Files
Qwen3-4B-SFT-science-1e-5/train_results.json
ModelHub XC afd3adcaa1 初始化项目,由ModelHub XC社区提供模型
Model: graf/Qwen3-4B-SFT-science-1e-5
Source: Original Platform
2026-05-30 05:11:19 +08:00

8 lines
208 B
JSON

{
"epoch": 3.0,
"total_flos": 8.852766725217714e+18,
"train_loss": 0.6584745990833162,
"train_runtime": 19013.667,
"train_samples_per_second": 15.562,
"train_steps_per_second": 0.122
}