duplicated block id: 1
size: 34 cleaned lines of code
in 2 files:
 - mdr/qa/basic_tokenizer.py (0:0)
 - mdr/retrieval/utils/basic_tokenizer.py (0:0)

duplicated block id: 2
size: 22 cleaned lines of code
in 2 files:
 - mdr/qa/basic_tokenizer.py (0:0)
 - mdr/retrieval/utils/basic_tokenizer.py (0:0)

duplicated block id: 3
size: 17 cleaned lines of code
in 2 files:
 - scripts/train_momentum.py (0:0)
 - scripts/train_mhop.py (0:0)

duplicated block id: 4
size: 17 cleaned lines of code
in 2 files:
 - mdr/qa/utils.py (0:0)
 - mdr/retrieval/utils/tokenizer.py (0:0)

duplicated block id: 5
size: 17 cleaned lines of code
in 2 files:
 - mdr/qa/utils.py (0:0)
 - mdr/retrieval/utils/tokenizer.py (0:0)

duplicated block id: 6
size: 19 cleaned lines of code
in 2 files:
 - mdr/qa/basic_tokenizer.py (0:0)
 - mdr/retrieval/utils/basic_tokenizer.py (0:0)

duplicated block id: 7
size: 19 cleaned lines of code
in 2 files:
 - mdr/qa/basic_tokenizer.py (0:0)
 - mdr/retrieval/utils/basic_tokenizer.py (0:0)

duplicated block id: 8
size: 15 cleaned lines of code
in 2 files:
 - mdr/qa/utils.py (0:0)
 - mdr/retrieval/utils/utils.py (0:0)

duplicated block id: 9
size: 15 cleaned lines of code
in 2 files:
 - mdr/qa/utils.py (0:0)
 - mdr/retrieval/utils/utils.py (0:0)

duplicated block id: 10
size: 16 cleaned lines of code
in 2 files:
 - mdr/qa/qa_dataset.py (0:0)
 - mdr/retrieval/data/data_utils.py (0:0)

duplicated block id: 11
size: 13 cleaned lines of code
in 2 files:
 - mdr/retrieval/data/sp_datasets.py (0:0)
 - mdr/retrieval/data/sp_datasets.py (0:0)

duplicated block id: 12
size: 21 cleaned lines of code
in 2 files:
 - mdr/qa/basic_tokenizer.py (0:0)
 - mdr/retrieval/utils/basic_tokenizer.py (0:0)

duplicated block id: 13
size: 12 cleaned lines of code
in 2 files:
 - mdr/qa/utils.py (0:0)
 - mdr/retrieval/utils/tokenizer.py (0:0)

duplicated block id: 14
size: 12 cleaned lines of code
in 3 files:
 - mdr/qa/qa_trainer.py (0:0)
 - mdr/retrieval/single_trainer.py (0:0)
 - mdr/retrieval/mhop_trainer.py (0:0)

duplicated block id: 15
size: 11 cleaned lines of code
in 2 files:
 - mdr/qa/utils.py (0:0)
 - mdr/retrieval/utils/tokenizer.py (0:0)

duplicated block id: 16
size: 11 cleaned lines of code
in 2 files:
 - mdr/retrieval/utils/mhop_utils.py (0:0)
 - mdr/retrieval/data/data_utils.py (0:0)

duplicated block id: 17
size: 9 cleaned lines of code
in 3 files:
 - mdr/qa/qa_trainer.py (0:0)
 - mdr/retrieval/single_trainer.py (0:0)
 - mdr/retrieval/mhop_trainer.py (0:0)

duplicated block id: 18
size: 13 cleaned lines of code
in 2 files:
 - mdr/qa/utils.py (0:0)
 - mdr/retrieval/utils/tokenizer.py (0:0)

duplicated block id: 19
size: 9 cleaned lines of code
in 2 files:
 - mdr/qa/utils.py (0:0)
 - mdr/retrieval/utils/tokenizer.py (0:0)

duplicated block id: 20
size: 13 cleaned lines of code
in 3 files:
 - mdr/qa/qa_trainer.py (0:0)
 - mdr/retrieval/single_trainer.py (0:0)
 - mdr/retrieval/mhop_trainer.py (0:0)

duplicated block id: 21
size: 12 cleaned lines of code
in 2 files:
 - mdr/qa/basic_tokenizer.py (0:0)
 - mdr/retrieval/utils/basic_tokenizer.py (0:0)

duplicated block id: 22
size: 8 cleaned lines of code
in 2 files:
 - mdr/retrieval/data/encode_datasets.py (0:0)
 - mdr/retrieval/data/fever_dataset.py (0:0)

duplicated block id: 23
size: 10 cleaned lines of code
in 2 files:
 - submitit/submitit_train_qa.py (0:0)
 - submitit/submitit_train.py (0:0)

duplicated block id: 24
size: 9 cleaned lines of code
in 2 files:
 - mdr/qa/utils.py (0:0)
 - mdr/retrieval/utils/tokenizer.py (0:0)

duplicated block id: 25
size: 9 cleaned lines of code
in 2 files:
 - mdr/qa/utils.py (0:0)
 - mdr/retrieval/utils/tokenizer.py (0:0)

duplicated block id: 26
size: 6 cleaned lines of code
in 4 files:
 - mdr/retrieval/models/retriever.py (0:0)
 - mdr/retrieval/models/retriever.py (0:0)
 - mdr/retrieval/models/unified_retriever.py (0:0)
 - mdr/retrieval/models/mhop_retriever.py (0:0)

duplicated block id: 27
size: 6 cleaned lines of code
in 2 files:
 - submitit/submitit_train_qa.py (0:0)
 - submitit/submitit_train.py (0:0)

duplicated block id: 28
size: 6 cleaned lines of code
in 2 files:
 - mdr/qa/utils.py (0:0)
 - mdr/retrieval/utils/tokenizer.py (0:0)

duplicated block id: 29
size: 6 cleaned lines of code
in 3 files:
 - mdr/qa/qa_trainer.py (0:0)
 - mdr/retrieval/single_trainer.py (0:0)
 - mdr/retrieval/mhop_trainer.py (0:0)

duplicated block id: 30
size: 6 cleaned lines of code
in 3 files:
 - mdr/qa/qa_trainer.py (0:0)
 - mdr/retrieval/single_trainer.py (0:0)
 - mdr/retrieval/mhop_trainer.py (0:0)

duplicated block id: 31
size: 8 cleaned lines of code
in 3 files:
 - mdr/qa/qa_trainer.py (0:0)
 - mdr/retrieval/single_trainer.py (0:0)
 - mdr/retrieval/mhop_trainer.py (0:0)

duplicated block id: 32
size: 8 cleaned lines of code
in 2 files:
 - mdr/qa/basic_tokenizer.py (0:0)
 - mdr/retrieval/utils/basic_tokenizer.py (0:0)

duplicated block id: 33
size: 6 cleaned lines of code
in 2 files:
 - mdr/qa/basic_tokenizer.py (0:0)
 - mdr/retrieval/utils/basic_tokenizer.py (0:0)

duplicated block id: 34
size: 6 cleaned lines of code
in 2 files:
 - mdr/qa/basic_tokenizer.py (0:0)
 - mdr/retrieval/utils/basic_tokenizer.py (0:0)

duplicated block id: 35
size: 6 cleaned lines of code
in 2 files:
 - mdr/qa/basic_tokenizer.py (0:0)
 - mdr/retrieval/utils/basic_tokenizer.py (0:0)