upload inference results

inference/graphcodebert-base-lowLR-highBatchSize/checkpoint-1022/inference.log

@@ -0,0 +1,62 @@
+2026-04-28 04:22:23,122 - INFO - Loading model and tokenizer from: checkpoints/graphcodebert-base-lowLR-highBatchSize/checkpoint-1022
+2026-04-28 04:22:23,386 - INFO - ===== Model Architecture =====
+2026-04-28 04:22:23,387 - 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=0.3, 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=0.3, 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=0.3, 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=0.3, inplace=False)
+          )
+        )
+      )
+    )
+  )
+  (classifier): RobertaClassificationHead(
+    (dense): Linear(in_features=768, out_features=768, bias=True)
+    (dropout): Dropout(p=0.3, inplace=False)
+    (out_proj): Linear(in_features=768, out_features=2, bias=True)
+  )
+)
+2026-04-28 04:22:23,389 - INFO - ===== Parameter Summary =====
+2026-04-28 04:22:23,390 - INFO - Total Parameters:         124,647,170
+2026-04-28 04:22:23,391 - INFO - Trainable Parameters:     124,647,170
+2026-04-28 04:22:23,392 - INFO - Non-trainable Parameters: 0
+2026-04-28 04:22:23,393 - INFO - ===== Tokenizer Summary =====
+2026-04-28 04:22:23,408 - INFO - Vocab size: 50265 | Special tokens: ['<s>', '</s>', '<unk>', '<pad>', '<mask>']
+2026-04-28 04:22:23,409 - INFO - ===== End of Architecture Log =====
+2026-04-28 04:22:23,831 - INFO - Loading dataset from: /kaggle/input/datasets/dzung271828/semeval/Task_A/test.parquet
+2026-04-28 04:22:23,832 - INFO - Detected .parquet file – loading directly with datasets (memory-mapped)
+2026-04-28 04:22:30,067 - INFO - Loaded Parquet file with 500000 examples (memory-mapped)
+2026-04-28 04:22:30,068 - INFO - Columns found: ['ID', 'code', '__index_level_0__']
+2026-04-28 04:22:30,072 - INFO - Tokenizing dataset...
+2026-04-28 04:27:31,809 - INFO - Running inference on 500000 examples...
+2026-04-28 08:29:06,190 - WARNING - No 'label' column found. Skipping metric calculation.
+2026-04-28 08:29:11,935 - INFO - ✅ Predictions saved to test/inference/graphcodebert-base-lowLR-highBatchSize/checkpoint-1022/checkpoint-1022-submission.csv