Files
llama-3-8b-base-new-dpo-hh-…/train_results.json
ModelHub XC 89b1c23d07 初始化项目,由ModelHub XC社区提供模型
Model: W-61/llama-3-8b-base-new-dpo-hh-harmless-4xh200-batch-64-q_t-0.45-s_star-0.4-eta-0.3
Source: Original Platform
2026-06-01 07:20:16 +08:00

9 lines
232 B
JSON

{
"epoch": 0.999244142101285,
"total_flos": 0.0,
"train_loss": 1.1683954546924078,
"train_runtime": 1648.9587,
"train_samples": 42336,
"train_samples_per_second": 25.674,
"train_steps_per_second": 0.401
}