初始化项目,由ModelHub XC社区提供模型

Model: W-61/llama-3-8b-base-new-dpo-hh-helpful-4xh200-batch-64-q_t-0.45-eta-0.1-s_star-0.35-20260428-045924
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-05-26 11:34:17 +08:00
commit a01ae90d80
19 changed files with 19568 additions and 0 deletions

9
all_results.json Normal file
View File

@@ -0,0 +1,9 @@
{
"epoch": 1.0,
"total_flos": 0.0,
"train_loss": 1.1324475014612363,
"train_runtime": 1725.4575,
"train_samples": 43598,
"train_samples_per_second": 25.268,
"train_steps_per_second": 0.395
}