2026-04-24 17:12:05,101 - INFO - Loading model and tokenizer from: output_checkpoints/graphcodebert-base-lowLR-highBatchSize/checkpoint-450
2026-04-24 17:12:05,271 - INFO - ===== Model Architecture =====
2026-04-24 17:12:05,274 - 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)
  )
)
2026-04-24 17:12:05,276 - INFO - ===== Parameter Summary =====
2026-04-24 17:12:05,277 - INFO - Total Parameters:         124,647,170
2026-04-24 17:12:05,278 - INFO - Trainable Parameters:     124,647,170
2026-04-24 17:12:05,279 - INFO - Non-trainable Parameters: 0
2026-04-24 17:12:05,282 - INFO - ===== Tokenizer Summary =====
2026-04-24 17:12:05,297 - INFO - Vocab size: 50265 | Special tokens: ['<s>', '</s>', '<unk>', '<pad>', '<mask>']
2026-04-24 17:12:05,299 - INFO - ===== End of Architecture Log =====
2026-04-24 17:12:05,463 - INFO - Loading dataset: DaniilOr/SemEval-2026-Task13 (A)
2026-04-24 17:12:05,959 - INFO - Tokenizing dataset...
2026-04-24 17:12:05,993 - INFO - Running inference on 1000 examples...
2026-04-24 17:12:36,750 - INFO - Calculating classification metrics...
2026-04-24 17:12:36,769 - INFO - ------------------------------
2026-04-24 17:12:36,771 - INFO - METRICS FOR SPLIT: test
2026-04-24 17:12:36,772 - INFO - Accuracy:  0.7380
2026-04-24 17:12:36,774 - INFO - Precision: 0.6753
2026-04-24 17:12:36,776 - INFO - Recall:    0.7380
2026-04-24 17:12:36,777 - INFO - F1-Score:  0.6952
2026-04-24 17:12:36,780 - INFO - ------------------------------
2026-04-24 17:12:36,781 - INFO - Confusion Matrix:
[[710  67]
 [195  28]]
2026-04-24 17:12:36,783 - INFO - ✅ Metrics saved to test/inference/graphcodebert-base-lowLR-highBatchSize/checkpoint-450/metrics.json
2026-04-24 17:12:36,786 - INFO - ✅ Predictions saved to test/inference/graphcodebert-base-lowLR-highBatchSize/checkpoint-450/submission.csv