Files
llama-3-8b-base-margin-dpo-…/train_results.json
ModelHub XC ae71885186 初始化项目,由ModelHub XC社区提供模型
Model: jackf857/llama-3-8b-base-margin-dpo-4xh100
Source: Original Platform
2026-05-10 13:57:42 +08:00

9 lines
233 B
JSON

{
"epoch": 0.9988221436984688,
"total_flos": 0.0,
"train_loss": 0.5765140090348586,
"train_runtime": 5442.9429,
"train_samples": 61135,
"train_samples_per_second": 11.232,
"train_steps_per_second": 0.088
}