2026-04-16 10:42:50,167 - INFO - Loading model and tokenizer from: checkpoints/graphcodebert-robust/checkpoint-200
2026-04-16 10:42:50,469 - INFO - ===== Model Architecture =====
2026-04-16 10:42:50,471 - 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 10:42:50,475 - INFO - ===== Parameter Summary =====
2026-04-16 10:42:50,478 - INFO - Total Parameters:         124,647,170
2026-04-16 10:42:50,480 - INFO - Trainable Parameters:     124,647,170
2026-04-16 10:42:50,483 - INFO - Non-trainable Parameters: 0
2026-04-16 10:42:50,485 - INFO - ===== Tokenizer Summary =====
2026-04-16 10:42:50,501 - INFO - Vocab size: 50265 | Special tokens: ['<s>', '</s>', '<unk>', '<pad>', '<mask>']
2026-04-16 10:42:50,503 - INFO - ===== End of Architecture Log =====
2026-04-16 10:42:50,964 - INFO - Loading dataset: dzungpham/SemEval-2026-TaskA-dataset (default)
2026-04-16 10:43:17,351 - WARNING - Default loading failed due to schema mismatch: An error occurred while generating the dataset
2026-04-16 10:43:17,353 - INFO - Attempting to load split 'test' using data_files...
2026-04-16 10:43:21,380 - INFO - Tokenizing dataset...
2026-04-16 10:48:34,156 - INFO - Running inference on 500000 examples...
2026-04-16 15:41:53,221 - WARNING - No 'label' column found in dataset. Skipping metric calculation.
2026-04-16 15:41:59,383 - INFO - ✅ Predictions saved to test/inference/graphcodebert-robust/submission.csv