UWNSL/Qwen2.5-3B-Instruct_Short_CoT
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: UWNSL/Qwen2.5-3B-Instruct_Short_CoT
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-07-13 18:10:28 +08:00
commit a35b9234ce
21 changed files with 157691 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
all_results.json Normal file
View File

@@ -0,0 +1,12 @@
{
"epoch": 2.0,
"eval_loss": 0.13600705564022064,
"eval_runtime": 3.0073,
"eval_samples_per_second": 17.957,
"eval_steps_per_second": 4.655,
"total_flos": 12178659213312.0,
"train_loss": 0.07465152751130169,
"train_runtime": 886.8941,
"train_samples_per_second": 12.017,
"train_steps_per_second": 0.753
}