初始化项目,由ModelHub XC社区提供模型

Model: W-61/llama-3-8b-base-sft-ultrachat-8xh200
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-05-09 12:48:29 +08:00
commit e9b9bc6186
19 changed files with 3967 additions and 0 deletions

9
train_results.json Normal file
View File

@@ -0,0 +1,9 @@
{
"epoch": 1.0,
"total_flos": 1.381094473127166e+18,
"train_loss": 1.105873676828849,
"train_runtime": 5784.2377,
"train_samples": 207864,
"train_samples_per_second": 20.701,
"train_steps_per_second": 0.162
}