---

language: en

rawpowertools/MH_5000T_L_Qwen2_500M_gguf Model Data

Base_Model: unsloth/Qwen2-0.5B

Training_Data: mh_5000_train

Eval_Input: mh_small_test

Merged_Model: rawpowertools/MH_5000T_L_Qwen2_500M

Epochs: 5

Rank: 32

Alpha: 32

LR: 0.0005

LR_Scheduler: linear

ClearML: http://clearml.rptinternal.com:8080/projects/d061c7fcfaa049b69a4ee1ff0ed89be2/experiments/91759c4e95344c31942f6b55b75ba9f9/output/log