logical-reasoning / data /Qwen2-72B-Instruct_shots_metrics.csv
dh-mc's picture
ready to run 10-shots for 70/72B models
809e98c
raw
history blame
228 Bytes
shots,model,run,accuracy,precision,recall,f1,ratio_valid_classifications
0,Qwen2-72B-Instruct,Qwen/Qwen2-72B-Instruct_torch/shots-00,0.7516666666666667,0.7949378981748352,0.7516666666666667,0.7572499605227642,0.9773333333333334