evaluation_results.csv

eval_loss,eval_model_preparation_time,eval_accuracy,eval_RMSE,eval_QWK,eval_HDIV,eval_Macro_F1,eval_Micro_F1,eval_Weighted_F1,eval_TP_0,eval_TN_0,eval_FP_0,eval_FN_0,eval_TP_1,eval_TN_1,eval_FP_1,eval_FN_1,eval_TP_2,eval_TN_2,eval_FP_2,eval_FN_2,eval_TP_3,eval_TN_3,eval_FP_3,eval_FN_3,eval_TP_4,eval_TN_4,eval_FP_4,eval_FN_4,eval_TP_5,eval_TN_5,eval_FP_5,eval_FN_5,eval_runtime,eval_samples_per_second,eval_steps_per_second,epoch,reference,timestamp,id
1.90119206905365,0.0019,0.2803030303030303,65.78200914591106,0.020291060291060203,0.21212121212121215,0.07805907172995781,0.2803030303030303,0.14192558496355964,0,125,6,1,0,108,0,24,0,118,8,6,0,79,0,53,37,11,81,3,0,124,0,8,0.7319,180.364,12.298,-1,validation_before_training,2025-07-09 17:04:32,BERTugues-base-portuguese-cased-encoder_classification-C3-essay_only
1.6529216766357422,0.0019,0.4393939393939394,43.34498677803327,0.5384823603717406,0.045454545454545414,0.32197721633205506,0.4393939393939394,0.4213255952258885,0,131,0,1,2,108,0,22,6,108,18,0,24,63,16,29,21,65,27,19,5,111,13,3,0.3947,334.439,22.803,13.0,validation_after_training,2025-07-09 17:04:32,BERTugues-base-portuguese-cased-encoder_classification-C3-essay_only
2.0192933082580566,0.0019,0.36231884057971014,55.638585297552666,0.2865109794353433,0.09420289855072461,0.26051544019593825,0.36231884057971014,0.34754448627572954,0,135,2,1,3,100,9,26,10,102,18,8,18,63,30,27,18,78,22,20,1,124,7,6,0.3908,353.12,23.03,13.0,test_results,2025-07-09 17:04:32,BERTugues-base-portuguese-cased-encoder_classification-C3-essay_only