language: en
rawpowertools/MH_250T_L_Qwen2_500M Model Data
Base_Model: unsloth/Qwen2-0.5B
Training_Data: mh_250_train
Eval_Input: mh_small_test
Epochs: 5
Rank: 32
Alpha: 32
LR: 0.0005
LR_Scheduler: linear
ClearML: http://clearml.rptinternal.com:8080/projects/d061c7fcfaa049b69a4ee1ff0ed89be2/experiments/beb81b4f2f9b402b92f65791f6c8917e/output/log
