初始化项目,由ModelHub XC社区提供模型

Model: promotion/qwen3-8b-dpo-avg-beta0p05-s42
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-07-24 19:30:30 +08:00
commit 8bc779b4d2
22 changed files with 152912 additions and 0 deletions

9
train_results.json Normal file
View File

@@ -0,0 +1,9 @@
{
"epoch": 1.0,
"total_flos": 0.0,
"train_loss": 0.6846090351065545,
"train_runtime": 26441.528,
"train_samples": 18644,
"train_samples_per_second": 0.705,
"train_steps_per_second": 0.011
}