初始化项目,由ModelHub XC社区提供模型

Model: jackf857/qwen3-8b-base-sft-ultrachat-4xh200-batch-128
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-07-22 21:02:26 +08:00
commit 120f806b99
23 changed files with 154864 additions and 0 deletions

9
train_results.json Normal file
View File

@@ -0,0 +1,9 @@
{
"epoch": 0.9994722955145119,
"total_flos": 2.8182891025525637e+18,
"train_loss": 1.100929617000608,
"train_runtime": 11309.6924,
"train_samples": 207864,
"train_samples_per_second": 10.721,
"train_steps_per_second": 0.084
}