Loading examples/pretrain_t5_distributed_with_mp.sh +0 −1 Original line number Diff line number Diff line Loading @@ -25,7 +25,6 @@ python -m torch.distributed.launch $DISTRIBUTED_ARGS \ --decoder-seq-length 128 \ --micro-batch-size 16 \ --global-batch-size 2048 \ --seq-length 512 \ --max-position-embeddings 512 \ --train-iters 1000000 \ --lr-decay-iters 1000000 \ Loading Loading
examples/pretrain_t5_distributed_with_mp.sh +0 −1 Original line number Diff line number Diff line Loading @@ -25,7 +25,6 @@ python -m torch.distributed.launch $DISTRIBUTED_ARGS \ --decoder-seq-length 128 \ --micro-batch-size 16 \ --global-batch-size 2048 \ --seq-length 512 \ --max-position-embeddings 512 \ --train-iters 1000000 \ --lr-decay-iters 1000000 \ Loading
