upload graphcodebert robust, best f1 score at 0.54 at robust checkpoint 200

Browse files

Files changed (2) hide show

inference/graphcodebert-robust/inference.log +69 -0
inference/graphcodebert-robust/submission.csv +1001 -0

inference/graphcodebert-robust/inference.log ADDED Viewed

	@@ -0,0 +1,69 @@

+2026-04-16 09:16:18,911 - INFO - Loading model and tokenizer from: ./checkpoints/graphcodebert-robust/checkpoint-200
+2026-04-16 09:16:20,848 - INFO - ===== Model Architecture =====
+2026-04-16 09:16:20,851 - INFO -
+RobertaForSequenceClassification(
+  (roberta): RobertaModel(
+    (embeddings): RobertaEmbeddings(
+      (word_embeddings): Embedding(50265, 768, padding_idx=1)
+      (position_embeddings): Embedding(514, 768, padding_idx=1)
+      (token_type_embeddings): Embedding(1, 768)
+      (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
+      (dropout): Dropout(p=0.2, inplace=False)
+    )
+    (encoder): RobertaEncoder(
+      (layer): ModuleList(
+        (0-11): 12 x RobertaLayer(
+          (attention): RobertaAttention(
+            (self): RobertaSdpaSelfAttention(
+              (query): Linear(in_features=768, out_features=768, bias=True)
+              (key): Linear(in_features=768, out_features=768, bias=True)
+              (value): Linear(in_features=768, out_features=768, bias=True)
+              (dropout): Dropout(p=0.2, inplace=False)
+            )
+            (output): RobertaSelfOutput(
+              (dense): Linear(in_features=768, out_features=768, bias=True)
+              (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
+              (dropout): Dropout(p=0.2, inplace=False)
+            )
+          )
+          (intermediate): RobertaIntermediate(
+            (dense): Linear(in_features=768, out_features=3072, bias=True)
+            (intermediate_act_fn): GELUActivation()
+          )
+          (output): RobertaOutput(
+            (dense): Linear(in_features=3072, out_features=768, bias=True)
+            (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
+            (dropout): Dropout(p=0.2, inplace=False)
+          )
+        )
+      )
+    )
+  )
+  (classifier): RobertaClassificationHead(
+    (dense): Linear(in_features=768, out_features=768, bias=True)
+    (dropout): Dropout(p=0.2, inplace=False)
+    (out_proj): Linear(in_features=768, out_features=2, bias=True)
+  )
+)
+2026-04-16 09:16:20,853 - INFO - ===== Parameter Summary =====
+2026-04-16 09:16:20,855 - INFO - Total Parameters:         124,647,170
+2026-04-16 09:16:20,857 - INFO - Trainable Parameters:     124,647,170
+2026-04-16 09:16:20,858 - INFO - Non-trainable Parameters: 0
+2026-04-16 09:16:20,859 - INFO - ===== Tokenizer Summary =====
+2026-04-16 09:16:20,874 - INFO - Vocab size: 50265 | Special tokens: ['<s>', '</s>', '<unk>', '<pad>', '<mask>']
+2026-04-16 09:16:20,876 - INFO - ===== End of Architecture Log =====
+2026-04-16 09:16:21,287 - INFO - Loading dataset: DaniilOr/SemEval-2026-Task13 (A)
+2026-04-16 09:16:28,538 - INFO - Tokenizing dataset...
+2026-04-16 09:16:29,324 - INFO - Running inference on 1000 examples...
+2026-04-16 09:16:55,877 - INFO - Calculating classification metrics...
+2026-04-16 09:16:55,902 - INFO - ------------------------------
+2026-04-16 09:16:55,904 - INFO - METRICS FOR SPLIT: test
+2026-04-16 09:16:55,905 - INFO - Accuracy:  0.5030
+2026-04-16 09:16:55,907 - INFO - Precision: 0.6228
+2026-04-16 09:16:55,909 - INFO - Recall:    0.5030
+2026-04-16 09:16:55,910 - INFO - F1-Score:  0.5438
+2026-04-16 09:16:55,912 - INFO - ------------------------------
+2026-04-16 09:16:55,918 - INFO - Confusion Matrix:
+[[422 355]
+ [142  81]]
+2026-04-16 09:16:55,921 - INFO - ✅ Predictions saved to test/inference/graphcodebert-robust/submission.csv

inference/graphcodebert-robust/submission.csv ADDED Viewed

	@@ -0,0 +1,1001 @@

+id,label
+0,0
+1,1
+2,1
+3,0
+4,0
+5,1
+6,1
+7,1
+8,0
+9,0
+10,1
+11,0
+12,1
+13,0
+14,0
+15,1
+16,0
+17,0
+18,0
+19,0
+20,0
+21,0
+22,0
+23,0
+24,0
+25,0
+26,0
+27,0
+28,0
+29,1
+30,0
+31,0
+32,1
+33,1
+34,0
+35,1
+36,0
+37,0
+38,0
+39,1
+40,1
+41,0
+42,0
+43,0
+44,1
+45,1
+46,0
+47,0
+48,0
+49,0
+50,1
+51,1
+52,1
+53,1
+54,0
+55,1
+56,0
+57,1
+58,0
+59,1
+60,0
+61,1
+62,0
+63,0
+64,1
+65,0
+66,0
+67,1
+68,1
+69,1
+70,0
+71,0
+72,1
+73,0
+74,0
+75,0
+76,1
+77,0
+78,1
+79,0
+80,1
+81,0
+82,1
+83,1
+84,0
+85,1
+86,0
+87,1
+88,1
+89,1
+90,0
+91,0
+92,0
+93,0
+94,1
+95,0
+96,1
+97,1
+98,1
+99,1
+100,1
+101,0
+102,1
+103,0
+104,1
+105,0
+106,0
+107,1
+108,1
+109,1
+110,0
+111,0
+112,0
+113,1
+114,1
+115,0
+116,1
+117,0
+118,1
+119,0
+120,1
+121,1
+122,0
+123,0
+124,0
+125,1
+126,1
+127,0
+128,1
+129,0
+130,1
+131,0
+132,1
+133,0
+134,0
+135,1
+136,1
+137,1
+138,1
+139,1
+140,0
+141,0
+142,0
+143,0
+144,1
+145,0
+146,0
+147,0
+148,1
+149,1
+150,0
+151,0
+152,1
+153,0
+154,0
+155,1
+156,0
+157,0
+158,1
+159,0
+160,1
+161,0
+162,0
+163,1
+164,1
+165,0
+166,0
+167,0
+168,0
+169,0
+170,1
+171,0
+172,1
+173,0
+174,0
+175,0
+176,0
+177,0
+178,0
+179,1
+180,1
+181,1
+182,0
+183,1
+184,1
+185,0
+186,0
+187,0
+188,1
+189,1
+190,1
+191,0
+192,0
+193,0
+194,0
+195,1
+196,0
+197,1
+198,1
+199,1
+200,1
+201,0
+202,1
+203,1
+204,0
+205,0
+206,1
+207,0
+208,0
+209,0
+210,0
+211,0
+212,0
+213,0
+214,0
+215,1
+216,0
+217,0
+218,0
+219,1
+220,1
+221,0
+222,0
+223,0
+224,0
+225,0
+226,1
+227,1
+228,0
+229,0
+230,0
+231,0
+232,1
+233,1
+234,1
+235,1
+236,1
+237,0
+238,1
+239,0
+240,1
+241,0
+242,0
+243,1
+244,1
+245,0
+246,1
+247,0
+248,0
+249,0
+250,0
+251,0
+252,0
+253,1
+254,0
+255,0
+256,1
+257,0
+258,1
+259,1
+260,0
+261,0
+262,0
+263,1
+264,0
+265,1
+266,1
+267,1
+268,1
+269,1
+270,0
+271,0
+272,0
+273,0
+274,1
+275,0
+276,0
+277,1
+278,1
+279,0
+280,1
+281,0
+282,0
+283,0
+284,1
+285,1
+286,1
+287,1
+288,1
+289,0
+290,0
+291,0
+292,0
+293,1
+294,1
+295,0
+296,1
+297,0
+298,0
+299,1
+300,0
+301,1
+302,0
+303,0
+304,0
+305,0
+306,0
+307,1
+308,1
+309,0
+310,1
+311,0
+312,0
+313,0
+314,0
+315,0
+316,1
+317,1
+318,1
+319,1
+320,1
+321,0
+322,1
+323,1
+324,1
+325,0
+326,0
+327,0
+328,0
+329,0
+330,0
+331,0
+332,0
+333,0
+334,0
+335,0
+336,1
+337,0
+338,0
+339,0
+340,0
+341,1
+342,0
+343,1
+344,0
+345,0
+346,0
+347,1
+348,0
+349,0
+350,1
+351,1
+352,0
+353,1
+354,1
+355,0
+356,1
+357,0
+358,0
+359,1
+360,1
+361,1
+362,0
+363,0
+364,0
+365,1
+366,0
+367,0
+368,0
+369,0
+370,0
+371,1
+372,0
+373,1
+374,0
+375,0
+376,0
+377,0
+378,1
+379,0
+380,0
+381,1
+382,1
+383,0
+384,1
+385,0
+386,1
+387,0
+388,1
+389,1
+390,0
+391,1
+392,1
+393,0
+394,0
+395,0
+396,1
+397,0
+398,1
+399,0
+400,1
+401,1
+402,0
+403,0
+404,1
+405,0
+406,1
+407,0
+408,1
+409,1
+410,1
+411,1
+412,1
+413,0
+414,0
+415,0
+416,1
+417,0
+418,0
+419,1
+420,1
+421,0
+422,1
+423,0
+424,0
+425,1
+426,0
+427,1
+428,1
+429,1
+430,0
+431,1
+432,0
+433,1
+434,0
+435,0
+436,1
+437,0
+438,0
+439,0
+440,0
+441,0
+442,0
+443,0
+444,1
+445,1
+446,0
+447,1
+448,1
+449,0
+450,1
+451,1
+452,0
+453,0
+454,0
+455,0
+456,1
+457,0
+458,1
+459,1
+460,0
+461,0
+462,0
+463,1
+464,0
+465,0
+466,1
+467,1
+468,1
+469,1
+470,1
+471,0
+472,1
+473,1
+474,0
+475,1
+476,0
+477,0
+478,1
+479,0
+480,1
+481,0
+482,1
+483,1
+484,1
+485,0
+486,0
+487,1
+488,1
+489,0
+490,0
+491,1
+492,1
+493,1
+494,1
+495,1
+496,1
+497,1
+498,0
+499,0
+500,1
+501,1
+502,1
+503,1
+504,0
+505,0
+506,1
+507,0
+508,0
+509,0
+510,1
+511,1
+512,0
+513,0
+514,0
+515,1
+516,0
+517,1
+518,0
+519,0
+520,1
+521,1
+522,0
+523,1
+524,0
+525,0
+526,0
+527,1
+528,0
+529,0
+530,1
+531,0
+532,1
+533,0
+534,1
+535,1
+536,1
+537,0
+538,0
+539,1
+540,0
+541,0
+542,1
+543,0
+544,1
+545,1
+546,0
+547,1
+548,1
+549,0
+550,0
+551,1
+552,0
+553,0
+554,0
+555,1
+556,0
+557,0
+558,1
+559,0
+560,1
+561,0
+562,1
+563,1
+564,0
+565,0
+566,1
+567,1
+568,0
+569,0
+570,1
+571,1
+572,0
+573,1
+574,1
+575,0
+576,0
+577,0
+578,0
+579,0
+580,0
+581,0
+582,0
+583,1
+584,1
+585,1
+586,0
+587,0
+588,0
+589,0
+590,0
+591,0
+592,0
+593,1
+594,1
+595,0
+596,1
+597,0
+598,0
+599,0
+600,1
+601,0
+602,1
+603,0
+604,0
+605,0
+606,1
+607,0
+608,1
+609,1
+610,0
+611,1
+612,1
+613,1
+614,1
+615,0
+616,0
+617,1
+618,0
+619,0
+620,0
+621,0
+622,0
+623,0
+624,1
+625,0
+626,0
+627,0
+628,0
+629,1
+630,1
+631,1
+632,1
+633,0
+634,1
+635,0
+636,0
+637,1
+638,1
+639,0
+640,0
+641,0
+642,1
+643,0
+644,0
+645,1
+646,1
+647,0
+648,0
+649,0
+650,0
+651,1
+652,1
+653,1
+654,1
+655,1
+656,0
+657,0
+658,1
+659,0
+660,0
+661,0
+662,1
+663,1
+664,0
+665,1
+666,1
+667,1
+668,0
+669,0
+670,1
+671,0
+672,0
+673,0
+674,1
+675,0
+676,0
+677,0
+678,1
+679,0
+680,1
+681,0
+682,1
+683,0
+684,1
+685,0
+686,0
+687,1
+688,1
+689,1
+690,0
+691,1
+692,0
+693,1
+694,1
+695,1
+696,0
+697,0
+698,0
+699,0
+700,0
+701,0
+702,0
+703,0
+704,0
+705,0
+706,0
+707,1
+708,0
+709,0
+710,1
+711,0
+712,1
+713,0
+714,0
+715,1
+716,1
+717,1
+718,0
+719,0
+720,1
+721,0
+722,0
+723,1
+724,0
+725,1
+726,0
+727,0
+728,0
+729,0
+730,0
+731,0
+732,0
+733,0
+734,0
+735,1
+736,1
+737,1
+738,0
+739,0
+740,1
+741,0
+742,1
+743,0
+744,1
+745,1
+746,0
+747,0
+748,0
+749,1
+750,0
+751,0
+752,0
+753,0
+754,0
+755,1
+756,0
+757,0
+758,0
+759,1
+760,1
+761,1
+762,1
+763,0
+764,0
+765,0
+766,0
+767,0
+768,1
+769,0
+770,1
+771,1
+772,0
+773,0
+774,0
+775,0
+776,1
+777,1
+778,0
+779,1
+780,0
+781,0
+782,0
+783,0
+784,1
+785,1
+786,1
+787,0
+788,0
+789,0
+790,0
+791,1
+792,0
+793,1
+794,0
+795,0
+796,0
+797,1
+798,1
+799,1
+800,0
+801,1
+802,1
+803,1
+804,1
+805,1
+806,0
+807,1
+808,0
+809,0
+810,0
+811,0
+812,0
+813,1
+814,1
+815,1
+816,0
+817,0
+818,0
+819,0
+820,0
+821,1
+822,1
+823,0
+824,0
+825,1
+826,1
+827,1
+828,0
+829,0
+830,1
+831,0
+832,1
+833,1
+834,1
+835,1
+836,0
+837,1
+838,0
+839,1
+840,1
+841,1
+842,0
+843,0
+844,0
+845,1
+846,1
+847,0
+848,1
+849,1
+850,1
+851,0
+852,0
+853,0
+854,1
+855,0
+856,1
+857,1
+858,0
+859,1
+860,1
+861,0
+862,0
+863,0
+864,0
+865,0
+866,0
+867,1
+868,1
+869,0
+870,0
+871,1
+872,1
+873,0
+874,1
+875,0
+876,1
+877,0
+878,0
+879,0
+880,1
+881,0
+882,1
+883,1
+884,1
+885,0
+886,1
+887,0
+888,0
+889,0
+890,1
+891,0
+892,0
+893,1
+894,1
+895,0
+896,1
+897,1
+898,0
+899,1
+900,1
+901,0
+902,0
+903,1
+904,0
+905,0
+906,1
+907,0
+908,1
+909,1
+910,1
+911,1
+912,1
+913,0
+914,1
+915,0
+916,0
+917,0
+918,1
+919,0
+920,0
+921,1
+922,0
+923,0
+924,0
+925,1
+926,1
+927,1
+928,1
+929,0
+930,1
+931,0
+932,0
+933,0
+934,1
+935,0
+936,0
+937,0
+938,1
+939,0
+940,0
+941,0
+942,1
+943,0
+944,0
+945,1
+946,1
+947,0
+948,1
+949,1
+950,1
+951,0
+952,0
+953,1
+954,0
+955,1
+956,0
+957,0
+958,0
+959,1
+960,0
+961,1
+962,0
+963,1
+964,0
+965,1
+966,0
+967,1
+968,0
+969,0
+970,0
+971,1
+972,0
+973,0
+974,0
+975,0
+976,0
+977,0
+978,1
+979,0
+980,0
+981,0
+982,1
+983,0
+984,0
+985,0
+986,1
+987,1
+988,1
+989,0
+990,0
+991,1
+992,1
+993,0
+994,0
+995,1
+996,1
+997,0
+998,1
+999,1