初始化项目,由ModelHub XC社区提供模型

Model: shubhamrgandhi/qwen3-8b-full-sft-prm-opus-distill-32k-lr5e6-flattened
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-06-18 18:29:20 +08:00
commit ceba279c82
25 changed files with 152975 additions and 0 deletions

8
train_results.json Normal file
View File

@@ -0,0 +1,8 @@
{
"epoch": 3.0,
"total_flos": 6.988388070252872e+17,
"train_loss": 0.41709409590923424,
"train_runtime": 37712.5646,
"train_samples_per_second": 0.14,
"train_steps_per_second": 0.018
}