初始化项目,由ModelHub XC社区提供模型

Model: jackf857/qwen3-8b-base-simpo-ultrafeedback-4xH200-batch-128
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-05-16 14:41:21 +08:00
commit 24073ff9d6
22 changed files with 153108 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": 9.188309121681709,
"train_runtime": 5401.7608,
"train_samples": 61135,
"train_samples_per_second": 11.318,
"train_steps_per_second": 0.088
}