初始化项目,由ModelHub XC社区提供模型

Model: jackf857/llama-3-8b-base-margin-dpo-hh-4xh100
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-04-24 16:00:00 +08:00
commit d238cc8b5c
18 changed files with 3612 additions and 0 deletions

9
train_results.json Normal file
View File

@@ -0,0 +1,9 @@
{
"epoch": 0.9977324263038548,
"total_flos": 0.0,
"train_loss": 4.569111451235685,
"train_runtime": 1865.9225,
"train_samples": 42336,
"train_samples_per_second": 22.689,
"train_steps_per_second": 0.177
}