初始化项目,由ModelHub XC社区提供模型

Model: promotion/qwen3-8b-aaai27-p3-ronpo-alpha050_anchor0035_lr7p5e8-s42
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-07-22 04:24:16 +08:00
commit 5228db97cc
13 changed files with 5250 additions and 0 deletions

9
train_results.json Normal file
View File

@@ -0,0 +1,9 @@
{
"epoch": 0.2860548271752086,
"total_flos": 0.0,
"train_loss": 0.4220078429910872,
"train_runtime": 7042.2326,
"train_samples": 50340,
"train_samples_per_second": 2.045,
"train_steps_per_second": 0.128
}