File size: 3,414 Bytes
9064b12 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 | 2026-04-23 15:05:31,479 - INFO - Loading model and tokenizer from: output_checkpoints/codebert-base/final_model
2026-04-23 15:05:31,661 - INFO - ===== Model Architecture =====
2026-04-23 15:05:31,663 - 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)
)
)
2026-04-23 15:05:31,666 - INFO - ===== Parameter Summary =====
2026-04-23 15:05:31,667 - INFO - Total Parameters: 124,647,170
2026-04-23 15:05:31,668 - INFO - Trainable Parameters: 124,647,170
2026-04-23 15:05:31,670 - INFO - Non-trainable Parameters: 0
2026-04-23 15:05:31,671 - INFO - ===== Tokenizer Summary =====
2026-04-23 15:05:31,689 - INFO - Vocab size: 50265 | Special tokens: ['<s>', '</s>', '<unk>', '<pad>', '<mask>']
2026-04-23 15:05:31,691 - INFO - ===== End of Architecture Log =====
2026-04-23 15:05:31,855 - INFO - Loading dataset: DaniilOr/SemEval-2026-Task13 (A)
2026-04-23 15:05:32,531 - INFO - Tokenizing dataset...
2026-04-23 15:05:33,814 - INFO - Running inference on 1000 examples...
2026-04-23 15:06:01,067 - INFO - Calculating classification metrics...
2026-04-23 15:06:01,086 - INFO - ------------------------------
2026-04-23 15:06:01,088 - INFO - METRICS FOR SPLIT: test
2026-04-23 15:06:01,089 - INFO - Accuracy: 0.7770
2026-04-23 15:06:01,091 - INFO - Precision: 0.6037
2026-04-23 15:06:01,092 - INFO - Recall: 0.7770
2026-04-23 15:06:01,094 - INFO - F1-Score: 0.6795
2026-04-23 15:06:01,095 - INFO - ------------------------------
2026-04-23 15:06:01,098 - INFO - Confusion Matrix:
[[777 0]
[223 0]]
2026-04-23 15:06:01,101 - INFO - ✅ Predictions saved to test/inference/codebert-base/submission.csv
|