Files
llama3-8b-full-pretrain-was…/train_results.json
ModelHub XC 368ad2ab8c 初始化项目,由ModelHub XC社区提供模型
Model: shuoxing/llama3-8b-full-pretrain-wash-c4-2-1m-bs4
Source: Original Platform
2026-06-12 17:17:17 +08:00

8 lines
200 B
JSON

{
"epoch": 3.0,
"total_flos": 8949330124800.0,
"train_loss": 1.6578803809801559,
"train_runtime": 3829.0681,
"train_samples_per_second": 3.476,
"train_steps_per_second": 0.87
}