aq_bert_gaq_mt / eval_results.txt
anlausch's picture
Upload eval_results.txt
447f63c
cogency = {'mae': 0.51180685, 'mse': 0.43609676, 'pearsonr': 0.37778644378237336, 'pearsonp': 3.134744098208519e-41}
effectiveness = {'mae': 0.57646537, 'mse': 0.53637373, 'pearsonr': 0.43734952510864855, 'pearsonp': 3.6106714086480524e-56}
overall = {'mae': 0.54442376, 'mse': 0.4794784, 'pearsonr': 0.43281147859754376, 'pearsonp': 6.380852802761839e-55}
reasonableness = {'mae': 0.54984224, 'mse': 0.49801204, 'pearsonr': 0.4312355839717975, 'pearsonp': 1.7123600367088884e-54}