初始化项目,由ModelHub XC社区提供模型

Model: W-61/qwen3-8b-base-kto-ultrafeedback-4xh200-batch-128
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-06-09 14:29:38 +08:00
commit 843cd5af24
28 changed files with 153774 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": 1.4430672781629712,
"train_runtime": 11696.6719,
"train_samples": 122270,
"train_samples_per_second": 10.453,
"train_steps_per_second": 0.082
}