Files
llama-3-8b-base-new-dpo-hh-…/train_results.json
ModelHub XC 58012c8d13 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-s_star-0.4-eta-0.1-q_t-0.4
Source: Original Platform
2026-06-01 07:43:16 +08:00

9 lines
231 B
JSON

{
"epoch": 0.999244142101285,
"total_flos": 0.0,
"train_loss": 1.1812428684169693,
"train_runtime": 1648.6054,
"train_samples": 42336,
"train_samples_per_second": 25.68,
"train_steps_per_second": 0.401
}