初始化项目,由ModelHub XC社区提供模型

Model: W-61/llama-3-8b-base-sft-hh-harmless-8xh200
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-04-24 11:28:52 +08:00
commit 9f1e640c36
20 changed files with 4007 additions and 0 deletions

9
train_results.json Normal file
View File

@@ -0,0 +1,9 @@
{
"epoch": 1.0,
"total_flos": 3.836373525279539e+16,
"train_loss": 1.9909558915174925,
"train_runtime": 382.237,
"train_samples": 42336,
"train_samples_per_second": 34.549,
"train_steps_per_second": 0.272
}