Deberta-Finetuning-Results

F1 Scores of different configurations of Deberta

@kaggle.jarvisai7_deberta_finetuning_results

Table List

1 table(16 KB)

Deberta Finetuning

@kaggle.jarvisai7_deberta_finetuning_results.deberta_finetuning

16 KB
16 rows
20 columns

unnamed_0 Unnamed: 0	accumulation ACCUMULATION	batch BATCH	epochs EPOCHS	threshold THRESHOLD	effective_batch Effective Batch	f1_fold_0 F1 Fold 0	f1_fold_1 F1 Fold 1	f1_fold_2 F1 Fold 2	f1_fold_3 F1 Fold 3	mean_f1 Mean F1	precision_fold_0 Precision Fold 0	precision_fold_1 Precision Fold 1	precision_fold_2 Precision Fold 2	precision_fold_3 Precision Fold 3	recall_fold_0 Recall Fold 0	recall_fold_1 Recall Fold 1	recall_fold_2 Recall Fold 2	recall_fold_3 Recall Fold 3	std_f1 Std F1
	1	4	3	0.99	4	0.9639116457533964	0.9743437462881578	0.9656214188978018	0.9572500436224044	0.96528171364044	0.6738925541941565	0.6911281489594743	0.6644920782851818	0.6374622356495468	0.98079561042524	0.9905808477237048	0.983448275862069	0.976851851851852	0.0060955033562434
1	1	6	3	0.99	6	0.959483870967742	0.9698046181172292	0.9638680033416877	0.9487164493304484	0.9604682354392768	0.6217391304347826	0.6528497409326425	0.691333982473223	0.6925638179800222	0.98079561042524	0.989010989010989	0.9793103448275862	0.9629629629629628	0.0077103812075003
2	1	4	2	0.99	4	0.9594935405836637	0.964319248826291	0.9620570711821887	0.9472703992550344	0.9582850649617944	0.595514950166113	0.5668161434977579	0.7016848364717542	0.6374745417515275	0.9835390946502056	0.9921507064364208	0.976551724137931	0.9660493827160492	0.00658450225525
3	2	4	2	0.99	8	0.9602806148767152	0.9547421354227577	0.9598672612257596	0.9555826511060792	0.957618165657828	0.6167097329888027	0.5335598980458793	0.6132644272179156	0.6187683284457478	0.9821673525377228	0.9858712715855572	0.9820689655172414	0.976851851851852	0.0024780000060665
4	1	4	3	0.95	4	0.9671831794229666	0.9668716050856564	0.9653870358716172	0.923267180966963	0.9556772503368008	0.7569002123142251	0.7524154589371981	0.750795334040297	0.7720870678617158	0.9780521262002744	0.978021978021978	0.976551724137931	0.9305555555555556	0.0187242657671063
5	1	6	2	0.99	6	0.959632459219492	0.9567757009345794	0.9595996455194704	0.9409782734983152	0.9542465197929644	0.6233653007846556	0.5271966527196653	0.6691871455576559	0.6143984220907298	0.98079561042524	0.989010989010989	0.976551724137931	0.9614197530864198	0.0077476999092081
6	2	4	2	0.95	8	0.9486779096398084	0.9592738845995168	0.961907743686078	0.9439897100093544	0.9534623119836896	0.7102330293819655	0.6007677543186181	0.6823869104908566	0.6869469026548672	0.96159122085048	0.9827315541601256	0.9779310344827586	0.9583333333333334	0.0073776755631609
7	2	4	3	0.9	8	0.9514847344207444	0.9657853810264384	0.960991232215047	0.9331531954887218	0.952853635787738	0.7751937984496124	0.7831021437578815	0.7635574837310195	0.741504854368932	0.9602194787379972	0.9748822605965464	0.9710344827586208	0.9429012345679012	0.0124843076445999
8	1	6	3	0.95	6	0.9679841485034936	0.972541545059265	0.9509865659109992	0.9188521698224156	0.9525911073240432	0.7492130115424974	0.7268518518518519	0.748657357679914	0.7456575682382134	0.9794238683127572	0.9858712715855572	0.9613793103448276	0.9274691358024691	0.0210704540735607
9	1	4	2	0.95	4	0.9593546708300806	0.9644441815062414	0.9627104421251376	0.919638667292351	0.9515369904384527	0.7161616161616161	0.6411042944785276	0.7494692144373672	0.7110849056603774	0.9725651577503428	0.9843014128728416	0.973793103448276	0.9305555555555556	0.018507165842545


CREATE TABLE deberta_finetuning (
  "unnamed_0" BIGINT,
  "accumulation" BIGINT,
  "batch" BIGINT,
  "epochs" BIGINT,
  "threshold" DOUBLE,
  "effective_batch" BIGINT,
  "f1_fold_0" DOUBLE,
  "f1_fold_1" DOUBLE,
  "f1_fold_2" DOUBLE,
  "f1_fold_3" DOUBLE,
  "mean_f1" DOUBLE,
  "precision_fold_0" DOUBLE,
  "precision_fold_1" DOUBLE,
  "precision_fold_2" DOUBLE,
  "precision_fold_3" DOUBLE,
  "recall_fold_0" DOUBLE,
  "recall_fold_1" DOUBLE,
  "recall_fold_2" DOUBLE,
  "recall_fold_3" DOUBLE,
  "std_f1" DOUBLE
);