Files
llama-3-8b-base-new-dpo-hh-…/all_results.json
ModelHub XC ff148490b3 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-q_t-0.45-s_star-0.4-eta-5
Source: Original Platform
2026-05-20 14:34:40 +08:00

9 lines
218 B
JSON

{
"epoch": 1.0,
"total_flos": 0.0,
"train_loss": 1.3263754091949014,
"train_runtime": 1741.0925,
"train_samples": 43598,
"train_samples_per_second": 25.041,
"train_steps_per_second": 0.391
}