Files
appworld_distillation_sft-S…/all_results.json
ModelHub XC 5d5e560dae 初始化项目,由ModelHub XC社区提供模型
Model: huseyinatahaninan/appworld_distillation_sft-SFT-Qwen3-4B-Instruct-2507
Source: Original Platform
2026-06-08 23:26:22 +08:00

12 lines
348 B
JSON

{
"epoch": 10.0,
"eval_loss": 0.25876814126968384,
"eval_runtime": 8.9435,
"eval_samples_per_second": 4.361,
"eval_steps_per_second": 0.559,
"total_flos": 3.3888284102885376e+17,
"train_loss": 0.3828152969479561,
"train_runtime": 594.2554,
"train_samples_per_second": 0.875,
"train_steps_per_second": 0.034
}