Apply isort and black reformatting

Signed-off-by: akoumpa <akoumpa@users.noreply.github.com>

nemo/collections/llm/api.py

@@ -23,8 +23,8 @@
 
 from nemo.lightning import AutoResume, NeMoLogger, OptimizerModule, Trainer, io
 from nemo.lightning.pytorch.callbacks import PEFT, ModelTransform
-from nemo.utils import logging
 from nemo.lightning.run import cli_entrypoint
+from nemo.utils import logging
 
 TokenizerType = Any
 

nemo/collections/llm/recipes/mistral.py

@@ -31,8 +31,8 @@
 from nemo.collections.llm.recipes.log.default import default_log, default_resume, tensorboard_logger
 from nemo.collections.llm.recipes.optim.adam import distributed_fused_adam_with_cosine_annealing
 from nemo.collections.llm.recipes.precision.mixed_precision import bf16_mixed
-from nemo.utils.exp_manager import TimingCallback
 from nemo.lightning.run import cli_factory
+from nemo.utils.exp_manager import TimingCallback
 
 NAME = "mistral"
 

nemo/collections/llm/recipes/mixtral_8x22b.py

@@ -32,8 +32,8 @@
 from nemo.collections.llm.recipes.optim.adam import distributed_fused_adam_with_cosine_annealing
 from nemo.lightning.pytorch.callbacks.megatron_comm_overlap import MegatronCommOverlapCallback
 from nemo.lightning.pytorch.callbacks.moe_token_drop import MegatronTokenDropCallback
-from nemo.utils.exp_manager import TimingCallback
 from nemo.lightning.run import cli_factory
+from nemo.utils.exp_manager import TimingCallback
 
 NAME = "mixtral_8x22b"
 

nemo/collections/llm/recipes/mixtral_8x7b.py

@@ -32,8 +32,8 @@
 from nemo.collections.llm.recipes.optim.adam import distributed_fused_adam_with_cosine_annealing
 from nemo.lightning.pytorch.callbacks.megatron_comm_overlap import MegatronCommOverlapCallback
 from nemo.lightning.pytorch.callbacks.moe_token_drop import MegatronTokenDropCallback
-from nemo.utils.exp_manager import TimingCallback
 from nemo.lightning.run import cli_factory
+from nemo.utils.exp_manager import TimingCallback
 
 NAME = "mixtral_8x7b"
 

nemo/collections/llm/recipes/mixtral_8x7b_16k.py

@@ -23,8 +23,8 @@
 from nemo.collections.llm.gpt.data.mock import MockDataModule
 from nemo.collections.llm.gpt.data.squad import SquadDataModule
 from nemo.collections.llm.recipes import mixtral_8x7b
-from nemo.utils.exp_manager import TimingCallback
 from nemo.lightning.run import cli_factory
+from nemo.utils.exp_manager import TimingCallback
 
 NAME = "mixtral_8x7b_16k"
 

nemo/collections/llm/recipes/mixtral_8x7b_64k.py

@@ -23,8 +23,8 @@
 from nemo.collections.llm.gpt.data.mock import MockDataModule
 from nemo.collections.llm.gpt.data.squad import SquadDataModule
 from nemo.collections.llm.recipes import mixtral_8x7b
-from nemo.utils.exp_manager import TimingCallback
 from nemo.lightning.run import cli_factory
+from nemo.utils.exp_manager import TimingCallback
 
 NAME = "mixtral_8x7b_64k"
 

nemo/collections/llm/recipes/nemotron3_4b.py

@@ -23,8 +23,8 @@
 from nemo.collections.llm.recipes.log.default import default_log, default_resume, tensorboard_logger
 from nemo.collections.llm.recipes.nemotron import nemotron_model, nemotron_trainer
 from nemo.collections.llm.recipes.optim.adam import distributed_fused_adam_with_cosine_annealing
-from nemo.utils.exp_manager import TimingCallback
 from nemo.lightning.run import cli_factory
+from nemo.utils.exp_manager import TimingCallback
 
 NAME = "nemotron3_4b"
 

nemo/collections/llm/recipes/nemotron3_8b.py

@@ -26,8 +26,8 @@
 from nemo.collections.llm.recipes.log.default import default_log, default_resume, tensorboard_logger
 from nemo.collections.llm.recipes.nemotron import nemotron_model, nemotron_trainer
 from nemo.collections.llm.recipes.optim.adam import distributed_fused_adam_with_cosine_annealing
-from nemo.utils.exp_manager import TimingCallback
 from nemo.lightning.run import cli_factory
+from nemo.utils.exp_manager import TimingCallback
 
 NAME = "nemotron3_8b"
 

nemo/collections/llm/recipes/nemotron4_15b.py

@@ -23,8 +23,8 @@
 from nemo.collections.llm.recipes.log.default import default_log, default_resume, tensorboard_logger
 from nemo.collections.llm.recipes.nemotron import nemotron_model, nemotron_trainer
 from nemo.collections.llm.recipes.optim.adam import distributed_fused_adam_with_cosine_annealing
-from nemo.utils.exp_manager import TimingCallback
 from nemo.lightning.run import cli_factory
+from nemo.utils.exp_manager import TimingCallback
 
 NAME = "nemotron4_15b"
 

nemo/collections/llm/recipes/nemotron4_15b_16k.py

@@ -23,8 +23,8 @@
 from nemo.collections.llm.recipes.log.default import default_log, default_resume, tensorboard_logger
 from nemo.collections.llm.recipes.nemotron import nemotron_model, nemotron_trainer
 from nemo.collections.llm.recipes.optim.adam import distributed_fused_adam_with_cosine_annealing
-from nemo.utils.exp_manager import TimingCallback
 from nemo.lightning.run import cli_factory
+from nemo.utils.exp_manager import TimingCallback
 
 NAME = "nemotron4_15b_16k"
 

nemo/collections/llm/recipes/nemotron4_15b_64k.py

@@ -23,8 +23,8 @@
 from nemo.collections.llm.recipes.log.default import default_log, default_resume, tensorboard_logger
 from nemo.collections.llm.recipes.nemotron import nemotron_model, nemotron_trainer
 from nemo.collections.llm.recipes.optim.adam import distributed_fused_adam_with_cosine_annealing
-from nemo.utils.exp_manager import TimingCallback
 from nemo.lightning.run import cli_factory
+from nemo.utils.exp_manager import TimingCallback
 
 NAME = "nemotron4_15b_64k"
 

nemo/collections/llm/recipes/nemotron4_22b.py

@@ -23,8 +23,8 @@
 from nemo.collections.llm.recipes.log.default import default_log, default_resume, tensorboard_logger
 from nemo.collections.llm.recipes.nemotron import nemotron_model, nemotron_trainer
 from nemo.collections.llm.recipes.optim.adam import distributed_fused_adam_with_cosine_annealing
-from nemo.utils.exp_manager import TimingCallback
 from nemo.lightning.run import cli_factory
+from nemo.utils.exp_manager import TimingCallback
 
 NAME = "nemotron4_22b"
 

nemo/collections/llm/recipes/nemotron4_22b_16k.py

@@ -23,8 +23,8 @@
 from nemo.collections.llm.recipes.log.default import default_log, default_resume, tensorboard_logger
 from nemo.collections.llm.recipes.nemotron import nemotron_model, nemotron_trainer
 from nemo.collections.llm.recipes.optim.adam import distributed_fused_adam_with_cosine_annealing
-from nemo.utils.exp_manager import TimingCallback
 from nemo.lightning.run import cli_factory
+from nemo.utils.exp_manager import TimingCallback
 
 NAME = "nemotron4_22b_16k"
 

nemo/collections/llm/recipes/nemotron4_22b_64k.py

@@ -23,8 +23,8 @@
 from nemo.collections.llm.recipes.log.default import default_log, default_resume, tensorboard_logger
 from nemo.collections.llm.recipes.nemotron import nemotron_model, nemotron_trainer
 from nemo.collections.llm.recipes.optim.adam import distributed_fused_adam_with_cosine_annealing
-from nemo.utils.exp_manager import TimingCallback
 from nemo.lightning.run import cli_factory
+from nemo.utils.exp_manager import TimingCallback
 
 NAME = "nemotron4_22b_64k"
 

nemo/collections/llm/recipes/nemotron4_340b.py

@@ -26,8 +26,8 @@
 from nemo.collections.llm.recipes.log.default import default_log, default_resume, tensorboard_logger
 from nemo.collections.llm.recipes.nemotron import nemotron_model, nemotron_trainer
 from nemo.collections.llm.recipes.optim.adam import distributed_fused_adam_with_cosine_annealing
-from nemo.utils.exp_manager import TimingCallback
 from nemo.lightning.run import cli_factory
+from nemo.utils.exp_manager import TimingCallback
 
 NAME = "nemotron4_340b"
 

nemo/collections/llm/recipes/optim/adam.py

@@ -16,8 +16,9 @@
 
 import nemo_run as run
 from megatron.core.optimizer import OptimizerConfig
-from nemo.lightning.run import cli_factory
+
 from nemo.lightning.pytorch.optim import CosineAnnealingScheduler, MegatronOptimizerModule, OptimizerModule
+from nemo.lightning.run import cli_factory
 
 
 @cli_factory

nemo/lightning/run/cli.py

@@ -28,4 +28,3 @@ def wrapper(*args, **kwargs):
         return wrapper
 
     return decorator
-