初始化项目,由ModelHub XC社区提供模型

Model: W-61/llama-3-8b-base-sft-hh-helpful-8xh200
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-04-24 12:05:40 +08:00
commit cda0f8938a
20 changed files with 4053 additions and 0 deletions

9
train_results.json Normal file
View File

@@ -0,0 +1,9 @@
{
"epoch": 1.0,
"total_flos": 4.795466914988032e+16,
"train_loss": 1.8291644793290358,
"train_runtime": 404.0129,
"train_samples": 43598,
"train_samples_per_second": 40.88,
"train_steps_per_second": 0.322
}