初始化项目,由ModelHub XC社区提供模型

Model: jackf857/qwen3-8b-base-epsilon-dpo-hh-harmless-4xh200-batch-64
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-05-26 01:10:34 +08:00
commit 6dfe4c8f03
22 changed files with 170392 additions and 0 deletions

9
train_results.json Normal file
View File

@@ -0,0 +1,9 @@
{
"epoch": 0.999244142101285,
"total_flos": 0.0,
"train_loss": 1.1906072249390895,
"train_runtime": 2288.3837,
"train_samples": 42336,
"train_samples_per_second": 18.5,
"train_steps_per_second": 0.289
}