0 deletions

8
all_results.json Normal file
View File

@@ -0,0 +1,8 @@
{
"total_flos": 0.0,
"train_loss": 0.013345611529686698,
"train_runtime": 16054.0136,
"train_samples": 3053,
"train_samples_per_second": 0.951,
"train_steps_per_second": 0.118
}