2026-04-23 14:54:53,797 - INFO - Loading model and tokenizer from: output_checkpoints/unixcoder-base/final_model
2026-04-23 14:54:53,967 - INFO - ===== Model Architecture =====
2026-04-23 14:54:53,969 - INFO - 
RobertaForSequenceClassification(
  (roberta): RobertaModel(
    (embeddings): RobertaEmbeddings(
      (word_embeddings): Embedding(51416, 768, padding_idx=1)
      (position_embeddings): Embedding(1026, 768, padding_idx=1)
      (token_type_embeddings): Embedding(10, 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)
  )
)
2026-04-23 14:54:53,972 - INFO - ===== Parameter Summary =====
2026-04-23 14:54:53,973 - INFO - Total Parameters:         125,931,266
2026-04-23 14:54:53,974 - INFO - Trainable Parameters:     125,931,266
2026-04-23 14:54:53,975 - INFO - Non-trainable Parameters: 0
2026-04-23 14:54:53,977 - INFO - ===== Tokenizer Summary =====
2026-04-23 14:54:53,993 - INFO - Vocab size: 51416 | Special tokens: ['<s>', '</s>', '<unk>', '<pad>', '<mask>']
2026-04-23 14:54:53,995 - INFO - ===== End of Architecture Log =====
2026-04-23 14:54:54,167 - INFO - Loading dataset: DaniilOr/SemEval-2026-Task13 (A)
2026-04-23 14:54:54,652 - INFO - Tokenizing dataset...
2026-04-23 14:54:55,793 - INFO - Running inference on 1000 examples...
2026-04-23 14:55:23,416 - INFO - Calculating classification metrics...
2026-04-23 14:55:23,435 - INFO - ------------------------------
2026-04-23 14:55:23,436 - INFO - METRICS FOR SPLIT: test
2026-04-23 14:55:23,438 - INFO - Accuracy:  0.7420
2026-04-23 14:55:23,439 - INFO - Precision: 0.6199
2026-04-23 14:55:23,441 - INFO - Recall:    0.7420
2026-04-23 14:55:23,442 - INFO - F1-Score:  0.6681
2026-04-23 14:55:23,443 - INFO - ------------------------------
2026-04-23 14:55:23,446 - INFO - Confusion Matrix:
[[738  39]
 [219   4]]
2026-04-23 14:55:23,448 - INFO - ✅ Predictions saved to test/inference/unixcoder-base/submission.csv