21 lines
571 B
JSON
21 lines
571 B
JSON
|
{
|
||
|
|
"method": "gkd",
|
||
|
|
"student_model": "Qwen/Qwen2.5-3B-Instruct",
|
||
|
|
"teacher_model": "Qwen/Qwen2-7B-Instruct",
|
||
|
|
"train_dataset": "EleutherAI/hendrycks_math/all",
|
||
|
|
"eval_dataset": "HuggingFaceH4/MATH-500",
|
||
|
|
"train_samples": 7500,
|
||
|
|
"eval_samples": 500,
|
||
|
|
"beta": 0.5,
|
||
|
|
"max_steps": 800,
|
||
|
|
"num_epochs": 1.0,
|
||
|
|
"lr": 2e-06,
|
||
|
|
"batch_size": 1,
|
||
|
|
"grad_accum": 8,
|
||
|
|
"output_dir": "gkd_math500_S-Qwen2.5-3B-Instruct_T-Qwen2-7B-Instruct_20260420_154438",
|
||
|
|
"use_lora": false,
|
||
|
|
"lora_r": null,
|
||
|
|
"lora_alpha": null,
|
||
|
|
"lora_dropout": null,
|
||
|
|
"lora_target_modules": null
|
||
|
|
}
|