初始化项目,由ModelHub XC社区提供模型

Model: yuerxin/DeepSeek-R1-Distill-Qwen-1.5B-GRPO
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-05-30 02:44:18 +08:00
commit d1d83abf72
13 changed files with 3430 additions and 0 deletions

8
all_results.json Normal file
View File

@@ -0,0 +1,8 @@
{
"total_flos": 0.0,
"train_loss": 0.0464448650211034,
"train_runtime": 1230.2242,
"train_samples": 100,
"train_samples_per_second": 0.081,
"train_steps_per_second": 0.081
}