dzungpham/graphcodebert-code-classification
0
12026-04-20 11:15:57,077 - INFO - Loading model and tokenizer from: output_checkpoints/graphcodebert-mixcode-fft/checkpoint-20022026-04-20 11:15:57,642 - INFO - ===== Model Architecture =====32026-04-20 11:15:57,646 - INFO - 4RobertaForSequenceClassification(5 (roberta): RobertaModel(6 (embeddings): RobertaEmbeddings(7 (word_embeddings): Embedding(50265, 768, padding_idx=1)8 (position_embeddings): Embedding(514, 768, padding_idx=1)9 (token_type_embeddings): Embedding(1, 768)10 (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)11 (dropout): Dropout(p=0.3, inplace=False)12 )13 (encoder): RobertaEncoder(14 (layer): ModuleList(15 (0-11): 12 x RobertaLayer(16 (attention): RobertaAttention(17 (self): RobertaSdpaSelfAttention(18 (query): Linear(in_features=768, out_features=768, bias=True)19 (key): Linear(in_features=768, out_features=768, bias=True)20 (value): Linear(in_features=768, out_features=768, bias=True)21 (dropout): Dropout(p=0.3, inplace=False)22 )23 (output): RobertaSelfOutput(24 (dense): Linear(in_features=768, out_features=768, bias=True)25 (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)26 (dropout): Dropout(p=0.3, inplace=False)27 )28 )29 (intermediate): RobertaIntermediate(30 (dense): Linear(in_features=768, out_features=3072, bias=True)31 (intermediate_act_fn): GELUActivation()32 )33 (output): RobertaOutput(34 (dense): Linear(in_features=3072, out_features=768, bias=True)35 (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)36 (dropout): Dropout(p=0.3, inplace=False)37 )38 )39 )40 )41 )42 (classifier): RobertaClassificationHead(43 (dense): Linear(in_features=768, out_features=768, bias=True)44 (dropout): Dropout(p=0.3, inplace=False)45 (out_proj): Linear(in_features=768, out_features=2, bias=True)46 )47)482026-04-20 11:15:57,651 - INFO - ===== Parameter Summary =====492026-04-20 11:15:57,654 - INFO - Total Parameters: 124,647,170502026-04-20 11:15:57,656 - INFO - Trainable Parameters: 124,647,170512026-04-20 11:15:57,658 - INFO - Non-trainable Parameters: 0522026-04-20 11:15:57,662 - INFO - ===== Tokenizer Summary =====532026-04-20 11:15:57,722 - INFO - Vocab size: 50265 | Special tokens: ['<s>', '</s>', '<unk>', '<pad>', '<mask>']542026-04-20 11:15:57,726 - INFO - ===== End of Architecture Log =====552026-04-20 11:15:58,051 - INFO - Loading dataset: DaniilOr/SemEval-2026-Task13 (A)562026-04-20 11:16:00,140 - INFO - Tokenising dataset...572026-04-20 11:16:00,328 - INFO - Running inference on 1000 examples...582026-04-20 11:16:34,745 - INFO - Classification metrics for output_checkpoints/graphcodebert-mixcode-fft/checkpoint-200592026-04-20 11:16:34,789 - INFO - ------------------------------602026-04-20 11:16:34,795 - INFO - METRICS FOR SPLIT: test612026-04-20 11:16:34,799 - INFO - Accuracy: 0.5880622026-04-20 11:16:34,805 - INFO - Precision: 0.6758632026-04-20 11:16:34,814 - INFO - Recall: 0.5880642026-04-20 11:16:34,821 - INFO - F1-Score: 0.6189652026-04-20 11:16:34,829 - INFO - ------------------------------662026-04-20 11:16:34,834 - INFO - Confusion Matrix:67[[490 287]68 [125 98]]692026-04-20 11:16:34,842 - INFO - ✅ Metrics saved to test/inference/graphcodebert-mixcode-fft/checkpoint-200/metrics.json702026-04-20 11:16:34,850 - INFO - ✅ Predictions saved to test/inference/graphcodebert-mixcode-fft/checkpoint-200/submission.csv712026-04-20 11:18:51,695 - INFO - Loading model and tokenizer from: output_checkpoints/graphcodebert-mixcode-fft/checkpoint-200722026-04-20 11:18:51,695 - INFO - Loading model and tokenizer from: output_checkpoints/graphcodebert-mixcode-fft/checkpoint-200732026-04-20 11:18:52,448 - INFO - ===== Model Architecture =====742026-04-20 11:18:52,448 - INFO - ===== Model Architecture =====752026-04-20 11:18:52,458 - INFO - 76RobertaForSequenceClassification(77 (roberta): RobertaModel(78 (embeddings): RobertaEmbeddings(79 (word_embeddings): Embedding(50265, 768, padding_idx=1)80 (position_embeddings): Embedding(514, 768, padding_idx=1)81 (token_type_embeddings): Embedding(1, 768)82 (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)83 (dropout): Dropout(p=0.3, inplace=False)84 )85 (encoder): RobertaEncoder(86 (layer): ModuleList(87 (0-11): 12 x RobertaLayer(88 (attention): RobertaAttention(89 (self): RobertaSdpaSelfAttention(90 (query): Linear(in_features=768, out_features=768, bias=True)91 (key): Linear(in_features=768, out_features=768, bias=True)92 (value): Linear(in_features=768, out_features=768, bias=True)93 (dropout): Dropout(p=0.3, inplace=False)94 )95 (output): RobertaSelfOutput(96 (dense): Linear(in_features=768, out_features=768, bias=True)97 (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)98 (dropout): Dropout(p=0.3, inplace=False)99 )100 )101 (intermediate): RobertaIntermediate(102 (dense): Linear(in_features=768, out_features=3072, bias=True)103 (intermediate_act_fn): GELUActivation()104 )105 (output): RobertaOutput(106 (dense): Linear(in_features=3072, out_features=768, bias=True)107 (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)108 (dropout): Dropout(p=0.3, inplace=False)109 )110 )111 )112 )113 )114 (classifier): RobertaClassificationHead(115 (dense): Linear(in_features=768, out_features=768, bias=True)116 (dropout): Dropout(p=0.3, inplace=False)117 (out_proj): Linear(in_features=768, out_features=2, bias=True)118 )119)1202026-04-20 11:18:52,458 - INFO - 121RobertaForSequenceClassification(122 (roberta): RobertaModel(123 (embeddings): RobertaEmbeddings(124 (word_embeddings): Embedding(50265, 768, padding_idx=1)125 (position_embeddings): Embedding(514, 768, padding_idx=1)126 (token_type_embeddings): Embedding(1, 768)127 (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)128 (dropout): Dropout(p=0.3, inplace=False)129 )130 (encoder): RobertaEncoder(131 (layer): ModuleList(132 (0-11): 12 x RobertaLayer(133 (attention): RobertaAttention(134 (self): RobertaSdpaSelfAttention(135 (query): Linear(in_features=768, out_features=768, bias=True)136 (key): Linear(in_features=768, out_features=768, bias=True)137 (value): Linear(in_features=768, out_features=768, bias=True)138 (dropout): Dropout(p=0.3, inplace=False)139 )140 (output): RobertaSelfOutput(141 (dense): Linear(in_features=768, out_features=768, bias=True)142 (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)143 (dropout): Dropout(p=0.3, inplace=False)144 )145 )146 (intermediate): RobertaIntermediate(147 (dense): Linear(in_features=768, out_features=3072, bias=True)148 (intermediate_act_fn): GELUActivation()149 )150 (output): RobertaOutput(151 (dense): Linear(in_features=3072, out_features=768, bias=True)152 (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)153 (dropout): Dropout(p=0.3, inplace=False)154 )155 )156 )157 )158 )159 (classifier): RobertaClassificationHead(160 (dense): Linear(in_features=768, out_features=768, bias=True)161 (dropout): Dropout(p=0.3, inplace=False)162 (out_proj): Linear(in_features=768, out_features=2, bias=True)163 )164)1652026-04-20 11:18:52,475 - INFO - ===== Parameter Summary =====1662026-04-20 11:18:52,475 - INFO - ===== Parameter Summary =====1672026-04-20 11:18:52,482 - INFO - Total Parameters: 124,647,1701682026-04-20 11:18:52,482 - INFO - Total Parameters: 124,647,1701692026-04-20 11:18:52,487 - INFO - Trainable Parameters: 124,647,1701702026-04-20 11:18:52,487 - INFO - Trainable Parameters: 124,647,1701712026-04-20 11:18:52,493 - INFO - Non-trainable Parameters: 01722026-04-20 11:18:52,493 - INFO - Non-trainable Parameters: 01732026-04-20 11:18:52,499 - INFO - ===== Tokenizer Summary =====1742026-04-20 11:18:52,499 - INFO - ===== Tokenizer Summary =====1752026-04-20 11:18:52,537 - INFO - Vocab size: 50265 | Special tokens: ['<s>', '</s>', '<unk>', '<pad>', '<mask>']1762026-04-20 11:18:52,537 - INFO - Vocab size: 50265 | Special tokens: ['<s>', '</s>', '<unk>', '<pad>', '<mask>']1772026-04-20 11:18:52,545 - INFO - ===== End of Architecture Log =====1782026-04-20 11:18:52,545 - INFO - ===== End of Architecture Log =====1792026-04-20 11:18:52,827 - INFO - Loading dataset: DaniilOr/SemEval-2026-Task13 (A)1802026-04-20 11:18:52,827 - INFO - Loading dataset: DaniilOr/SemEval-2026-Task13 (A)1812026-04-20 11:18:54,882 - INFO - Tokenising dataset...1822026-04-20 11:18:54,882 - INFO - Tokenising dataset...1832026-04-20 11:18:55,060 - INFO - Running inference on 1000 examples...1842026-04-20 11:18:55,060 - INFO - Running inference on 1000 examples...1852026-04-20 11:19:29,762 - INFO - Classification metrics for output_checkpoints/graphcodebert-mixcode-fft/checkpoint-2001862026-04-20 11:19:29,762 - INFO - Classification metrics for output_checkpoints/graphcodebert-mixcode-fft/checkpoint-2001872026-04-20 11:19:29,813 - INFO - ------------------------------1882026-04-20 11:19:29,813 - INFO - ------------------------------1892026-04-20 11:19:29,818 - INFO - METRICS FOR SPLIT: test1902026-04-20 11:19:29,818 - INFO - METRICS FOR SPLIT: test1912026-04-20 11:19:29,824 - INFO - Accuracy: 0.58801922026-04-20 11:19:29,824 - INFO - Accuracy: 0.58801932026-04-20 11:19:29,829 - INFO - Precision: 0.67581942026-04-20 11:19:29,829 - INFO - Precision: 0.67581952026-04-20 11:19:29,834 - INFO - Recall: 0.58801962026-04-20 11:19:29,834 - INFO - Recall: 0.58801972026-04-20 11:19:29,839 - INFO - F1-Score: 0.61891982026-04-20 11:19:29,839 - INFO - F1-Score: 0.61891992026-04-20 11:19:29,846 - INFO - ------------------------------2002026-04-20 11:19:29,846 - INFO - ------------------------------2012026-04-20 11:19:29,853 - INFO - Confusion Matrix:202[[490 287]203 [125 98]]2042026-04-20 11:19:29,853 - INFO - Confusion Matrix:205[[490 287]206 [125 98]]2072026-04-20 11:19:29,859 - INFO - ✅ Metrics saved to test/inference/graphcodebert-mixcode-fft/checkpoint-200/metrics.json2082026-04-20 11:19:29,859 - INFO - ✅ Metrics saved to test/inference/graphcodebert-mixcode-fft/checkpoint-200/metrics.json2092026-04-20 11:19:29,865 - INFO - ✅ Predictions saved to test/inference/graphcodebert-mixcode-fft/checkpoint-200/submission.csv2102026-04-20 11:19:29,865 - INFO - ✅ Predictions saved to test/inference/graphcodebert-mixcode-fft/checkpoint-200/submission.csv2112026-04-20 11:21:17,370 - INFO - Loading model and tokenizer from: output_checkpoints/graphcodebert-mixcode-fft/checkpoint-1502122026-04-20 11:21:17,370 - INFO - Loading model and tokenizer from: output_checkpoints/graphcodebert-mixcode-fft/checkpoint-1502132026-04-20 11:21:17,931 - INFO - ===== Model Architecture =====2142026-04-20 11:21:17,931 - INFO - ===== Model Architecture =====2152026-04-20 11:21:17,944 - INFO - 216RobertaForSequenceClassification(217 (roberta): RobertaModel(218 (embeddings): RobertaEmbeddings(219 (word_embeddings): Embedding(50265, 768, padding_idx=1)220 (position_embeddings): Embedding(514, 768, padding_idx=1)221 (token_type_embeddings): Embedding(1, 768)222 (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)223 (dropout): Dropout(p=0.3, inplace=False)224 )225 (encoder): RobertaEncoder(226 (layer): ModuleList(227 (0-11): 12 x RobertaLayer(228 (attention): RobertaAttention(229 (self): RobertaSdpaSelfAttention(230 (query): Linear(in_features=768, out_features=768, bias=True)231 (key): Linear(in_features=768, out_features=768, bias=True)232 (value): Linear(in_features=768, out_features=768, bias=True)233 (dropout): Dropout(p=0.3, inplace=False)234 )235 (output): RobertaSelfOutput(236 (dense): Linear(in_features=768, out_features=768, bias=True)237 (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)238 (dropout): Dropout(p=0.3, inplace=False)239 )240 )241 (intermediate): RobertaIntermediate(242 (dense): Linear(in_features=768, out_features=3072, bias=True)243 (intermediate_act_fn): GELUActivation()244 )245 (output): RobertaOutput(246 (dense): Linear(in_features=3072, out_features=768, bias=True)247 (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)248 (dropout): Dropout(p=0.3, inplace=False)249 )250 )251 )252 )253 )254 (classifier): RobertaClassificationHead(255 (dense): Linear(in_features=768, out_features=768, bias=True)256 (dropout): Dropout(p=0.3, inplace=False)257 (out_proj): Linear(in_features=768, out_features=2, bias=True)258 )259)2602026-04-20 11:21:17,944 - INFO - 261RobertaForSequenceClassification(262 (roberta): RobertaModel(263 (embeddings): RobertaEmbeddings(264 (word_embeddings): Embedding(50265, 768, padding_idx=1)265 (position_embeddings): Embedding(514, 768, padding_idx=1)266 (token_type_embeddings): Embedding(1, 768)267 (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)268 (dropout): Dropout(p=0.3, inplace=False)269 )270 (encoder): RobertaEncoder(271 (layer): ModuleList(272 (0-11): 12 x RobertaLayer(273 (attention): RobertaAttention(274 (self): RobertaSdpaSelfAttention(275 (query): Linear(in_features=768, out_features=768, bias=True)276 (key): Linear(in_features=768, out_features=768, bias=True)277 (value): Linear(in_features=768, out_features=768, bias=True)278 (dropout): Dropout(p=0.3, inplace=False)279 )280 (output): RobertaSelfOutput(281 (dense): Linear(in_features=768, out_features=768, bias=True)282 (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)283 (dropout): Dropout(p=0.3, inplace=False)284 )285 )286 (intermediate): RobertaIntermediate(287 (dense): Linear(in_features=768, out_features=3072, bias=True)288 (intermediate_act_fn): GELUActivation()289 )290 (output): RobertaOutput(291 (dense): Linear(in_features=3072, out_features=768, bias=True)292 (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)293 (dropout): Dropout(p=0.3, inplace=False)294 )295 )296 )297 )298 )299 (classifier): RobertaClassificationHead(300 (dense): Linear(in_features=768, out_features=768, bias=True)301 (dropout): Dropout(p=0.3, inplace=False)302 (out_proj): Linear(in_features=768, out_features=2, bias=True)303 )304)3052026-04-20 11:21:17,954 - INFO - ===== Parameter Summary =====3062026-04-20 11:21:17,954 - INFO - ===== Parameter Summary =====3072026-04-20 11:21:17,963 - INFO - Total Parameters: 124,647,1703082026-04-20 11:21:17,963 - INFO - Total Parameters: 124,647,1703092026-04-20 11:21:17,970 - INFO - Trainable Parameters: 124,647,1703102026-04-20 11:21:17,970 - INFO - Trainable Parameters: 124,647,1703112026-04-20 11:21:17,980 - INFO - Non‑trainable Parameters: 03122026-04-20 11:21:17,980 - INFO - Non‑trainable Parameters: 03132026-04-20 11:21:17,986 - INFO - ===== Tokenizer Summary =====3142026-04-20 11:21:17,986 - INFO - ===== Tokenizer Summary =====3152026-04-20 11:21:18,059 - INFO - Vocab size: 50265 | Special tokens: ['<s>', '</s>', '<unk>', '<pad>', '<mask>']3162026-04-20 11:21:18,059 - INFO - Vocab size: 50265 | Special tokens: ['<s>', '</s>', '<unk>', '<pad>', '<mask>']3172026-04-20 11:21:18,067 - INFO - ===== End of Architecture Log =====3182026-04-20 11:21:18,067 - INFO - ===== End of Architecture Log =====3192026-04-20 11:21:18,559 - INFO - Loading dataset: DaniilOr/SemEval-2026-Task13 (A)3202026-04-20 11:21:18,559 - INFO - Loading dataset: DaniilOr/SemEval-2026-Task13 (A)3212026-04-20 11:21:20,637 - INFO - Tokenising dataset...3222026-04-20 11:21:20,637 - INFO - Tokenising dataset...3232026-04-20 11:21:20,809 - INFO - Running inference on 1000 examples...3242026-04-20 11:21:20,809 - INFO - Running inference on 1000 examples...3252026-04-20 11:21:55,162 - INFO - Computing metrics for output_checkpoints/graphcodebert-mixcode-fft/checkpoint-1503262026-04-20 11:21:55,162 - INFO - Computing metrics for output_checkpoints/graphcodebert-mixcode-fft/checkpoint-1503272026-04-20 11:21:55,216 - INFO - ------------------------------3282026-04-20 11:21:55,216 - INFO - ------------------------------3292026-04-20 11:21:55,223 - INFO - METRICS FOR SPLIT: test3302026-04-20 11:21:55,223 - INFO - METRICS FOR SPLIT: test3312026-04-20 11:21:55,232 - INFO - Accuracy: 0.68703322026-04-20 11:21:55,232 - INFO - Accuracy: 0.68703332026-04-20 11:21:55,239 - INFO - Precision: 0.67083342026-04-20 11:21:55,239 - INFO - Precision: 0.67083352026-04-20 11:21:55,247 - INFO - Recall: 0.68703362026-04-20 11:21:55,247 - INFO - Recall: 0.68703372026-04-20 11:21:55,256 - INFO - F1‑Score: 0.67843382026-04-20 11:21:55,256 - INFO - F1‑Score: 0.67843392026-04-20 11:21:55,260 - INFO - ------------------------------3402026-04-20 11:21:55,260 - INFO - ------------------------------3412026-04-20 11:21:55,268 - INFO - Confusion Matrix:342[[636 141]343 [172 51]]3442026-04-20 11:21:55,268 - INFO - Confusion Matrix:345[[636 141]346 [172 51]]3472026-04-20 11:21:55,280 - INFO - ✅ Metrics saved to test/inference/graphcodebert-mixcode-fft/checkpoint-150/metrics.json3482026-04-20 11:21:55,280 - INFO - ✅ Metrics saved to test/inference/graphcodebert-mixcode-fft/checkpoint-150/metrics.json3492026-04-20 11:21:55,288 - INFO - ✅ Predictions saved to test/inference/graphcodebert-mixcode-fft/checkpoint-150/submission.csv3502026-04-20 11:21:55,288 - INFO - ✅ Predictions saved to test/inference/graphcodebert-mixcode-fft/checkpoint-150/submission.csv3512026-04-20 11:22:18,401 - INFO - Loading model and tokenizer from: output_checkpoints/graphcodebert-mixcode-fft/checkpoint-1003522026-04-20 11:22:18,401 - INFO - Loading model and tokenizer from: output_checkpoints/graphcodebert-mixcode-fft/checkpoint-1003532026-04-20 11:22:19,077 - INFO - ===== Model Architecture =====3542026-04-20 11:22:19,077 - INFO - ===== Model Architecture =====3552026-04-20 11:22:19,094 - INFO - 356RobertaForSequenceClassification(357 (roberta): RobertaModel(358 (embeddings): RobertaEmbeddings(359 (word_embeddings): Embedding(50265, 768, padding_idx=1)360 (position_embeddings): Embedding(514, 768, padding_idx=1)361 (token_type_embeddings): Embedding(1, 768)362 (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)363 (dropout): Dropout(p=0.3, inplace=False)364 )365 (encoder): RobertaEncoder(366 (layer): ModuleList(367 (0-11): 12 x RobertaLayer(368 (attention): RobertaAttention(369 (self): RobertaSdpaSelfAttention(370 (query): Linear(in_features=768, out_features=768, bias=True)371 (key): Linear(in_features=768, out_features=768, bias=True)372 (value): Linear(in_features=768, out_features=768, bias=True)373 (dropout): Dropout(p=0.3, inplace=False)374 )375 (output): RobertaSelfOutput(376 (dense): Linear(in_features=768, out_features=768, bias=True)377 (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)378 (dropout): Dropout(p=0.3, inplace=False)379 )380 )381 (intermediate): RobertaIntermediate(382 (dense): Linear(in_features=768, out_features=3072, bias=True)383 (intermediate_act_fn): GELUActivation()384 )385 (output): RobertaOutput(386 (dense): Linear(in_features=3072, out_features=768, bias=True)387 (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)388 (dropout): Dropout(p=0.3, inplace=False)389 )390 )391 )392 )393 )394 (classifier): RobertaClassificationHead(395 (dense): Linear(in_features=768, out_features=768, bias=True)396 (dropout): Dropout(p=0.3, inplace=False)397 (out_proj): Linear(in_features=768, out_features=2, bias=True)398 )399)4002026-04-20 11:22:19,094 - INFO - 401RobertaForSequenceClassification(402 (roberta): RobertaModel(403 (embeddings): RobertaEmbeddings(404 (word_embeddings): Embedding(50265, 768, padding_idx=1)405 (position_embeddings): Embedding(514, 768, padding_idx=1)406 (token_type_embeddings): Embedding(1, 768)407 (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)408 (dropout): Dropout(p=0.3, inplace=False)409 )410 (encoder): RobertaEncoder(411 (layer): ModuleList(412 (0-11): 12 x RobertaLayer(413 (attention): RobertaAttention(414 (self): RobertaSdpaSelfAttention(415 (query): Linear(in_features=768, out_features=768, bias=True)416 (key): Linear(in_features=768, out_features=768, bias=True)417 (value): Linear(in_features=768, out_features=768, bias=True)418 (dropout): Dropout(p=0.3, inplace=False)419 )420 (output): RobertaSelfOutput(421 (dense): Linear(in_features=768, out_features=768, bias=True)422 (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)423 (dropout): Dropout(p=0.3, inplace=False)424 )425 )426 (intermediate): RobertaIntermediate(427 (dense): Linear(in_features=768, out_features=3072, bias=True)428 (intermediate_act_fn): GELUActivation()429 )430 (output): RobertaOutput(431 (dense): Linear(in_features=3072, out_features=768, bias=True)432 (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)433 (dropout): Dropout(p=0.3, inplace=False)434 )435 )436 )437 )438 )439 (classifier): RobertaClassificationHead(440 (dense): Linear(in_features=768, out_features=768, bias=True)441 (dropout): Dropout(p=0.3, inplace=False)442 (out_proj): Linear(in_features=768, out_features=2, bias=True)443 )444)4452026-04-20 11:22:19,112 - INFO - ===== Parameter Summary =====4462026-04-20 11:22:19,112 - INFO - ===== Parameter Summary =====4472026-04-20 11:22:19,123 - INFO - Total Parameters: 124,647,1704482026-04-20 11:22:19,123 - INFO - Total Parameters: 124,647,1704492026-04-20 11:22:19,132 - INFO - Trainable Parameters: 124,647,1704502026-04-20 11:22:19,132 - INFO - Trainable Parameters: 124,647,1704512026-04-20 11:22:19,141 - INFO - Non‑trainable Parameters: 04522026-04-20 11:22:19,141 - INFO - Non‑trainable Parameters: 04532026-04-20 11:22:19,145 - INFO - ===== Tokenizer Summary =====4542026-04-20 11:22:19,145 - INFO - ===== Tokenizer Summary =====4552026-04-20 11:22:19,195 - INFO - Vocab size: 50265 | Special tokens: ['<s>', '</s>', '<unk>', '<pad>', '<mask>']4562026-04-20 11:22:19,195 - INFO - Vocab size: 50265 | Special tokens: ['<s>', '</s>', '<unk>', '<pad>', '<mask>']4572026-04-20 11:22:19,205 - INFO - ===== End of Architecture Log =====4582026-04-20 11:22:19,205 - INFO - ===== End of Architecture Log =====4592026-04-20 11:22:21,126 - INFO - Loading dataset: DaniilOr/SemEval-2026-Task13 (A)4602026-04-20 11:22:21,126 - INFO - Loading dataset: DaniilOr/SemEval-2026-Task13 (A)4612026-04-20 11:22:23,159 - INFO - Tokenising dataset...4622026-04-20 11:22:23,159 - INFO - Tokenising dataset...4632026-04-20 11:22:23,233 - INFO - Running inference on 1000 examples...4642026-04-20 11:22:23,233 - INFO - Running inference on 1000 examples...4652026-04-20 11:22:57,170 - INFO - Computing metrics for output_checkpoints/graphcodebert-mixcode-fft/checkpoint-1004662026-04-20 11:22:57,170 - INFO - Computing metrics for output_checkpoints/graphcodebert-mixcode-fft/checkpoint-1004672026-04-20 11:22:57,283 - INFO - ------------------------------4682026-04-20 11:22:57,283 - INFO - ------------------------------4692026-04-20 11:22:57,300 - INFO - METRICS FOR SPLIT: test4702026-04-20 11:22:57,300 - INFO - METRICS FOR SPLIT: test4712026-04-20 11:22:57,312 - INFO - Accuracy: 0.73404722026-04-20 11:22:57,312 - INFO - Accuracy: 0.73404732026-04-20 11:22:57,326 - INFO - Precision: 0.67044742026-04-20 11:22:57,326 - INFO - Precision: 0.67044752026-04-20 11:22:57,337 - INFO - Recall: 0.73404762026-04-20 11:22:57,337 - INFO - Recall: 0.73404772026-04-20 11:22:57,354 - INFO - F1‑Score: 0.69164782026-04-20 11:22:57,354 - INFO - F1‑Score: 0.69164792026-04-20 11:22:57,373 - INFO - ------------------------------4802026-04-20 11:22:57,373 - INFO - ------------------------------4812026-04-20 11:22:57,392 - INFO - Confusion Matrix:482[[707 70]483 [196 27]]4842026-04-20 11:22:57,392 - INFO - Confusion Matrix:485[[707 70]486 [196 27]]4872026-04-20 11:22:57,401 - INFO - ✅ Metrics saved to test/inference/graphcodebert-mixcode-fft/checkpoint-100/metrics.json4882026-04-20 11:22:57,401 - INFO - ✅ Metrics saved to test/inference/graphcodebert-mixcode-fft/checkpoint-100/metrics.json4892026-04-20 11:22:57,412 - INFO - ✅ Predictions saved to test/inference/graphcodebert-mixcode-fft/checkpoint-100/submission.csv4902026-04-20 11:22:57,412 - INFO - ✅ Predictions saved to test/inference/graphcodebert-mixcode-fft/checkpoint-100/submission.csv4912026-04-20 11:23:14,035 - INFO - Loading model and tokenizer from: output_checkpoints/graphcodebert-mixcode-fft/checkpoint-504922026-04-20 11:23:14,035 - INFO - Loading model and tokenizer from: output_checkpoints/graphcodebert-mixcode-fft/checkpoint-504932026-04-20 11:23:14,977 - INFO - ===== Model Architecture =====4942026-04-20 11:23:14,977 - INFO - ===== Model Architecture =====4952026-04-20 11:23:14,996 - INFO - 496RobertaForSequenceClassification(497 (roberta): RobertaModel(498 (embeddings): RobertaEmbeddings(499 (word_embeddings): Embedding(50265, 768, padding_idx=1)500 (position_embeddings): Embedding(514, 768, padding_idx=1)501 (token_type_embeddings): Embedding(1, 768)502 (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)503 (dropout): Dropout(p=0.3, inplace=False)504 )505 (encoder): RobertaEncoder(506 (layer): ModuleList(507 (0-11): 12 x RobertaLayer(508 (attention): RobertaAttention(509 (self): RobertaSdpaSelfAttention(510 (query): Linear(in_features=768, out_features=768, bias=True)511 (key): Linear(in_features=768, out_features=768, bias=True)512 (value): Linear(in_features=768, out_features=768, bias=True)513 (dropout): Dropout(p=0.3, inplace=False)514 )515 (output): RobertaSelfOutput(516 (dense): Linear(in_features=768, out_features=768, bias=True)517 (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)518 (dropout): Dropout(p=0.3, inplace=False)519 )520 )521 (intermediate): RobertaIntermediate(522 (dense): Linear(in_features=768, out_features=3072, bias=True)523 (intermediate_act_fn): GELUActivation()524 )525 (output): RobertaOutput(526 (dense): Linear(in_features=3072, out_features=768, bias=True)527 (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)528 (dropout): Dropout(p=0.3, inplace=False)529 )530 )531 )532 )533 )534 (classifier): RobertaClassificationHead(535 (dense): Linear(in_features=768, out_features=768, bias=True)536 (dropout): Dropout(p=0.3, inplace=False)537 (out_proj): Linear(in_features=768, out_features=2, bias=True)538 )539)5402026-04-20 11:23:14,996 - INFO - 541RobertaForSequenceClassification(542 (roberta): RobertaModel(543 (embeddings): RobertaEmbeddings(544 (word_embeddings): Embedding(50265, 768, padding_idx=1)545 (position_embeddings): Embedding(514, 768, padding_idx=1)546 (token_type_embeddings): Embedding(1, 768)547 (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)548 (dropout): Dropout(p=0.3, inplace=False)549 )550 (encoder): RobertaEncoder(551 (layer): ModuleList(552 (0-11): 12 x RobertaLayer(553 (attention): RobertaAttention(554 (self): RobertaSdpaSelfAttention(555 (query): Linear(in_features=768, out_features=768, bias=True)556 (key): Linear(in_features=768, out_features=768, bias=True)557 (value): Linear(in_features=768, out_features=768, bias=True)558 (dropout): Dropout(p=0.3, inplace=False)559 )560 (output): RobertaSelfOutput(561 (dense): Linear(in_features=768, out_features=768, bias=True)562 (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)563 (dropout): Dropout(p=0.3, inplace=False)564 )565 )566 (intermediate): RobertaIntermediate(567 (dense): Linear(in_features=768, out_features=3072, bias=True)568 (intermediate_act_fn): GELUActivation()569 )570 (output): RobertaOutput(571 (dense): Linear(in_features=3072, out_features=768, bias=True)572 (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)573 (dropout): Dropout(p=0.3, inplace=False)574 )575 )576 )577 )578 )579 (classifier): RobertaClassificationHead(580 (dense): Linear(in_features=768, out_features=768, bias=True)581 (dropout): Dropout(p=0.3, inplace=False)582 (out_proj): Linear(in_features=768, out_features=2, bias=True)583 )584)5852026-04-20 11:23:15,018 - INFO - ===== Parameter Summary =====5862026-04-20 11:23:15,018 - INFO - ===== Parameter Summary =====5872026-04-20 11:23:15,029 - INFO - Total Parameters: 124,647,1705882026-04-20 11:23:15,029 - INFO - Total Parameters: 124,647,1705892026-04-20 11:23:15,041 - INFO - Trainable Parameters: 124,647,1705902026-04-20 11:23:15,041 - INFO - Trainable Parameters: 124,647,1705912026-04-20 11:23:15,052 - INFO - Non‑trainable Parameters: 05922026-04-20 11:23:15,052 - INFO - Non‑trainable Parameters: 05932026-04-20 11:23:15,068 - INFO - ===== Tokenizer Summary =====5942026-04-20 11:23:15,068 - INFO - ===== Tokenizer Summary =====5952026-04-20 11:23:15,164 - INFO - Vocab size: 50265 | Special tokens: ['<s>', '</s>', '<unk>', '<pad>', '<mask>']5962026-04-20 11:23:15,164 - INFO - Vocab size: 50265 | Special tokens: ['<s>', '</s>', '<unk>', '<pad>', '<mask>']5972026-04-20 11:23:15,176 - INFO - ===== End of Architecture Log =====5982026-04-20 11:23:15,176 - INFO - ===== End of Architecture Log =====5992026-04-20 11:23:17,129 - INFO - Loading dataset: DaniilOr/SemEval-2026-Task13 (A)6002026-04-20 11:23:17,129 - INFO - Loading dataset: DaniilOr/SemEval-2026-Task13 (A)6012026-04-20 11:23:19,193 - INFO - Tokenising dataset...6022026-04-20 11:23:19,193 - INFO - Tokenising dataset...6032026-04-20 11:23:19,390 - INFO - Running inference on 1000 examples...6042026-04-20 11:23:19,390 - INFO - Running inference on 1000 examples...6052026-04-20 11:23:53,670 - INFO - Computing metrics for output_checkpoints/graphcodebert-mixcode-fft/checkpoint-506062026-04-20 11:23:53,670 - INFO - Computing metrics for output_checkpoints/graphcodebert-mixcode-fft/checkpoint-506072026-04-20 11:23:53,713 - INFO - ------------------------------6082026-04-20 11:23:53,713 - INFO - ------------------------------6092026-04-20 11:23:53,719 - INFO - METRICS FOR SPLIT: test6102026-04-20 11:23:53,719 - INFO - METRICS FOR SPLIT: test6112026-04-20 11:23:53,731 - INFO - Accuracy: 0.74006122026-04-20 11:23:53,731 - INFO - Accuracy: 0.74006132026-04-20 11:23:53,740 - INFO - Precision: 0.66406142026-04-20 11:23:53,740 - INFO - Precision: 0.66406152026-04-20 11:23:53,752 - INFO - Recall: 0.74006162026-04-20 11:23:53,752 - INFO - Recall: 0.74006172026-04-20 11:23:53,761 - INFO - F1‑Score: 0.68796182026-04-20 11:23:53,761 - INFO - F1‑Score: 0.68796192026-04-20 11:23:53,773 - INFO - ------------------------------6202026-04-20 11:23:53,773 - INFO - ------------------------------6212026-04-20 11:23:53,782 - INFO - Confusion Matrix:622[[720 57]623 [203 20]]6242026-04-20 11:23:53,782 - INFO - Confusion Matrix:625[[720 57]626 [203 20]]6272026-04-20 11:23:53,793 - INFO - ✅ Metrics saved to test/inference/graphcodebert-mixcode-fft/checkpoint-50/metrics.json6282026-04-20 11:23:53,793 - INFO - ✅ Metrics saved to test/inference/graphcodebert-mixcode-fft/checkpoint-50/metrics.json6292026-04-20 11:23:53,807 - INFO - ✅ Predictions saved to test/inference/graphcodebert-mixcode-fft/checkpoint-50/submission.csv6302026-04-20 11:23:53,807 - INFO - ✅ Predictions saved to test/inference/graphcodebert-mixcode-fft/checkpoint-50/submission.csv631