Files
HT-ht-analysis-Qwen-instruc…/all_results.json
ModelHub XC 2c9e4ba4c0 初始化项目,由ModelHub XC社区提供模型
Model: ShourenWSR/HT-ht-analysis-Qwen-instruct-no-think-only
Source: Original Platform
2026-06-07 18:08:19 +08:00

8 lines
203 B
JSON

{
"epoch": 3.0,
"total_flos": 154685539491840.0,
"train_loss": 0.3971013587030393,
"train_runtime": 54304.2861,
"train_samples_per_second": 4.076,
"train_steps_per_second": 0.17
}