初始化项目,由ModelHub XC社区提供模型

Model: vukien2301/llama-3.1-8b-ultrafeedback-dpo-from-epoch1
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-06-05 12:06:16 +08:00
commit 7a74f79f49
16 changed files with 6446 additions and 0 deletions

9
all_results.json Normal file
View File

@@ -0,0 +1,9 @@
{
"epoch": 1.0,
"total_flos": 0.0,
"train_loss": 0.5733826223727876,
"train_runtime": 2164.3688,
"train_samples": 57673,
"train_samples_per_second": 26.647,
"train_steps_per_second": 0.104
}