初始化项目,由ModelHub XC社区提供模型

Model: W-61/qwen3-8b-base-margin-dpo-ultrafeedback-4xh200-batch-128-20260423-040315
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-06-01 09:31:36 +08:00
commit 27acccf3d4
501 changed files with 162734 additions and 0 deletions

9
train_results.json Normal file
View File

@@ -0,0 +1,9 @@
{
"epoch": 0.9989528795811519,
"total_flos": 0.0,
"train_loss": 4.779813265150698,
"train_runtime": 7822.2821,
"train_samples": 61135,
"train_samples_per_second": 7.815,
"train_steps_per_second": 0.061
}