初始化项目,由ModelHub XC社区提供模型

Model: W-61/llama-3-8b-base-epsilon-dpo-hh-harmless-4xh200-batch-64-20260418-003215
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-06-13 14:08:31 +08:00
commit 121c6f2962
20 changed files with 22470 additions and 0 deletions

9
train_results.json Normal file
View File

@@ -0,0 +1,9 @@
{
"epoch": 0.999244142101285,
"total_flos": 0.0,
"train_loss": 1.1175190241903112,
"train_runtime": 3196.4458,
"train_samples": 42336,
"train_samples_per_second": 13.245,
"train_steps_per_second": 0.207
}