Files
llama-3-8b-base-epsilon-dpo…/train_results.json
ModelHub XC 121c6f2962 初始化项目,由ModelHub XC社区提供模型
Model: W-61/llama-3-8b-base-epsilon-dpo-hh-harmless-4xh200-batch-64-20260418-003215
Source: Original Platform
2026-06-13 14:08:31 +08:00

9 lines
232 B
JSON

{
"epoch": 0.999244142101285,
"total_flos": 0.0,
"train_loss": 1.1175190241903112,
"train_runtime": 3196.4458,
"train_samples": 42336,
"train_samples_per_second": 13.245,
"train_steps_per_second": 0.207
}