Files
llama-3-8b-base-margin-dpo-…/train_results.json
ModelHub XC e2d7fad87f 初始化项目,由ModelHub XC社区提供模型
Model: jackf857/llama-3-8b-base-margin-dpo-hh-helpful-batch-64
Source: Original Platform
2026-05-10 12:37:20 +08:00

9 lines
217 B
JSON

{
"epoch": 1.0,
"total_flos": 0.0,
"train_loss": 0.572698849610295,
"train_runtime": 1998.3785,
"train_samples": 43598,
"train_samples_per_second": 21.817,
"train_steps_per_second": 0.341
}