初始化项目,由ModelHub XC社区提供模型

Model: jackf857/qwen-3-8b-base-r-dpo-ultrafeedback-4xH200-batch-128-rerun-2-runpod
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-05-09 21:14:25 +08:00
commit a1e826d8db
22 changed files with 153214 additions and 0 deletions

9
train_results.json Normal file
View File

@@ -0,0 +1,9 @@
{
"epoch": 0.9989528795811519,
"total_flos": 0.0,
"train_loss": 17.04746322311945,
"train_runtime": 7166.7787,
"train_samples": 61135,
"train_samples_per_second": 8.53,
"train_steps_per_second": 0.067
}