Files
llama3-8b-full-pretrain-was…/all_results.json
ModelHub XC 2f01fa7de3 初始化项目,由ModelHub XC社区提供模型
Model: shuoxing/llama3-8b-full-pretrain-wash-c4-3-6m-bs4
Source: Original Platform
2026-06-12 17:03:27 +08:00

8 lines
202 B
JSON

{
"epoch": 3.0,
"total_flos": 15197432340480.0,
"train_loss": 1.6582482910574172,
"train_runtime": 6482.0567,
"train_samples_per_second": 3.524,
"train_steps_per_second": 0.881
}