W-61/llama-3-8b-base-new-dpo-hh-helpful-4xh200-batch-64-s_star-0.4-eta-0.1-q_t-0.48
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: W-61/llama-3-8b-base-new-dpo-hh-helpful-4xh200-batch-64-s_star-0.4-eta-0.1-q_t-0.48
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-05-26 11:58:18 +08:00
commit 4d19c05e0b
18 changed files with 18269 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": 1.0,
"total_flos": 0.0,
"train_loss": 1.0968060302664355,
"train_runtime": 1742.1859,
"train_samples": 43598,
"train_samples_per_second": 25.025,
"train_steps_per_second": 0.391
}