Files
llama-3-8b-base-margin-dpo-…/train_results.json
ModelHub XC 2c77b1ba39 初始化项目,由ModelHub XC社区提供模型
Model: W-61/llama-3-8b-base-margin-dpo-hh-helpful-4xh200-batch-64-20260417-212312
Source: Original Platform
2026-05-29 00:58:20 +08:00

9 lines
217 B
JSON

{
"epoch": 1.0,
"total_flos": 0.0,
"train_loss": 0.5730435011495403,
"train_runtime": 3273.0613,
"train_samples": 43598,
"train_samples_per_second": 13.32,
"train_steps_per_second": 0.208
}