jackf857/llama-3-8b-base-margin-dpo-4xh100
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: jackf857/llama-3-8b-base-margin-dpo-4xh100
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-05-10 13:57:42 +08:00
commit ae71885186
18 changed files with 414604 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
train_results.json Normal file
View File

@@ -0,0 +1,9 @@
{
"epoch": 0.9988221436984688,
"total_flos": 0.0,
"train_loss": 0.5765140090348586,
"train_runtime": 5442.9429,
"train_samples": 61135,
"train_samples_per_second": 11.232,
"train_steps_per_second": 0.088
}