dzungpham/graphcodebert-code-classification
0
12026-04-20 11:12:17,780 - INFO - Loading model and tokenizer from: output_checkpoints/graphcodebert-mixcode-fft/checkpoint-20022026-04-20 11:12:18,292 - INFO - ===== Model Architecture =====32026-04-20 11:12:18,296 - 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 11:12:18,301 - INFO - ===== Parameter Summary =====492026-04-20 11:12:18,303 - INFO - Total Parameters: 124,647,170502026-04-20 11:12:18,304 - INFO - Trainable Parameters: 124,647,170512026-04-20 11:12:18,306 - INFO - Non-trainable Parameters: 0522026-04-20 11:12:18,307 - INFO - ===== Tokenizer Summary =====532026-04-20 11:12:18,332 - INFO - Vocab size: 50265 | Special tokens: ['<s>', '</s>', '<unk>', '<pad>', '<mask>']542026-04-20 11:12:18,333 - INFO - ===== End of Architecture Log =====552026-04-20 11:12:18,798 - INFO - Loading dataset: DaniilOr/SemEval-2026-Task13 (A)562026-04-20 11:12:20,862 - INFO - Tokenising dataset...572026-04-20 11:12:21,038 - INFO - Running inference on 1000 examples...582026-04-20 11:12:56,041 - INFO - Classification metrics for output_checkpoints/graphcodebert-mixcode-fft/checkpoint-200592026-04-20 11:12:56,081 - INFO - ------------------------------602026-04-20 11:12:56,082 - INFO - METRICS FOR SPLIT: test612026-04-20 11:12:56,085 - INFO - Accuracy: 0.5880622026-04-20 11:12:56,088 - INFO - Precision: 0.6758632026-04-20 11:12:56,090 - INFO - Recall: 0.5880642026-04-20 11:12:56,092 - INFO - F1-Score: 0.6189652026-04-20 11:12:56,094 - INFO - ------------------------------662026-04-20 11:12:56,098 - INFO - Confusion Matrix:67[[490 287]68 [125 98]]692026-04-20 11:12:56,102 - INFO - ✅ Predictions saved to test/inference/graphcodebert-mixcode-fft/submission.csv702026-04-20 11:15:57,077 - INFO - Loading model and tokenizer from: output_checkpoints/graphcodebert-mixcode-fft/checkpoint-200712026-04-20 11:15:57,642 - INFO - ===== Model Architecture =====722026-04-20 11:15:57,646 - INFO - 73RobertaForSequenceClassification(74 (roberta): RobertaModel(75 (embeddings): RobertaEmbeddings(76 (word_embeddings): Embedding(50265, 768, padding_idx=1)77 (position_embeddings): Embedding(514, 768, padding_idx=1)78 (token_type_embeddings): Embedding(1, 768)79 (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)80 (dropout): Dropout(p=0.3, inplace=False)81 )82 (encoder): RobertaEncoder(83 (layer): ModuleList(84 (0-11): 12 x RobertaLayer(85 (attention): RobertaAttention(86 (self): RobertaSdpaSelfAttention(87 (query): Linear(in_features=768, out_features=768, bias=True)88 (key): Linear(in_features=768, out_features=768, bias=True)89 (value): Linear(in_features=768, out_features=768, bias=True)90 (dropout): Dropout(p=0.3, inplace=False)91 )92 (output): RobertaSelfOutput(93 (dense): Linear(in_features=768, out_features=768, bias=True)94 (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)95 (dropout): Dropout(p=0.3, inplace=False)96 )97 )98 (intermediate): RobertaIntermediate(99 (dense): Linear(in_features=768, out_features=3072, bias=True)100 (intermediate_act_fn): GELUActivation()101 )102 (output): RobertaOutput(103 (dense): Linear(in_features=3072, out_features=768, bias=True)104 (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)105 (dropout): Dropout(p=0.3, inplace=False)106 )107 )108 )109 )110 )111 (classifier): RobertaClassificationHead(112 (dense): Linear(in_features=768, out_features=768, bias=True)113 (dropout): Dropout(p=0.3, inplace=False)114 (out_proj): Linear(in_features=768, out_features=2, bias=True)115 )116)1172026-04-20 11:15:57,651 - INFO - ===== Parameter Summary =====1182026-04-20 11:15:57,654 - INFO - Total Parameters: 124,647,1701192026-04-20 11:15:57,656 - INFO - Trainable Parameters: 124,647,1701202026-04-20 11:15:57,658 - INFO - Non-trainable Parameters: 01212026-04-20 11:15:57,662 - INFO - ===== Tokenizer Summary =====1222026-04-20 11:15:57,722 - INFO - Vocab size: 50265 | Special tokens: ['<s>', '</s>', '<unk>', '<pad>', '<mask>']1232026-04-20 11:15:57,726 - INFO - ===== End of Architecture Log =====1242026-04-20 11:15:58,051 - INFO - Loading dataset: DaniilOr/SemEval-2026-Task13 (A)1252026-04-20 11:16:00,140 - INFO - Tokenising dataset...1262026-04-20 11:16:00,328 - INFO - Running inference on 1000 examples...1272026-04-20 11:16:34,745 - INFO - Classification metrics for output_checkpoints/graphcodebert-mixcode-fft/checkpoint-2001282026-04-20 11:16:34,789 - INFO - ------------------------------1292026-04-20 11:16:34,795 - INFO - METRICS FOR SPLIT: test1302026-04-20 11:16:34,799 - INFO - Accuracy: 0.58801312026-04-20 11:16:34,805 - INFO - Precision: 0.67581322026-04-20 11:16:34,814 - INFO - Recall: 0.58801332026-04-20 11:16:34,821 - INFO - F1-Score: 0.61891342026-04-20 11:16:34,829 - INFO - ------------------------------1352026-04-20 11:16:34,834 - INFO - Confusion Matrix:136[[490 287]137 [125 98]]1382026-04-20 11:16:34,842 - INFO - ✅ Metrics saved to test/inference/graphcodebert-mixcode-fft/checkpoint-200/metrics.json1392026-04-20 11:16:34,850 - INFO - ✅ Predictions saved to test/inference/graphcodebert-mixcode-fft/checkpoint-200/submission.csv1402026-04-20 11:18:51,695 - INFO - Loading model and tokenizer from: output_checkpoints/graphcodebert-mixcode-fft/checkpoint-2001412026-04-20 11:18:52,448 - INFO - ===== Model Architecture =====1422026-04-20 11:18:52,458 - INFO - 143RobertaForSequenceClassification(144 (roberta): RobertaModel(145 (embeddings): RobertaEmbeddings(146 (word_embeddings): Embedding(50265, 768, padding_idx=1)147 (position_embeddings): Embedding(514, 768, padding_idx=1)148 (token_type_embeddings): Embedding(1, 768)149 (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)150 (dropout): Dropout(p=0.3, inplace=False)151 )152 (encoder): RobertaEncoder(153 (layer): ModuleList(154 (0-11): 12 x RobertaLayer(155 (attention): RobertaAttention(156 (self): RobertaSdpaSelfAttention(157 (query): Linear(in_features=768, out_features=768, bias=True)158 (key): Linear(in_features=768, out_features=768, bias=True)159 (value): Linear(in_features=768, out_features=768, bias=True)160 (dropout): Dropout(p=0.3, inplace=False)161 )162 (output): RobertaSelfOutput(163 (dense): Linear(in_features=768, out_features=768, bias=True)164 (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)165 (dropout): Dropout(p=0.3, inplace=False)166 )167 )168 (intermediate): RobertaIntermediate(169 (dense): Linear(in_features=768, out_features=3072, bias=True)170 (intermediate_act_fn): GELUActivation()171 )172 (output): RobertaOutput(173 (dense): Linear(in_features=3072, out_features=768, bias=True)174 (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)175 (dropout): Dropout(p=0.3, inplace=False)176 )177 )178 )179 )180 )181 (classifier): RobertaClassificationHead(182 (dense): Linear(in_features=768, out_features=768, bias=True)183 (dropout): Dropout(p=0.3, inplace=False)184 (out_proj): Linear(in_features=768, out_features=2, bias=True)185 )186)1872026-04-20 11:18:52,475 - INFO - ===== Parameter Summary =====1882026-04-20 11:18:52,482 - INFO - Total Parameters: 124,647,1701892026-04-20 11:18:52,487 - INFO - Trainable Parameters: 124,647,1701902026-04-20 11:18:52,493 - INFO - Non-trainable Parameters: 01912026-04-20 11:18:52,499 - INFO - ===== Tokenizer Summary =====1922026-04-20 11:18:52,537 - INFO - Vocab size: 50265 | Special tokens: ['<s>', '</s>', '<unk>', '<pad>', '<mask>']1932026-04-20 11:18:52,545 - INFO - ===== End of Architecture Log =====1942026-04-20 11:18:52,827 - INFO - Loading dataset: DaniilOr/SemEval-2026-Task13 (A)1952026-04-20 11:18:54,882 - INFO - Tokenising dataset...1962026-04-20 11:18:55,060 - INFO - Running inference on 1000 examples...1972026-04-20 11:19:29,762 - INFO - Classification metrics for output_checkpoints/graphcodebert-mixcode-fft/checkpoint-2001982026-04-20 11:19:29,813 - INFO - ------------------------------1992026-04-20 11:19:29,818 - INFO - METRICS FOR SPLIT: test2002026-04-20 11:19:29,824 - INFO - Accuracy: 0.58802012026-04-20 11:19:29,829 - INFO - Precision: 0.67582022026-04-20 11:19:29,834 - INFO - Recall: 0.58802032026-04-20 11:19:29,839 - INFO - F1-Score: 0.61892042026-04-20 11:19:29,846 - INFO - ------------------------------2052026-04-20 11:19:29,853 - INFO - Confusion Matrix:206[[490 287]207 [125 98]]2082026-04-20 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 11:21:17,370 - INFO - Loading model and tokenizer from: output_checkpoints/graphcodebert-mixcode-fft/checkpoint-1502112026-04-20 11:21:17,931 - INFO - ===== Model Architecture =====2122026-04-20 11:21:17,944 - INFO - 213RobertaForSequenceClassification(214 (roberta): RobertaModel(215 (embeddings): RobertaEmbeddings(216 (word_embeddings): Embedding(50265, 768, padding_idx=1)217 (position_embeddings): Embedding(514, 768, padding_idx=1)218 (token_type_embeddings): Embedding(1, 768)219 (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)220 (dropout): Dropout(p=0.3, inplace=False)221 )222 (encoder): RobertaEncoder(223 (layer): ModuleList(224 (0-11): 12 x RobertaLayer(225 (attention): RobertaAttention(226 (self): RobertaSdpaSelfAttention(227 (query): Linear(in_features=768, out_features=768, bias=True)228 (key): Linear(in_features=768, out_features=768, bias=True)229 (value): Linear(in_features=768, out_features=768, bias=True)230 (dropout): Dropout(p=0.3, inplace=False)231 )232 (output): RobertaSelfOutput(233 (dense): Linear(in_features=768, out_features=768, bias=True)234 (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)235 (dropout): Dropout(p=0.3, inplace=False)236 )237 )238 (intermediate): RobertaIntermediate(239 (dense): Linear(in_features=768, out_features=3072, bias=True)240 (intermediate_act_fn): GELUActivation()241 )242 (output): RobertaOutput(243 (dense): Linear(in_features=3072, out_features=768, bias=True)244 (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)245 (dropout): Dropout(p=0.3, inplace=False)246 )247 )248 )249 )250 )251 (classifier): RobertaClassificationHead(252 (dense): Linear(in_features=768, out_features=768, bias=True)253 (dropout): Dropout(p=0.3, inplace=False)254 (out_proj): Linear(in_features=768, out_features=2, bias=True)255 )256)2572026-04-20 11:21:17,954 - INFO - ===== Parameter Summary =====2582026-04-20 11:21:17,963 - INFO - Total Parameters: 124,647,1702592026-04-20 11:21:17,970 - INFO - Trainable Parameters: 124,647,1702602026-04-20 11:21:17,980 - INFO - Non‑trainable Parameters: 02612026-04-20 11:21:17,986 - INFO - ===== Tokenizer Summary =====2622026-04-20 11:21:18,059 - INFO - Vocab size: 50265 | Special tokens: ['<s>', '</s>', '<unk>', '<pad>', '<mask>']2632026-04-20 11:21:18,067 - INFO - ===== End of Architecture Log =====2642026-04-20 11:21:18,559 - INFO - Loading dataset: DaniilOr/SemEval-2026-Task13 (A)2652026-04-20 11:21:20,637 - INFO - Tokenising dataset...2662026-04-20 11:21:20,809 - INFO - Running inference on 1000 examples...2672026-04-20 11:21:55,162 - INFO - Computing metrics for output_checkpoints/graphcodebert-mixcode-fft/checkpoint-1502682026-04-20 11:21:55,216 - INFO - ------------------------------2692026-04-20 11:21:55,223 - INFO - METRICS FOR SPLIT: test2702026-04-20 11:21:55,232 - INFO - Accuracy: 0.68702712026-04-20 11:21:55,239 - INFO - Precision: 0.67082722026-04-20 11:21:55,247 - INFO - Recall: 0.68702732026-04-20 11:21:55,256 - INFO - F1‑Score: 0.67842742026-04-20 11:21:55,260 - INFO - ------------------------------2752026-04-20 11:21:55,268 - INFO - Confusion Matrix:276[[636 141]277 [172 51]]2782026-04-20 11:21:55,280 - INFO - ✅ Metrics saved to test/inference/graphcodebert-mixcode-fft/checkpoint-150/metrics.json2792026-04-20 11:21:55,288 - INFO - ✅ Predictions saved to test/inference/graphcodebert-mixcode-fft/checkpoint-150/submission.csv2802026-04-20 11:22:18,401 - INFO - Loading model and tokenizer from: output_checkpoints/graphcodebert-mixcode-fft/checkpoint-1002812026-04-20 11:22:19,077 - INFO - ===== Model Architecture =====2822026-04-20 11:22:19,094 - INFO - 283RobertaForSequenceClassification(284 (roberta): RobertaModel(285 (embeddings): RobertaEmbeddings(286 (word_embeddings): Embedding(50265, 768, padding_idx=1)287 (position_embeddings): Embedding(514, 768, padding_idx=1)288 (token_type_embeddings): Embedding(1, 768)289 (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)290 (dropout): Dropout(p=0.3, inplace=False)291 )292 (encoder): RobertaEncoder(293 (layer): ModuleList(294 (0-11): 12 x RobertaLayer(295 (attention): RobertaAttention(296 (self): RobertaSdpaSelfAttention(297 (query): Linear(in_features=768, out_features=768, bias=True)298 (key): Linear(in_features=768, out_features=768, bias=True)299 (value): Linear(in_features=768, out_features=768, bias=True)300 (dropout): Dropout(p=0.3, inplace=False)301 )302 (output): RobertaSelfOutput(303 (dense): Linear(in_features=768, out_features=768, bias=True)304 (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)305 (dropout): Dropout(p=0.3, inplace=False)306 )307 )308 (intermediate): RobertaIntermediate(309 (dense): Linear(in_features=768, out_features=3072, bias=True)310 (intermediate_act_fn): GELUActivation()311 )312 (output): RobertaOutput(313 (dense): Linear(in_features=3072, out_features=768, bias=True)314 (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)315 (dropout): Dropout(p=0.3, inplace=False)316 )317 )318 )319 )320 )321 (classifier): RobertaClassificationHead(322 (dense): Linear(in_features=768, out_features=768, bias=True)323 (dropout): Dropout(p=0.3, inplace=False)324 (out_proj): Linear(in_features=768, out_features=2, bias=True)325 )326)3272026-04-20 11:22:19,112 - INFO - ===== Parameter Summary =====3282026-04-20 11:22:19,123 - INFO - Total Parameters: 124,647,1703292026-04-20 11:22:19,132 - INFO - Trainable Parameters: 124,647,1703302026-04-20 11:22:19,141 - INFO - Non‑trainable Parameters: 03312026-04-20 11:22:19,145 - INFO - ===== Tokenizer Summary =====3322026-04-20 11:22:19,195 - INFO - Vocab size: 50265 | Special tokens: ['<s>', '</s>', '<unk>', '<pad>', '<mask>']3332026-04-20 11:22:19,205 - INFO - ===== End of Architecture Log =====3342026-04-20 11:22:21,126 - INFO - Loading dataset: DaniilOr/SemEval-2026-Task13 (A)3352026-04-20 11:22:23,159 - INFO - Tokenising dataset...3362026-04-20 11:22:23,233 - INFO - Running inference on 1000 examples...3372026-04-20 11:22:57,170 - INFO - Computing metrics for output_checkpoints/graphcodebert-mixcode-fft/checkpoint-1003382026-04-20 11:22:57,283 - INFO - ------------------------------3392026-04-20 11:22:57,300 - INFO - METRICS FOR SPLIT: test3402026-04-20 11:22:57,312 - INFO - Accuracy: 0.73403412026-04-20 11:22:57,326 - INFO - Precision: 0.67043422026-04-20 11:22:57,337 - INFO - Recall: 0.73403432026-04-20 11:22:57,354 - INFO - F1‑Score: 0.69163442026-04-20 11:22:57,373 - INFO - ------------------------------3452026-04-20 11:22:57,392 - INFO - Confusion Matrix:346[[707 70]347 [196 27]]3482026-04-20 11:22:57,401 - INFO - ✅ Metrics saved to test/inference/graphcodebert-mixcode-fft/checkpoint-100/metrics.json3492026-04-20 11:22:57,412 - INFO - ✅ Predictions saved to test/inference/graphcodebert-mixcode-fft/checkpoint-100/submission.csv3502026-04-20 11:23:14,035 - INFO - Loading model and tokenizer from: output_checkpoints/graphcodebert-mixcode-fft/checkpoint-503512026-04-20 11:23:14,977 - INFO - ===== Model Architecture =====3522026-04-20 11:23:14,996 - INFO - 353RobertaForSequenceClassification(354 (roberta): RobertaModel(355 (embeddings): RobertaEmbeddings(356 (word_embeddings): Embedding(50265, 768, padding_idx=1)357 (position_embeddings): Embedding(514, 768, padding_idx=1)358 (token_type_embeddings): Embedding(1, 768)359 (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)360 (dropout): Dropout(p=0.3, inplace=False)361 )362 (encoder): RobertaEncoder(363 (layer): ModuleList(364 (0-11): 12 x RobertaLayer(365 (attention): RobertaAttention(366 (self): RobertaSdpaSelfAttention(367 (query): Linear(in_features=768, out_features=768, bias=True)368 (key): Linear(in_features=768, out_features=768, bias=True)369 (value): Linear(in_features=768, out_features=768, bias=True)370 (dropout): Dropout(p=0.3, inplace=False)371 )372 (output): RobertaSelfOutput(373 (dense): Linear(in_features=768, out_features=768, bias=True)374 (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)375 (dropout): Dropout(p=0.3, inplace=False)376 )377 )378 (intermediate): RobertaIntermediate(379 (dense): Linear(in_features=768, out_features=3072, bias=True)380 (intermediate_act_fn): GELUActivation()381 )382 (output): RobertaOutput(383 (dense): Linear(in_features=3072, out_features=768, bias=True)384 (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)385 (dropout): Dropout(p=0.3, inplace=False)386 )387 )388 )389 )390 )391 (classifier): RobertaClassificationHead(392 (dense): Linear(in_features=768, out_features=768, bias=True)393 (dropout): Dropout(p=0.3, inplace=False)394 (out_proj): Linear(in_features=768, out_features=2, bias=True)395 )396)3972026-04-20 11:23:15,018 - INFO - ===== Parameter Summary =====3982026-04-20 11:23:15,029 - INFO - Total Parameters: 124,647,1703992026-04-20 11:23:15,041 - INFO - Trainable Parameters: 124,647,1704002026-04-20 11:23:15,052 - INFO - Non‑trainable Parameters: 04012026-04-20 11:23:15,068 - INFO - ===== Tokenizer Summary =====4022026-04-20 11:23:15,164 - INFO - Vocab size: 50265 | Special tokens: ['<s>', '</s>', '<unk>', '<pad>', '<mask>']4032026-04-20 11:23:15,176 - INFO - ===== End of Architecture Log =====4042026-04-20 11:23:17,129 - INFO - Loading dataset: DaniilOr/SemEval-2026-Task13 (A)4052026-04-20 11:23:19,193 - INFO - Tokenising dataset...4062026-04-20 11:23:19,390 - INFO - Running inference on 1000 examples...4072026-04-20 11:23:53,670 - INFO - Computing metrics for output_checkpoints/graphcodebert-mixcode-fft/checkpoint-504082026-04-20 11:23:53,713 - INFO - ------------------------------4092026-04-20 11:23:53,719 - INFO - METRICS FOR SPLIT: test4102026-04-20 11:23:53,731 - INFO - Accuracy: 0.74004112026-04-20 11:23:53,740 - INFO - Precision: 0.66404122026-04-20 11:23:53,752 - INFO - Recall: 0.74004132026-04-20 11:23:53,761 - INFO - F1‑Score: 0.68794142026-04-20 11:23:53,773 - INFO - ------------------------------4152026-04-20 11:23:53,782 - INFO - Confusion Matrix:416[[720 57]417 [203 20]]4182026-04-20 11:23:53,793 - INFO - ✅ Metrics saved to test/inference/graphcodebert-mixcode-fft/checkpoint-50/metrics.json4192026-04-20 11:23:53,807 - INFO - ✅ Predictions saved to test/inference/graphcodebert-mixcode-fft/checkpoint-50/submission.csv420