Files
gkd_gsm8k_S-Qwen2-1.5B-Inst…/run_config.json
ModelHub XC dee121ea07 初始化项目,由ModelHub XC社区提供模型
Model: QpiEImitation/gkd_gsm8k_S-Qwen2-1.5B-Instruct_T-Qwen2-7B-Instruct
Source: Original Platform
2026-06-16 06:27:16 +08:00

20 lines
500 B
JSON

{
"method": "gkd",
"student_model": "Qwen/Qwen2-1.5B-Instruct",
"teacher_model": "Qwen/Qwen2-7B-Instruct",
"dataset": "gsm8k/main",
"train_samples": 2000,
"eval_samples": 256,
"beta": 0.5,
"max_steps": 800,
"num_epochs": 1.0,
"lr": 2e-06,
"batch_size": 1,
"grad_accum": 8,
"output_dir": "gkd_gsm8k_S-Qwen2-1.5B-Instruct_T-Qwen2-7B-Instruct_20260420_154424",
"use_lora": false,
"lora_r": null,
"lora_alpha": null,
"lora_dropout": null,
"lora_target_modules": null
}