Loading scripts/pretrain_bert.sh +1 −0 Original line number Diff line number Diff line Loading @@ -10,6 +10,7 @@ python pretrain_bert.py \ --tokenizer-model-type bert-large-uncased \ --vocab-size 30522 \ --train-data wikipedia \ --presplit-sentences \ --loose-json \ --text-key text \ --split 1000,1,1 \ Loading scripts/pretrain_bert_distributed.sh +1 −0 Original line number Diff line number Diff line Loading @@ -17,6 +17,7 @@ python -m torch.distributed.launch $DISTRIBUTED_ARGS \ --tokenizer-model-type bert-large-uncased \ --vocab-size 30522 \ --train-data wikipedia \ --presplit-sentences \ --loose-json \ --text-key text \ --split 1000,1,1 \ Loading scripts/pretrain_bert_sentencepiece.sh +1 −0 Original line number Diff line number Diff line Loading @@ -10,6 +10,7 @@ python pretrain_bert.py \ --tokenizer-path tokenizer.model \ --vocab-size 30522 \ --train-data wikipedia \ --presplit-sentences \ --loose-json \ --text-key text \ --split 1000,1,1 \ Loading Loading
scripts/pretrain_bert.sh +1 −0 Original line number Diff line number Diff line Loading @@ -10,6 +10,7 @@ python pretrain_bert.py \ --tokenizer-model-type bert-large-uncased \ --vocab-size 30522 \ --train-data wikipedia \ --presplit-sentences \ --loose-json \ --text-key text \ --split 1000,1,1 \ Loading
scripts/pretrain_bert_distributed.sh +1 −0 Original line number Diff line number Diff line Loading @@ -17,6 +17,7 @@ python -m torch.distributed.launch $DISTRIBUTED_ARGS \ --tokenizer-model-type bert-large-uncased \ --vocab-size 30522 \ --train-data wikipedia \ --presplit-sentences \ --loose-json \ --text-key text \ --split 1000,1,1 \ Loading
scripts/pretrain_bert_sentencepiece.sh +1 −0 Original line number Diff line number Diff line Loading @@ -10,6 +10,7 @@ python pretrain_bert.py \ --tokenizer-path tokenizer.model \ --vocab-size 30522 \ --train-data wikipedia \ --presplit-sentences \ --loose-json \ --text-key text \ --split 1000,1,1 \ Loading