Update quality tooling for formatting (#21480)

* Result of black 23.1

* Update target to Python 3.7

* Switch flake8 to ruff

* Configure isort

* Configure isort

* Apply isort with line limit

* Put the right black version

* adapt black in check copies

* Fix copies

examples/research_projects/distillation/distiller.py

@@ -21,14 +21,14 @@ import time
 
 import psutil
 import torch
+from grouped_batch_sampler import GroupedBatchSampler, create_lengths_groups
+from lm_seqs_dataset import LmSeqsDataset
 from torch import nn
 from torch.optim import AdamW
 from torch.utils.data import BatchSampler, DataLoader, RandomSampler
 from torch.utils.data.distributed import DistributedSampler
 from tqdm import tqdm
 
-from grouped_batch_sampler import GroupedBatchSampler, create_lengths_groups
-from lm_seqs_dataset import LmSeqsDataset
 from transformers import get_linear_schedule_with_warmup
 from utils import logger
 

examples/research_projects/distillation/run_squad_w_distillation.py

@@ -189,7 +189,6 @@ def train(args, train_dataset, model, tokenizer, teacher=None):
     for _ in train_iterator:
         epoch_iterator = tqdm(train_dataloader, desc="Iteration", disable=args.local_rank not in [-1, 0])
         for step, batch in enumerate(epoch_iterator):
-
             # Skip past any already trained steps if resuming training
             if steps_trained_in_current_epoch > 0:
                 steps_trained_in_current_epoch -= 1

examples/research_projects/distillation/train.py

@@ -24,9 +24,9 @@ import shutil
 
 import numpy as np
 import torch
-
 from distiller import Distiller
 from lm_seqs_dataset import LmSeqsDataset
+
 from transformers import (
     BertConfig,
     BertForMaskedLM,