Loading megatron/checkpointing.py +1 −2 Original line number Diff line number Diff line Loading @@ -22,7 +22,6 @@ import numpy as np import torch from torch.nn.parallel import DistributedDataParallel as torchDDP from torch.nn.parallel.distributed import DistributedDataParallel as torchDDP from megatron import mpu, get_args from megatron import get_args Loading pretrain_ict.py +0 −1 Original line number Diff line number Diff line Loading @@ -24,7 +24,6 @@ from megatron import print_rank_0 from megatron import get_timers from megatron import mpu from megatron.data.dataset_utils import build_train_valid_test_datasets from megatron.model import ICTBertModel from megatron.training import pretrain from megatron.utils import reduce_losses from megatron.model.realm_model import general_ict_model_provider Loading Loading
megatron/checkpointing.py +1 −2 Original line number Diff line number Diff line Loading @@ -22,7 +22,6 @@ import numpy as np import torch from torch.nn.parallel import DistributedDataParallel as torchDDP from torch.nn.parallel.distributed import DistributedDataParallel as torchDDP from megatron import mpu, get_args from megatron import get_args Loading
pretrain_ict.py +0 −1 Original line number Diff line number Diff line Loading @@ -24,7 +24,6 @@ from megatron import print_rank_0 from megatron import get_timers from megatron import mpu from megatron.data.dataset_utils import build_train_valid_test_datasets from megatron.model import ICTBertModel from megatron.training import pretrain from megatron.utils import reduce_losses from megatron.model.realm_model import general_ict_model_provider Loading