初始化项目,由ModelHub XC社区提供模型

Model: jackf857/llama-3-8b-base-margin-dpo-hh-helpful-batch-64
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-05-10 12:37:20 +08:00
commit e2d7fad87f
19 changed files with 16414 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": 0.572698849610295,
"train_runtime": 1998.3785,
"train_samples": 43598,
"train_samples_per_second": 21.817,
"train_steps_per_second": 0.341
}