logical-reasoning / data /Qwen2.5-0.5B-Instruct-float16_shots_metrics.csv
dh-mc's picture
final few-shots
84958e4
shots,model,run,accuracy,precision,recall,f1,ratio_valid_classifications
0,Qwen2.5-0.5B-Instruct,Qwen/Qwen2.5-0.5B-Instruct/shots-00,0.43833333333333335,0.5292917259914629,0.43833333333333335,0.42286875992486556,0.594
5,Qwen2.5-0.5B-Instruct,Qwen/Qwen2.5-0.5B-Instruct/shots-05,0.17966666666666667,0.47516573853109806,0.17966666666666667,0.214144872117911,0.004
10,Qwen2.5-0.5B-Instruct,Qwen/Qwen2.5-0.5B-Instruct/shots-10,0.351,0.5084853117995367,0.351,0.39097839594031075,0.068
20,Qwen2.5-0.5B-Instruct,Qwen/Qwen2.5-0.5B-Instruct/shots-20,0.43366666666666664,0.513186330900278,0.43366666666666664,0.463747974034812,0.37266666666666665
30,Qwen2.5-0.5B-Instruct,Qwen/Qwen2.5-0.5B-Instruct/shots-30,0.39,0.5367753683204347,0.39,0.4299603249123421,0.07566666666666666
40,Qwen2.5-0.5B-Instruct,Qwen/Qwen2.5-0.5B-Instruct/shots-40,0.466,0.5400134144413437,0.466,0.49542975613961904,0.324
50,Qwen2.5-0.5B-Instruct,Qwen/Qwen2.5-0.5B-Instruct/shots-50,0.496,0.5465409839032335,0.496,0.5069942984615308,0.24333333333333335