初始化项目,由ModelHub XC社区提供模型

Model: jayzou3773/Qwen1.5-MOE-sft-ESFT-intent
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-05-15 09:11:48 +08:00
commit 22aa64164f
22 changed files with 160219 additions and 0 deletions

8
train_results.json Normal file
View File

@@ -0,0 +1,8 @@
{
"total_flos": 1.0952542154391552e+17,
"train_loss": 0.13070940664814165,
"train_runtime": 1765.7438,
"train_samples": 7280,
"train_samples_per_second": 8.246,
"train_steps_per_second": 0.258
}