Files
mistral-7b-base-epsilon-dpo…/train_results.json
ModelHub XC 0fcf19d1a3 初始化项目,由ModelHub XC社区提供模型
Model: W-61/mistral-7b-base-epsilon-dpo-hh-helpful-4xh200-batch-64
Source: Original Platform
2026-04-22 12:22:48 +08:00

9 lines
218 B
JSON

{
"epoch": 1.0,
"total_flos": 0.0,
"train_loss": 0.6833117403385398,
"train_runtime": 3053.5655,
"train_samples": 43598,
"train_samples_per_second": 14.278,
"train_steps_per_second": 0.223
}