Files
llama-3-8b-base-new-dpo-hh-…/all_results.json
ModelHub XC 4a3ecef1ee 初始化项目,由ModelHub XC社区提供模型
Model: W-61/llama-3-8b-base-new-dpo-hh-helpful-4xh200-batch-64-s_star-0.4-eta-0.1-q_t-0.43
Source: Original Platform
2026-05-13 20:03:24 +08:00

9 lines
218 B
JSON

{
"epoch": 1.0,
"total_flos": 0.0,
"train_loss": 1.1157032691609667,
"train_runtime": 1740.0089,
"train_samples": 43598,
"train_samples_per_second": 25.056,
"train_steps_per_second": 0.391
}