def training_step(self, batch, batch_idx):
    x, y, z = batch
    out = self.encoder(x)
    loss = self.loss(out, x)
    return loss

# Multiple optimizers (e.g.: GANs)
def training_step(self, batch, batch_idx, optimizer_idx):
    if optimizer_idx == 0:
        # do training_step with encoder
    if optimizer_idx == 1:
        # do training_step with decoder
        
# Truncated back-propagation through time
def training_step(self, batch, batch_idx, hiddens):
    # hiddens are the hidden states from the previous truncated backprop step
    ...
    out, hiddens = self.lstm(data, hiddens)
    ...
    return {'loss': loss, 'hiddens': hiddens}

# most cases
def configure_optimizers(self):
    opt = Adam(self.parameters(), lr=1e-3)
    return opt

# multiple optimizer case (e.g.: GAN)
def configure_optimizers(self):
    generator_opt = Adam(self.model_gen.parameters(), lr=0.01)
    disriminator_opt = Adam(self.model_disc.parameters(), lr=0.02)
    return generator_opt, disriminator_opt

# example with learning rate schedulers
def configure_optimizers(self):
    generator_opt = Adam(self.model_gen.parameters(), lr=0.01)
    disriminator_opt = Adam(self.model_disc.parameters(), lr=0.02)
    discriminator_sched = CosineAnnealing(discriminator_opt, T_max=10)
    return [generator_opt, disriminator_opt], [discriminator_sched]

# example with step-based learning rate schedulers
def configure_optimizers(self):
    gen_opt = Adam(self.model_gen.parameters(), lr=0.01)
    dis_opt = Adam(self.model_disc.parameters(), lr=0.02)
    gen_sched = {'scheduler': ExponentialLR(gen_opt, 0.99),
                 'interval': 'step'}  # called after each training step
    dis_sched = CosineAnnealing(discriminator_opt, T_max=10) # called every epoch
    return [gen_opt, dis_opt], [gen_sched, dis_sched]

# example with optimizer frequencies
# see training procedure in `Improved Training of Wasserstein GANs`, Algorithm 1
# https://arxiv.org/abs/1704.00028
def configure_optimizers(self):
    gen_opt = Adam(self.model_gen.parameters(), lr=0.01)
    dis_opt = Adam(self.model_disc.parameters(), lr=0.02)
    n_critic = 5
    return (
        {'optimizer': dis_opt, 'frequency': n_critic},
        {'optimizer': gen_opt, 'frequency': 1}
    )

values = {'loss': loss, 'acc': acc, ..., 'metric_n': metric_n}
self.log_dict(values)

class LitModel(pl.LightningModule):

    def __init__(...):

    def forward(...):

    def training_step(...)

    def training_step_end(...)

    def training_epoch_end(...)

    def validation_step(...)

    def validation_step_end(...)

    def validation_epoch_end(...)

    def test_step(...)

    def test_step_end(...)

    def test_epoch_end(...)

    def configure_optimizers(...)

    def any_extra_hook(...)

def fit(...):
    on_fit_start()

    if global_rank == 0:
        # prepare data is called on GLOBAL_ZERO only
        prepare_data()

    for gpu/tpu in gpu/tpus:
        train_on_device(model.copy())

    on_fit_end()

def train_on_device(model):
    # setup is called PER DEVICE
    setup()
    configure_optimizers()
    on_pretrain_routine_start()

    for epoch in epochs:
        train_loop()

    teardown()

def train_loop():
    on_train_epoch_start()
    train_outs = []
    for train_batch in train_dataloader():
        on_train_batch_start()

        # ----- train_step methods -------
        out = training_step(batch)
        train_outs.append(out)

        loss = out.loss

        backward()
        on_after_backward()
        optimizer_step()
        on_before_zero_grad()
        optimizer_zero_grad()

        on_train_batch_end(out)

        if should_check_val:
            val_loop()

    # end training epoch
    logs = training_epoch_end(outs)

def val_loop():
    model.eval()
    torch.set_grad_enabled(False)

    on_validation_epoch_start()
    val_outs = []
    for val_batch in val_dataloader():
        on_validation_batch_start()

        # -------- val step methods -------
        out = validation_step(val_batch)
        val_outs.append(out)

        on_validation_batch_end(out)

    validation_epoch_end(val_outs)
    on_validation_epoch_end()

    # set up for train
    model.train()
    torch.set_grad_enabled(True)

# default used by the Trainer (no scaling of batch size)
trainer = Trainer(auto_scale_batch_size=None)

# run batch size scaling, result overrides hparams.batch_size
trainer = Trainer(auto_scale_batch_size='binsearch')

# call tune to find the batch size
trainer.tune(model)

# run learning rate finder, results override hparams.learning_rate
trainer = Trainer(auto_lr_find=True)

# run learning rate finder, results override hparams.my_lr_arg
trainer = Trainer(auto_lr_find='my_lr_arg')

# call tune to find the lr
trainer.tune(model)

# default used by the Trainer
trainer = Trainer(precision=32)

# 16-bit precision
trainer = Trainer(precision=16, gpus=1)

# default used by the Trainer
trainer = Trainer(val_check_interval=1.0)

# check validation set 4 times during a training epoch
trainer = Trainer(val_check_interval=0.25)

# check validation set every 1000 training batches
# use this when using iterableDataset and your dataset has no length
# (ie: production cases with streaming data)
trainer = Trainer(val_check_interval=1000)

# default used by the Trainer (ie: train on CPU)
trainer = Trainer(gpus=None)

# equivalent
trainer = Trainer(gpus=0)

# int: train on 2 gpus
trainer = Trainer(gpus=2)

# list: train on GPUs 1, 4 (by bus ordering)
trainer = Trainer(gpus=[1, 4])
trainer = Trainer(gpus='1, 4') # equivalent

# -1: train on all gpus
trainer = Trainer(gpus=-1)
trainer = Trainer(gpus='-1') # equivalent

# combine with num_nodes to train on multiple GPUs across nodes
# uses 8 gpus in total
trainer = Trainer(gpus=2, num_nodes=4)

# train only on GPUs 1 and 4 across nodes
trainer = Trainer(gpus=[1, 4], num_nodes=4)

# default used by the Trainer
trainer = Trainer(limit_train_batches=1.0)

# run through only 25% of the training set each epoch
trainer = Trainer(limit_train_batches=0.25)

# run through only 10 batches of the training set each epoch
trainer = Trainer(limit_train_batches=10)

# default used by the Trainer
trainer = Trainer(fast_dev_run=False)

# runs 1 train, val, test batch and program ends
trainer = Trainer(fast_dev_run=True)

# runs 7 train, val, test batches and program ends
trainer = Trainer(fast_dev_run=7)

from argparse import ArgumentParser

def main(hparams):
    model = LightningModule()
    trainer = Trainer(gpus=hparams.gpus)
    trainer.fit(model)

if __name__ == '__main__':
    parser = ArgumentParser()
    parser.add_argument('--gpus', default=None)
    args = parser.parse_args()

    main(args)

from argparse import ArgumentParser

def main(args):
    model = LightningModule()
    trainer = Trainer.from_argparse_args(args)
    trainer.fit(model)

if __name__ == '__main__':
    parser = ArgumentParser()
    parser = Trainer.add_argparse_args(
        # group the Trainer arguments together
        parser.add_argument_group(title="pl.Trainer args")
    )
    args = parser.parse_args()

    main(args)

from argparse import ArgumentParser
import pytorch_lightning as pl
from pytorch_lightning import LightningModule, Trainer

def main(args):
    model = LightningModule()
    trainer = Trainer.from_argparse_args(args)
    trainer.fit(model)

if __name__ == '__main__':
    parser = ArgumentParser()
    parser.add_argument('--batch_size', default=32, type=int)
    parser.add_argument('--hidden_dim', type=int, default=128)
    parser = Trainer.add_argparse_args(
        # group the Trainer arguments together
        parser.add_argument_group(title="pl.Trainer args")
    )
    args = parser.parse_args()
	
    main(args)

from pytorch_lightning.callbacks import ModelCheckpoint

# saves a file like: my/path/sample-mnist-epoch=02-val_loss=0.32.ckpt
checkpoint_callback = ModelCheckpoint(
    monitor='val_loss',
    filename='sample-mnist-{epoch:02d}-{val_loss:.2f}',
    save_top_k=3,
    mode='min',
    save_last=True
)

trainer = pl.Trainer(gpus=1, max_epochs=3, progress_bar_refresh_rate=20, callbacks=[checkpoint_callback])

from pytorch_lightning import Trainer
from pytorch_lightning.callbacks import EarlyStopping

early_stopping = EarlyStopping('val_loss')
trainer = Trainer(callbacks=[early_stopping])

from pl_bolts.callbacks import PrintTableMetricsCallback

callback = PrintTableMetricsCallback()
trainer = pl.Trainer(callbacks=[callback])
trainer.fit(...)

# ------------------------------
# at the end of every epoch it will print
# ------------------------------

# loss│train_loss│val_loss│epoch
# ──────────────────────────────
# 2.2541470527648926│2.2541470527648926│2.2158432006835938│0

from pytorch_lightning import loggers as pl_loggers

# Default
tb_logger = pl_loggers.TensorBoardLogger(
    save_dir=os.getcwd(),
    version=None,
    name='lightning_logs'
)
trainer = Trainer(logger=tb_logger)

# Or use the same format as others
tb_logger = pl_loggers.TensorBoardLogger('logs/')

# One Logger
comet_logger = pl_loggers.CometLogger(save_dir='logs/')
trainer = Trainer(logger=comet_logger)

# Save code snapshot
logger = pl_loggers.TestTubeLogger('logs/', create_git_tag=True)

# Multiple Logger
tb_logger = pl_loggers.TensorBoardLogger('logs/')
comet_logger = pl_loggers.CometLogger(save_dir='logs/')
trainer = Trainer(logger=[tb_logger, comet_logger])

def training_step(...):
    ...
    # the logger you used (in this case tensorboard)
    tensorboard = self.logger.experiment
    tensorboard.add_image()
    tensorboard.add_histogram(...)
    tensorboard.add_figure(...)

# Start tensorboard.
%load_ext tensorboard
%tensorboard --logdir lightning_logs/

# Single optimizer
for epoch in epochs:
    for batch in data:
        loss = model.training_step(batch, batch_idx, ...)
        loss.backward()
        optimizer.step()
        optimizer.zero_grad()

    for scheduler in schedulers:
        scheduler.step()
        
# Multiple optimizers
for epoch in epochs:
  for batch in data:
     for opt in optimizers:
        disable_grads_for_other_optimizers()
        train_step(opt)
        opt.step()

  for scheduler in schedulers:
     scheduler.step()

from torch.utils.data import DataLoader, random_split
from torchvision.datasets import MNIST

mnist_full = MNIST(self.data_dir, train=True, transform=self.transform)
self.mnist_train, self.mnist_val = random_split(mnist_full, [55000, 5000])