File size: 3,222 Bytes
caed328 4d2bc22 caed328 | 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 | 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
|