初始化项目,由ModelHub XC社区提供模型

Model: W-61/llama3-8b-dpo-4xh100-pilot
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-04-11 08:56:01 +08:00
commit 0ae0a8b0c9
20 changed files with 2877 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": 0.6806982485360877,
"train_runtime": 636.997,
"train_samples": 5501,
"train_samples_per_second": 8.636,
"train_steps_per_second": 0.135
}