duplicated block id: 1
size: 40 cleaned lines of code
in 2 files:
 - src/graph_construction.py (0:0)
 - src/prepare_data.py (0:0)

duplicated block id: 2
size: 26 cleaned lines of code
in 2 files:
 - src/fairseq/fairseq/tasks/masked_lm.py (0:0)
 - src/fairseq/fairseq/tasks/multilingual_masked_lm.py (0:0)

duplicated block id: 3
size: 24 cleaned lines of code
in 2 files:
 - src/fairseq/fairseq/modules/longformer_multihead_attention.py (0:0)
 - src/fairseq/fairseq/modules/multihead_attention.py (0:0)

duplicated block id: 4
size: 24 cleaned lines of code
in 2 files:
 - src/fairseq/fairseq/benchmark/dummy_lm.py (0:0)
 - src/fairseq/fairseq/benchmark/dummy_masked_lm.py (0:0)

duplicated block id: 5
size: 12 cleaned lines of code
in 2 files:
 - src/fairseq/fairseq/models/roberta/model.py (0:0)
 - src/fairseq/fairseq/model_parallel/models/roberta/model.py (0:0)

duplicated block id: 6
size: 11 cleaned lines of code
in 2 files:
 - src/fairseq/fairseq/modules/longformer_multihead_attention.py (0:0)
 - src/fairseq/fairseq/modules/multihead_attention.py (0:0)

duplicated block id: 7
size: 11 cleaned lines of code
in 3 files:
 - src/fairseq/fairseq/models/roberta/model_camembert.py (0:0)
 - src/fairseq/fairseq/models/roberta/model_xlmr.py (0:0)
 - src/fairseq/fairseq/models/roberta/model.py (0:0)

duplicated block id: 8
size: 11 cleaned lines of code
in 2 files:
 - src/fairseq/fairseq/criterions/sentence_prediction.py (0:0)
 - src/fairseq/fairseq/criterions/sentence_ranking.py (0:0)

duplicated block id: 9
size: 10 cleaned lines of code
in 2 files:
 - src/fairseq/fairseq/model_parallel/criterions/vocab_parallel_cross_entropy.py (0:0)
 - src/fairseq/fairseq/criterions/cross_entropy.py (0:0)

duplicated block id: 10
size: 7 cleaned lines of code
in 2 files:
 - src/fairseq/fairseq/models/roberta/model.py (0:0)
 - src/fairseq/fairseq/model_parallel/models/roberta/model.py (0:0)

duplicated block id: 11
size: 6 cleaned lines of code
in 2 files:
 - src/fairseq/fairseq/models/roberta/model.py (0:0)
 - src/fairseq/fairseq/model_parallel/models/roberta/model.py (0:0)

duplicated block id: 12
size: 6 cleaned lines of code
in 2 files:
 - src/fairseq/fairseq/models/roberta/model.py (0:0)
 - src/fairseq/fairseq/model_parallel/models/roberta/model.py (0:0)

duplicated block id: 13
size: 6 cleaned lines of code
in 2 files:
 - src/fairseq/fairseq/data/append_token_dataset.py (0:0)
 - src/fairseq/fairseq/data/prepend_token_dataset.py (0:0)

duplicated block id: 14
size: 8 cleaned lines of code
in 3 files:
 - src/fairseq/fairseq/data/monolingual_dataset.py (0:0)
 - src/fairseq/fairseq/data/audio/raw_audio_dataset.py (0:0)
 - src/fairseq/fairseq/data/subsample_dataset.py (0:0)

duplicated block id: 15
size: 11 cleaned lines of code
in 2 files:
 - src/fairseq/fairseq/optim/nag.py (0:0)
 - src/fairseq/fairseq/optim/sgd.py (0:0)

duplicated block id: 16
size: 6 cleaned lines of code
in 2 files:
 - src/fairseq/fairseq/benchmark/dummy_lm.py (0:0)
 - src/fairseq/fairseq/benchmark/dummy_masked_lm.py (0:0)

duplicated block id: 17
size: 8 cleaned lines of code
in 2 files:
 - src/fairseq/fairseq/tasks/multilingual_denoising.py (0:0)
 - src/fairseq/fairseq/tasks/multilingual_masked_lm.py (0:0)

duplicated block id: 18
size: 19 cleaned lines of code
in 2 files:
 - src/fairseq/fairseq/models/roberta/model.py (0:0)
 - src/fairseq/fairseq/model_parallel/models/roberta/model.py (0:0)

duplicated block id: 19
size: 7 cleaned lines of code
in 2 files:
 - src/fairseq/fairseq/tasks/sentence_prediction.py (0:0)
 - src/fairseq/fairseq/tasks/sentence_ranking.py (0:0)

duplicated block id: 20
size: 8 cleaned lines of code
in 2 files:
 - src/fairseq/fairseq/models/fairseq_model.py (0:0)
 - src/fairseq/fairseq/models/fairseq_model.py (0:0)

duplicated block id: 21
size: 7 cleaned lines of code
in 2 files:
 - src/fairseq/fairseq/models/fairseq_incremental_decoder.py (0:0)
 - src/fairseq/fairseq/models/fairseq_decoder.py (0:0)

duplicated block id: 22
size: 6 cleaned lines of code
in 10 files:
 - src/fairseq/fairseq/model_parallel/criterions/vocab_parallel_cross_entropy.py (0:0)
 - src/fairseq/fairseq/criterions/sentence_prediction.py (0:0)
 - src/fairseq/fairseq/criterions/label_smoothed_cross_entropy.py (0:0)
 - src/fairseq/fairseq/criterions/label_smoothed_cross_entropy_with_alignment.py (0:0)
 - src/fairseq/fairseq/criterions/nat_loss.py (0:0)
 - src/fairseq/fairseq/criterions/adaptive_loss.py (0:0)
 - src/fairseq/fairseq/criterions/masked_lm.py (0:0)
 - src/fairseq/fairseq/criterions/legacy_masked_lm.py (0:0)
 - src/fairseq/fairseq/criterions/sentence_ranking.py (0:0)
 - src/fairseq/fairseq/criterions/cross_entropy.py (0:0)