24 lines
615 B
JSON
24 lines
615 B
JSON
|
{
|
||
|
|
"job_type": "kd_black_box_api",
|
||
|
|
"dataset": {
|
||
|
|
"labeled_path": "distil_qwen_thoughtX.json",
|
||
|
|
"template" : "chat_template_kd.jinja",
|
||
|
|
"seed": 42
|
||
|
|
},
|
||
|
|
"models": {
|
||
|
|
"student": "model/Qwen/Qwen2.5-1.5B-Instruct/"
|
||
|
|
},
|
||
|
|
"training": {
|
||
|
|
"output_dir": "result/",
|
||
|
|
"num_train_epochs": 3,
|
||
|
|
"per_device_train_batch_size": 1,
|
||
|
|
"gradient_accumulation_steps": 8,
|
||
|
|
"max_length":4096,
|
||
|
|
"save_steps": 1000,
|
||
|
|
"logging_steps": 1,
|
||
|
|
"learning_rate": 2e-5,
|
||
|
|
"weight_decay": 0.05,
|
||
|
|
"warmup_ratio": 0.1,
|
||
|
|
"lr_scheduler_type": "cosine"
|
||
|
|
}
|
||
|
|
}
|