logbook-files/outputs/analysis/model_metrics.csv

model_key,hf_id,examples,original_accuracy,original_ci_low,original_ci_high,mean_capped_accuracy,mean_capped_ci_low,mean_capped_ci_high,invalid_rate,strict_invalid_rate_original,strict_invalid_rate_capped,fallback_invalid_rate_original,fallback_invalid_rate_capped,fallback_original_accuracy,fallback_mean_capped_accuracy,fallback_returns_reference_on_capped_rate,parser_disagreement_rate,capped_accuracy_published,fallback_capped_accuracy_published,capped_accuracy_synthetic_202601,fallback_capped_accuracy_synthetic_202601,capped_accuracy_synthetic_202602,fallback_capped_accuracy_synthetic_202602
qwen2.5-0.5b,Qwen/Qwen2.5-0.5B-Instruct,1319,0.09097801364670205,0.0758150113722517,0.1068991660348749,0.0032853171594642403,0.0010108668182966893,0.006065200909780136,0.7672479150871873,0.8165276724791509,0.7672479150871873,0.0,0.000758150113722517,0.41470811220621684,0.01592115238817286,0.37907505686125853,0.7915087187263078,0.002274450341167551,0.015163002274450341,0.0037907505686125853,0.014404852160727824,0.0037907505686125853,0.01819560272934041
qwen2.5-1.5b,Qwen/Qwen2.5-1.5B-Instruct,1319,0.0,0.0,0.0,0.0005054334091483447,0.0,0.001516300227445034,0.9962092494313874,0.9992418498862775,0.9962092494313874,0.0,0.0,0.6732373009855952,0.03462218852666161,0.5951478392721758,0.9977255496588324,0.0,0.03184230477634572,0.000758150113722517,0.037149355572403335,0.000758150113722517,0.034874905231235785