kev-4b-code-verify-v1 / run_eval.json
jtatman's picture
Upload code-verify-4b-v1
d1791cd verified
Raw History Blame Contribute Delete
3.9 kB
{
"development": {
"baseline kev": {
"auroc": 0.9595338983050847,
"acc": 0.9420289855072463,
"brier": 0.051967926948896535,
"ece": 0.08224694059061195,
"cov@2%": 0.8188405797101449,
"cov@5%": 0.8731884057971014,
"cov@10%": 0.9492753623188406
},
"fine-tuned kev": {
"auroc": 0.9582627118644068,
"acc": 0.967391304347826,
"brier": 0.03196338159102184,
"ece": 0.04480786530262329,
"cov@2%": 0.7391304347826086,
"cov@5%": 0.8985507246376812,
"cov@10%": 0.9492753623188406
},
"evidence score": {
"auroc": 0.9599576271186441,
"acc": 0.9710144927536232,
"brier": 0.03740658967391304,
"ece": 0.07269021739130432,
"cov@2%": 0.7898550724637681,
"cov@5%": 0.8985507246376812,
"cov@10%": 0.9239130434782609
},
"mean(evidence, baseline)": {
"auroc": 0.9653601694915255,
"acc": 0.9492753623188406,
"brier": 0.03681774037976611,
"ece": 0.07842630691187563,
"cov@2%": 0.7934782608695652,
"cov@5%": 0.8985507246376812,
"cov@10%": 0.9492753623188406
},
"mean(evidence, fine-tuned)": {
"auroc": 0.9679025423728813,
"acc": 0.967391304347826,
"brier": 0.030796113996718024,
"ece": 0.054936653462283394,
"cov@2%": 0.8007246376811594,
"cov@5%": 0.8985507246376812,
"cov@10%": 0.9492753623188406
}
},
"test_unseen_coder": {
"baseline kev": {
"auroc": 0.9663382594417077,
"acc": 0.9295774647887324,
"brier": 0.06354770562384918,
"ece": 0.04240858525824696,
"cov@2%": 0.28169014084507044,
"cov@5%": 0.4788732394366197,
"cov@10%": 0.647887323943662
},
"fine-tuned kev": {
"auroc": 0.9860426929392446,
"acc": 0.9154929577464789,
"brier": 0.06591741550271953,
"ece": 0.04675058358510263,
"cov@2%": 0.43661971830985913,
"cov@5%": 0.5915492957746479,
"cov@10%": 0.647887323943662
},
"evidence score": {
"auroc": 0.9433497536945813,
"acc": 0.9154929577464789,
"brier": 0.08483714788732394,
"ece": 0.1338028169014084,
"cov@2%": 0.15492957746478872,
"cov@5%": 0.15492957746478872,
"cov@10%": 0.5915492957746479
},
"mean(evidence, baseline)": {
"auroc": 0.9794745484400657,
"acc": 0.9154929577464789,
"brier": 0.06687451167408419,
"ece": 0.08106238257021522,
"cov@2%": 0.4225352112676056,
"cov@5%": 0.5774647887323944,
"cov@10%": 0.6197183098591549
},
"mean(evidence, fine-tuned)": {
"auroc": 0.9712643678160919,
"acc": 0.9154929577464789,
"brier": 0.06803778906539469,
"ece": 0.07175734922897826,
"cov@2%": 0.38028169014084506,
"cov@5%": 0.5774647887323944,
"cov@10%": 0.6056338028169014
}
},
"test_unseen_coder_all_tasks": {
"baseline kev": {
"auroc": 0.9704155219780219,
"acc": 0.9241803278688525,
"brier": 0.05993135831653411,
"ece": 0.031035312001956816,
"cov@2%": 0.3114754098360656,
"cov@5%": 0.514344262295082,
"cov@10%": 0.6229508196721312
},
"fine-tuned kev": {
"auroc": 0.9739182692307692,
"acc": 0.9385245901639344,
"brier": 0.04889003537440916,
"ece": 0.028302458894132104,
"cov@2%": 0.3442622950819672,
"cov@5%": 0.5430327868852459,
"cov@10%": 0.6352459016393442
},
"evidence score": {
"auroc": 0.943543956043956,
"acc": 0.9057377049180327,
"brier": 0.09111320255251247,
"ece": 0.09400301997638061,
"cov@2%": 0.0,
"cov@5%": 0.20901639344262296,
"cov@10%": 0.6188524590163934
},
"mean(evidence, baseline)": {
"auroc": 0.9705013736263737,
"acc": 0.9262295081967213,
"brier": 0.06611740777073485,
"ece": 0.06348054507231347,
"cov@2%": 0.3094262295081967,
"cov@5%": 0.5,
"cov@10%": 0.6270491803278688
},
"mean(evidence, fine-tuned)": {
"auroc": 0.9726304945054945,
"acc": 0.9364754098360656,
"brier": 0.05954172687246182,
"ece": 0.05905205255287546,
"cov@2%": 0.3463114754098361,
"cov@5%": 0.5061475409836066,
"cov@10%": 0.6352459016393442
}
}
}