Files
llama-3-8b-base-new-dpo-hh-…/all_results.json
ModelHub XC acb095f22e 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-0.01
Source: Original Platform
2026-06-01 08:08:16 +08:00

9 lines
218 B
JSON

{
"epoch": 1.0,
"total_flos": 0.0,
"train_loss": 0.9659692127799148,
"train_runtime": 1735.4678,
"train_samples": 43598,
"train_samples_per_second": 25.122,
"train_steps_per_second": 0.392
}