Aprendizaje Profundo ¶
Pytorch-lightning ¶
Fuente: Guilerms, CC BY-SA 4.0, via Wikimedia Commons
Coordinador¶
- Campo Elías Pardo, PhD, cepardot@unal.edu.co
Profesores¶
- Alvaro Montenegro, PhD, ammontenegrod@unal.edu.co
- Camilo José Torres Jiménez, Msc, cjtorresj@unal.edu.co
- Daniel Montenegro, Msc, dextronomo@gmail.com
Asesora Medios y Marketing digital¶
- Maria del Pilar Montenegro, pmontenegro88@gmail.com
- Jessica López Mejía, jelopezme@unal.edu.co
- Venus Celeste Puertas Gualtero, vpuertasg@unal.edu.co
Jefe Jurídica¶
- Paula Andrea Guzmán, guzmancruz.paula@gmail.com
Coordinador Jurídico¶
- David Fuentes, fuentesd065@gmail.com
Desarrolladores Principales¶
- Dairo Moreno, damoralesj@unal.edu.co
- Joan Castro, jocastroc@unal.edu.co
- Bryan Riveros, briveros@unal.edu.co
- Rosmer Vargas, rovargasc@unal.edu.co
- Venus Puertas, vpuertasg@unal.edu.co
Expertos en Bases de Datos¶
- Giovvani Barrera, udgiovanni@gmail.com
- Camilo Chitivo, cchitivo@unal.edu.co
Referencias¶
Contenido¶
Introducción¶
Fuente: Alvaro Montenegro
Introducción¶
En esta lección aprendemos como construir una modelo de clasificación de imágenes a color. Usaremos el framework Pytorch-lightning para construir el modelo y el conjunto de datos CIFAR10. La siguiente figura los tipos de datos que se usarán en esta lección. El contenido es una adaptación libre del tutorial Image Classification using PyTorch Lightning de WandB.
Fuente: Universidad de Toronto-Cifar10
Para esta lección usaremos los datos CIFAR10 disponibles en los datasets de la librería Torchvision. Adicionalmente usaremos Weights and bias-Wandb, una plataforma moderna que puede apoyar para crear mejores modelos, más rápido con el seguimiento de experimentos, el control de versiones de conjuntos de datos y la gestión de modelos. WandB debe instalarse por separado, pero se incorpora a la librería pytorch_lightning.loggers.
Preparación de los datos¶
Los DataModule son una forma de desacoplar enlaces relacionados con datos del LightningModule para que pueda desarrollar modelos agnósticos de conjuntos de datos. En otra palabras, con DataModule puede preparar los datos por fuera del módulo de entrenamiento, de tal manera que peude cambiar sus datos sin tocar el módulo de entrenamiento.
Con DataModule podemos organiza la canalización de datos en una clase compartible y reutilizable. Un módulo de datos encapsula los cinco pasos involucrados en el procesamiento de datos en PyTorch:
- Descargar/tokenizar/procesar.
- Limpiar y (tal vez) guardar en el disco.
- Cargar dentro del conjunto de datos.
- Aplicar transformaciones (rotar, tokenizar, etc.).
- Envolver dentro de un DataLoader.
Obtenga más información sobre los módulos de datos aquí. Construyamos un módulo de datos para el conjunto de datos Cifar-10.
Carga las librerías requeridas¶
Instale la libreria wandb con el siguiente comando:
In [1]:
#!conda install -c conda-forge wandb
In [2]:
import torch
import pytorch_lightning as pl
from torch import nn
from torch.nn import functional as F
# Carga DataLoader para crear los dataloaders
from torch.utils.data import DataLoader, random_split
# Librería Torchvision
import torchvision
from torchvision import transforms
# métricas
import torchmetrics
# Carga WandBLogger para hacer seguimiento (tracking) del entrenamiento
from pytorch_lightning.loggers import WandbLogger
# carga el dataset CIFAR10
import torchvision.datasets as datasets
CIFAR10 = datasets.CIFAR10
# callbacks
from pytorch_lightning.callbacks import Callback
from pytorch_lightning.callbacks.early_stopping import EarlyStopping
from pytorch_lightning.callbacks import ModelCheckpoint
Canalización (pipeline) de los datos con DataModule¶
Construimos una clase derivada de LightningDataModule específica para CIFAR10.
In [3]:
from torch.utils.data import DataLoader, random_split
import torchvision.datasets as datasets
CIFAR10 = datasets.CIFAR10
from torchvision import transforms
class CIFAR10DataModule(pl.LightningDataModule):
def __init__(self, batch_size, data_dir: str = './', num_workers=4):
"""
Pasaremos los hiperparámetros necesarios para nuestra canalización de datos
También definiremos la canalización de transformación de datos aquí.
"""
super().__init__()
self.data_dir = data_dir
self.batch_size = batch_size
self.num_workers = num_workers
self.transform = transforms.Compose([
transforms.ToTensor(),
transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))
])
self.dims = (3, 32, 32)
self.num_classes = 10
def prepare_data(self):
"""
Aquí es donde definiremos la lógica para descargar nuestro conjunto de datos.
Estamos utilizando la clase de conjunto de datos CIFAR10 de torchvision para descargar.
Use este método para hacer cosas que podrían escribirse en el disco
o que deben hacerse solo desde una única GPU en configuraciones distribuidas.
No haga ninguna asignación de estado en esta función
(es decir, self.alguna_cosa = ...).
"""
# descarga
CIFAR10(self.data_dir, train=True, download=True)
CIFAR10(self.data_dir, train=False, download=True)
def setup(self, stage=None):
"""
Aquí es donde cargaremos los datos del archivo y prepararemos
los conjuntos de datos del tensor PyTorch para cada división de los datos.
La división de datos es por lo tanto reproducible.
Este método espera un argumento de etapa (stage) que se utiliza para separar
la lógica de 'entrenamiento' y de 'prueba'.
Esto es útil si no queremos cargar todo el conjunto de datos a la vez.
Las operaciones de datos que queremos realizar en cada GPU se definen aquí.
Esto incluye aplicar la transformación al conjunto de datos del tensor de PyTorch.
"""
# Asigna datos a los datasets de entrenamiento/validación
# para uso en los dataloaders
if stage == 'fit' or stage is None:
cifar_full = CIFAR10(self.data_dir, train=True, transform=self.transform)
self.cifar_train, self.cifar_val = random_split(cifar_full, [45000, 5000])
# Asigna dataset de prueba para uso en los dataloader(s)
if stage == 'test' or stage is None:
self.cifar_test = CIFAR10(self.data_dir, train=False, transform=self.transform)
# Métodos para crear los dataloaders
def train_dataloader(self):
return DataLoader(self.cifar_train, batch_size=self.batch_size, shuffle=True, num_workers=self.num_workers)
def val_dataloader(self):
return DataLoader(self.cifar_val, batch_size=self.batch_size, num_workers=self.num_workers)
def test_dataloader(self):
return DataLoader(self.cifar_test, batch_size=self.batch_size, num_workers=self.num_workers)
Devolución de llamadas (Callbacks)¶
Una devolución de llamada o callback es un programa autónomo que se puede reutilizar en todos los proyectos. PyTorch Lightning viene con algunos callbacks integrados que se usan regularmente.
Obtenga más información sobre callbacks en PyTorch Lightning aquí.
Devoluciones de llamada integrados¶
En este tutorial, utilizaremos las devoluciones de llamada integradas de parada anticipada Early Stopping y punto de control checkpoint de modelo. Estos callback se pueden pasar al entrenador (Trainer).
Devoluciones de llamada personalizados¶
Si está familiarizado con la devolución de llamada personalizada de Keras, la capacidad de hacer lo mismo en su canalización de PyTorch es solo una cereza del pastel.
Dado que estamos realizando una clasificación de imágenes, la capacidad de visualizar las predicciones del modelo en algunas muestras de imágenes puede resultar útil. Esto en forma de callback puede ayudar a depurar el modelo en una etapa temprana. Así que vamos a implementar un callback personalizado para tal fin.
LightningModule - Definición del sistema¶
LightningModule define un sistema y no un modelo. Aquí, un sistema agrupa todo el código de investigación en una sola clase para que sea autónomo. LightningModule organiza su código PyTorch en 5 secciones:
- Bucle de entranamiento (training_step)
- Bucle de validación (validation_step)
- Bucle de prueba (test_step)
- Optimizadores (configure_optimizers)
Por lo tanto, se puede construir un modelo agnóstico del conjunto de datos que se puede compartir fácilmente. Construyamos un sistema para la clasificación Cifar-10.
In [4]:
class LitModel(pl.LightningModule):
def __init__(self, backbone, learning_rate=2e-4, ):
super().__init__()
# activa log para almacenar los hiperparámetros
self.save_hyperparameters()
# modelo
self.backbone = backbone
# rata de aprendizaje para el optimizador
self.learning_rate = learning_rate
# métricas
self.train_acc = torchmetrics.Accuracy(task="multiclass", num_classes=10)
self.valid_acc = torchmetrics.Accuracy(task="multiclass", num_classes=10)
self.test_acc = torchmetrics.Accuracy(task="multiclass", num_classes=10)
def training_step(self, batch, batch_idx):
"""
Lightning automatiza la mayor parte del entrenamiento para nosotros,
la época y las iteraciones por lotes, todo lo que necesitamos mantener
es la lógica del paso de entrenamiento. El método training_step requiere argumentos
batch y batch_idx que el Entrenador pasa automáticamente.
"""
x, y = batch
logits = self.backbone(x)
loss = F.nll_loss(logits, y) # entropía cruzada: negative log likelihood
# training metrics
preds = torch.argmax(logits, dim=1)
acc = self.train_acc(preds, y)
#self.log('perdida_entrenamiento', loss )
#self.log('precision_entrenamiento', acc)
wandb.log({"acc_train": acc, "loss_train": loss})
return loss
def validation_step(self, batch, batch_idx):
"""
el ciclo de validación se puede implementar sobrescribiendo este método
de LightningModule
"""
x, y = batch
logits = self.backbone(x)
loss = F.nll_loss(logits, y)
# validation metrics
preds = torch.argmax(logits, dim=1)
acc = self.valid_acc(preds, y)
#self.log('perdida_validacion', loss, prog_bar=True)
#self.log('precision_validacion', acc, prog_bar=True)
wandb.log({"acc_test": acc, "loss_test": loss})
return loss
def test_step(self, batch, batch_idx):
"""
Este método similar al ciclo de validación.
La única diferencia es que en prueba solo se llama
cuando se usa trainer.test().
Las métricas se registran automáticamente por épocas.
"""
x, y = batch
logits = self.backbone(x)
loss = F.nll_loss(logits, y)
# validation metrics
preds = torch.argmax(logits, dim=1)
acc = self.test_acc(preds, y)
#self.log('perdida_test', loss, prog_bar=True)
#self.log('precision_test', acc, prog_bar=True)
wandb.log({"acc_test": acc, "loss_test": loss})
return loss
def configure_optimizers(self):
"""
Podemos definir nuestro optimizador y programadores
de tasa de aprendizaje usando el método
configure_optimizer.
Incluso se pueden definir múltiples optimizadores
como en el caso de las GAN.
"""
optimizer = torch.optim.Adam(self.backbone.parameters(), lr=self.learning_rate)
return optimizer
In [5]:
class LitModel(pl.LightningModule):
def __init__(self, input_shape, num_classes, learning_rate=2e-4):
super().__init__()
# log hyperparameters
self.save_hyperparameters()
self.learning_rate = learning_rate
self.input_shape = input_shape
self.num_clases = num_classes
# bloque convolucional: cuerpo de la red
"""
CLASS torch.nn.Conv2d(in_channels, out_channels, kernel_size, stride=1,
padding=0, dilation=1, groups=1, bias=True, padding_mode='zeros', device=None, dtype=None)
"""
self.conv1 = nn.Conv2d(3, 32, 3, 1)
self.conv2 = nn.Conv2d(32, 32, 3, 1)
self.conv3 = nn.Conv2d(32, 64, 3, 1)
self.conv4 = nn.Conv2d(64, 3, 1)
"""
CLASS torch.nn.MaxPool2d(kernel_size, stride=None, padding=0, dilation=1,
return_indices=False, ceil_mode=False)
"""
self.pool1 = torch.nn.MaxPool2d(2)
self.pool2 = torch.nn.MaxPool2d(2)
n_sizes = self._get_conv_output(input_shape)
self.fc1 = nn.Linear(n_sizes, 512)
self.fc2 = nn.Linear(512, 128)
self.fc3 = nn.Linear(128, num_classes)
self.accuracy = torchmetrics.Accuracy(task ='multiclass', num_classes=self.num_clases)
# Calcula el tamaño de salida del bloque convolucional
# métodos auxiliares para calcular el tamaño de salida
# del bloque convolucion. Se requiere ara poder configurar
# totalmente la red. No requrido en Keras
def _get_conv_output(self, shape):
batch_size = 1
input = torch.autograd.Variable(torch.rand(batch_size, *shape))
output_feat = self._forward_features(input)
n_size = output_feat.data.view(batch_size, -1).size(1)
return n_size
# devuelve el tensor de características del bloque conv
def _forward_features(self, x):
x = F.relu(self.conv1(x))
x = self.pool1(F.relu(self.conv2(x)))
x = F.relu(self.conv3(x))
x = self.pool2(F.relu(self.conv4(x)))
return x
# forward
def forward(self, x):
x = self._forward_features(x)
x = x.view(x.size(0), -1)
x = F.relu(self.fc1(x))
x = F.relu(self.fc2(x))
x = F.log_softmax(self.fc3(x), dim=1)
return x
# paso de entrenamiento
def training_step(self, batch, batch_idx):
x, y = batch
logits = self(x)
loss = F.nll_loss(logits, y)
# training metrics
preds = torch.argmax(logits, dim=1)
acc = self.accuracy(preds, y)
self.log('train_loss', loss, on_step=True, on_epoch=True, logger=True)
self.log('train_acc', acc, on_step=True, on_epoch=True, logger=True)
return loss
# paso de validación
def validation_step(self, batch, batch_idx):
x, y = batch
logits = self(x)
loss = F.nll_loss(logits, y)
# validation metrics
preds = torch.argmax(logits, dim=1)
acc = self.accuracy(preds, y)
self.log('val_loss', loss, prog_bar=True)
self.log('val_acc', acc, prog_bar=True)
return loss
# paso de prueba
def test_step(self, batch, batch_idx):
x, y = batch
logits = self(x)
loss = F.nll_loss(logits, y)
# validation metrics
preds = torch.argmax(logits, dim=1)
acc = self.accuracy(preds, y)
self.log('test_loss', loss, prog_bar=True)
self.log('test_acc', acc, prog_bar=True)
return loss
# optimizador
def configure_optimizers(self):
optimizer = torch.optim.Adam(self.parameters(), lr=self.learning_rate)
return optimizer
Entrenamiento y Evaluación¶
Ahora que organizamos nuestra canalización de datos con DataModule y modelamos la arquitectura del modelo con nn.Module y el ciclo de entrenamiento con LightningModule, PyTorch Lightning Trainer automatiza todo lo demás por nosotros.
El Entrenador automatiza:
- Iteración de época y lote
- Llamada de
optimizer.step(),backward,zero_grad() - Llamada de
.eval(), habilitación/deshabilitación de gradientes - Guardar y cargar pesos
- Registro de pesos y sesgos
- Soporte de entrenamiento multi-GPU
- Soporte de TPU
- soporte de entrenamiento de 16 bits
Primero inicializaremos nuestra canalización de datos. El Entrenador solo necesita un DataLoader de PyTorch para los datos de entrenamiento/val/prueba.
Podemos pasar directamente el objeto dm que hemos creado al Entrenador. Pero dado que necesitamos algunas muestras para nuestro ImagePredictionLogger, llamaremos manualmente a los métodos prepare_data y setup.
Instancia los datos¶
In [6]:
# Inicializa la canalización de los datos
dm = CIFAR10DataModule(batch_size=32)
# Para acceder a los x_dataloader prepara los datos y configurar
dm.prepare_data()
dm.setup()
Files already downloaded and verified Files already downloaded and verified
In [7]:
# Muestras requeridas por la devolución de llamada personalizada de ImagePredictionLogger
# para registrar predicciones de imágenes.
val_samples = next(iter(dm.val_dataloader()))
val_imgs, val_labels = val_samples[0], val_samples[1]
val_imgs.shape, val_labels.shape
Out[7]:
(torch.Size([32, 3, 32, 32]), torch.Size([32]))
Solo necesitamos inicializar el modelo y nuestro logger favorito. Tenga en cuenta que hemos pasado checkpoint_callback por separado.
Instancia el modelo¶
In [8]:
# Instancia el modelo
inputshape = (3,32, 32)
numclases = 10
model = LitModel(inputshape, numclases)
model
[W NNPACK.cpp:64] Could not initialize NNPACK! Reason: Unsupported hardware.
Out[8]:
LitModel( (conv1): Conv2d(3, 32, kernel_size=(3, 3), stride=(1, 1)) (conv2): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1)) (conv3): Conv2d(32, 64, kernel_size=(3, 3), stride=(1, 1)) (conv4): Conv2d(64, 3, kernel_size=(1, 1), stride=(1, 1)) (pool1): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False) (pool2): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False) (fc1): Linear(in_features=108, out_features=512, bias=True) (fc2): Linear(in_features=512, out_features=128, bias=True) (fc3): Linear(in_features=128, out_features=10, bias=True) (accuracy): MulticlassAccuracy() )
Instancia el trainer¶
In [9]:
# Inicializa wandb logger
#wandb_logger = WandbLogger(project='wandb-lightning', job_type='train')
wandb_logger = WandbLogger(project='CIFAR10',
config={
"learning_rate": 0.02,
"architecture": "CNN",
"dataset": "CIFAR-100"})
wandb: Currently logged in as: ammontenegrod (aprendizaje-profundo). Use `wandb login --relogin` to force relogin
Tracking run with wandb version 0.15.2
Run data is saved locally in
./wandb/run-20230515_094528-p407cj4f
View project at https://wandb.ai/aprendizaje-profundo/CIFAR10
In [10]:
# Initialize a trainer
trainer = pl.Trainer(max_epochs=5,
precision=16,
logger=wandb_logger,
limit_train_batches=0.25,
default_root_dir="../Checkpoints",
)
/home/alvaro/anaconda3/envs/lightning/lib/python3.11/site-packages/lightning_fabric/connector.py:562: UserWarning: 16 is supported for historical reasons but its usage is discouraged. Please set your precision to 16-mixed instead! rank_zero_warn( /home/alvaro/anaconda3/envs/lightning/lib/python3.11/site-packages/pytorch_lightning/trainer/connectors/accelerator_connector.py:517: UserWarning: You passed `Trainer(accelerator='cpu', precision='16-mixed')` but AMP with fp16 is not supported on CPU. Using `precision='bf16-mixed'` instead. rank_zero_warn( Using bfloat16 Automatic Mixed Precision (AMP) GPU available: False, used: False TPU available: False, using: 0 TPU cores IPU available: False, using: 0 IPUs HPU available: False, using: 0 HPUs
Entrena el modelo¶
In [12]:
# Entrena el modelo
trainer.fit(model, dm)
Files already downloaded and verified Files already downloaded and verified
| Name | Type | Params ------------------------------------------------ 0 | conv1 | Conv2d | 896 1 | conv2 | Conv2d | 9.2 K 2 | conv3 | Conv2d | 18.5 K 3 | conv4 | Conv2d | 195 4 | pool1 | MaxPool2d | 0 5 | pool2 | MaxPool2d | 0 6 | fc1 | Linear | 55.8 K 7 | fc2 | Linear | 65.7 K 8 | fc3 | Linear | 1.3 K 9 | accuracy | MulticlassAccuracy | 0 ------------------------------------------------ 151 K Trainable params 0 Non-trainable params 151 K Total params 0.606 Total estimated model params size (MB)
Epoch 0: 100%|████████████████████| 351/351 [08:28<00:00, 1.45s/it, v_num=cj4f] Validation: 0it [00:00, ?it/s] Validation: 0%| | 0/157 [00:00<?, ?it/s] Validation DataLoader 0: 0%| | 0/157 [00:00<?, ?it/s] Validation DataLoader 0: 1%| | 1/157 [00:00<01:17, 2.02it/s] Validation DataLoader 0: 1%|▏ | 2/157 [00:00<01:13, 2.10it/s] Validation DataLoader 0: 2%|▎ | 3/157 [00:01<01:12, 2.12it/s] Validation DataLoader 0: 3%|▍ | 4/157 [00:01<01:11, 2.13it/s] Validation DataLoader 0: 3%|▌ | 5/157 [00:02<01:11, 2.13it/s] Validation DataLoader 0: 4%|▋ | 6/157 [00:02<01:12, 2.09it/s] Validation DataLoader 0: 4%|▊ | 7/157 [00:03<01:11, 2.10it/s] Validation DataLoader 0: 5%|▉ | 8/157 [00:03<01:10, 2.12it/s] Validation DataLoader 0: 6%|█ | 9/157 [00:04<01:10, 2.09it/s] Validation DataLoader 0: 6%|█ | 10/157 [00:04<01:10, 2.09it/s] Validation DataLoader 0: 7%|█▏ | 11/157 [00:05<01:10, 2.07it/s] Validation DataLoader 0: 8%|█▎ | 12/157 [00:05<01:09, 2.07it/s] Validation DataLoader 0: 8%|█▍ | 13/157 [00:06<01:09, 2.08it/s] Validation DataLoader 0: 9%|█▌ | 14/157 [00:06<01:10, 2.04it/s] Validation DataLoader 0: 10%|█▌ | 15/157 [00:07<01:09, 2.04it/s] Validation DataLoader 0: 10%|█▋ | 16/157 [00:07<01:09, 2.02it/s] Validation DataLoader 0: 11%|█▊ | 17/157 [00:08<01:08, 2.03it/s] Validation DataLoader 0: 11%|█▉ | 18/157 [00:08<01:09, 2.00it/s] Validation DataLoader 0: 12%|██ | 19/157 [00:09<01:08, 2.01it/s] Validation DataLoader 0: 13%|██▏ | 20/157 [00:09<01:07, 2.02it/s] Validation DataLoader 0: 13%|██▎ | 21/157 [00:10<01:07, 2.02it/s] Validation DataLoader 0: 14%|██▍ | 22/157 [00:10<01:06, 2.02it/s] Validation DataLoader 0: 15%|██▍ | 23/157 [00:11<01:06, 2.03it/s] Validation DataLoader 0: 15%|██▌ | 24/157 [00:11<01:06, 2.01it/s] Validation DataLoader 0: 16%|██▋ | 25/157 [00:12<01:05, 2.02it/s] Validation DataLoader 0: 17%|██▊ | 26/157 [00:12<01:05, 2.00it/s] Validation DataLoader 0: 17%|██▉ | 27/157 [00:13<01:04, 2.01it/s] Validation DataLoader 0: 18%|███ | 28/157 [00:13<01:04, 2.01it/s] Validation DataLoader 0: 18%|███▏ | 29/157 [00:14<01:03, 2.02it/s] Validation DataLoader 0: 19%|███▏ | 30/157 [00:14<01:02, 2.02it/s] Validation DataLoader 0: 20%|███▎ | 31/157 [00:15<01:02, 2.03it/s] Validation DataLoader 0: 20%|███▍ | 32/157 [00:15<01:01, 2.03it/s] Validation DataLoader 0: 21%|███▌ | 33/157 [00:16<01:01, 2.03it/s] Validation DataLoader 0: 22%|███▋ | 34/157 [00:16<01:00, 2.04it/s] Validation DataLoader 0: 22%|███▊ | 35/157 [00:17<01:00, 2.03it/s] Validation DataLoader 0: 23%|███▉ | 36/157 [00:17<00:59, 2.03it/s] Validation DataLoader 0: 24%|████ | 37/157 [00:18<00:59, 2.03it/s] Validation DataLoader 0: 24%|████ | 38/157 [00:18<00:58, 2.03it/s] Validation DataLoader 0: 25%|████▏ | 39/157 [00:19<00:58, 2.03it/s] Validation DataLoader 0: 25%|████▎ | 40/157 [00:19<00:57, 2.03it/s] Validation DataLoader 0: 26%|████▍ | 41/157 [00:20<00:56, 2.04it/s] Validation DataLoader 0: 27%|████▌ | 42/157 [00:20<00:56, 2.03it/s] Validation DataLoader 0: 27%|████▋ | 43/157 [00:21<00:56, 2.03it/s] Validation DataLoader 0: 28%|████▊ | 44/157 [00:21<00:55, 2.03it/s] Validation DataLoader 0: 29%|████▊ | 45/157 [00:22<00:54, 2.04it/s] Validation DataLoader 0: 29%|████▉ | 46/157 [00:22<00:54, 2.04it/s] Validation DataLoader 0: 30%|█████ | 47/157 [00:23<00:53, 2.04it/s] Validation DataLoader 0: 31%|█████▏ | 48/157 [00:23<00:53, 2.04it/s] Validation DataLoader 0: 31%|█████▎ | 49/157 [00:24<00:52, 2.04it/s] Validation DataLoader 0: 32%|█████▍ | 50/157 [00:24<00:52, 2.03it/s] Validation DataLoader 0: 32%|█████▌ | 51/157 [00:25<00:52, 2.02it/s] Validation DataLoader 0: 33%|█████▋ | 52/157 [00:25<00:51, 2.03it/s] Validation DataLoader 0: 34%|█████▋ | 53/157 [00:26<00:51, 2.03it/s] Validation DataLoader 0: 34%|█████▊ | 54/157 [00:26<00:50, 2.03it/s] Validation DataLoader 0: 35%|█████▉ | 55/157 [00:27<00:50, 2.03it/s] Validation DataLoader 0: 36%|██████ | 56/157 [00:27<00:49, 2.04it/s] Validation DataLoader 0: 36%|██████▏ | 57/157 [00:27<00:49, 2.04it/s] Validation DataLoader 0: 37%|██████▎ | 58/157 [00:28<00:48, 2.04it/s] Validation DataLoader 0: 38%|██████▍ | 59/157 [00:28<00:47, 2.04it/s] Validation DataLoader 0: 38%|██████▍ | 60/157 [00:29<00:47, 2.03it/s] Validation DataLoader 0: 39%|██████▌ | 61/157 [00:29<00:47, 2.04it/s] Validation DataLoader 0: 39%|██████▋ | 62/157 [00:30<00:46, 2.03it/s] Validation DataLoader 0: 40%|██████▊ | 63/157 [00:31<00:46, 2.03it/s] Validation DataLoader 0: 41%|██████▉ | 64/157 [00:31<00:45, 2.03it/s] Validation DataLoader 0: 41%|███████ | 65/157 [00:31<00:45, 2.03it/s] Validation DataLoader 0: 42%|███████▏ | 66/157 [00:32<00:44, 2.03it/s] Validation DataLoader 0: 43%|███████▎ | 67/157 [00:32<00:44, 2.03it/s] Validation DataLoader 0: 43%|███████▎ | 68/157 [00:33<00:43, 2.03it/s] Validation DataLoader 0: 44%|███████▍ | 69/157 [00:34<00:43, 2.03it/s] Validation DataLoader 0: 45%|███████▌ | 70/157 [00:34<00:42, 2.02it/s] Validation DataLoader 0: 45%|███████▋ | 71/157 [00:35<00:42, 2.02it/s] Validation DataLoader 0: 46%|███████▊ | 72/157 [00:35<00:41, 2.03it/s] Validation DataLoader 0: 46%|███████▉ | 73/157 [00:35<00:41, 2.03it/s] Validation DataLoader 0: 47%|████████ | 74/157 [00:36<00:40, 2.03it/s] Validation DataLoader 0: 48%|████████ | 75/157 [00:36<00:40, 2.03it/s] Validation DataLoader 0: 48%|████████▏ | 76/157 [00:37<00:39, 2.03it/s] Validation DataLoader 0: 49%|████████▎ | 77/157 [00:37<00:39, 2.03it/s] Validation DataLoader 0: 50%|████████▍ | 78/157 [00:38<00:38, 2.03it/s] Validation DataLoader 0: 50%|████████▌ | 79/157 [00:38<00:38, 2.03it/s] Validation DataLoader 0: 51%|████████▋ | 80/157 [00:39<00:37, 2.03it/s] Validation DataLoader 0: 52%|████████▊ | 81/157 [00:39<00:37, 2.03it/s] Validation DataLoader 0: 52%|████████▉ | 82/157 [00:40<00:36, 2.04it/s] Validation DataLoader 0: 53%|████████▉ | 83/157 [00:40<00:36, 2.04it/s] Validation DataLoader 0: 54%|█████████ | 84/157 [00:41<00:35, 2.04it/s] Validation DataLoader 0: 54%|█████████▏ | 85/157 [00:41<00:35, 2.04it/s] Validation DataLoader 0: 55%|█████████▎ | 86/157 [00:42<00:34, 2.04it/s] Validation DataLoader 0: 55%|█████████▍ | 87/157 [00:42<00:34, 2.04it/s] Validation DataLoader 0: 56%|█████████▌ | 88/157 [00:43<00:33, 2.04it/s] Validation DataLoader 0: 57%|█████████▋ | 89/157 [00:43<00:33, 2.04it/s] Validation DataLoader 0: 57%|█████████▋ | 90/157 [00:44<00:32, 2.04it/s] Validation DataLoader 0: 58%|█████████▊ | 91/157 [00:44<00:32, 2.03it/s] Validation DataLoader 0: 59%|█████████▉ | 92/157 [00:45<00:32, 2.03it/s] Validation DataLoader 0: 59%|██████████ | 93/157 [00:46<00:31, 2.02it/s] Validation DataLoader 0: 60%|██████████▏ | 94/157 [00:46<00:31, 2.02it/s] Validation DataLoader 0: 61%|██████████▎ | 95/157 [00:46<00:30, 2.02it/s] Validation DataLoader 0: 61%|██████████▍ | 96/157 [00:47<00:30, 2.02it/s] Validation DataLoader 0: 62%|██████████▌ | 97/157 [00:48<00:29, 2.02it/s] Validation DataLoader 0: 62%|██████████▌ | 98/157 [00:48<00:29, 2.02it/s] Validation DataLoader 0: 63%|██████████▋ | 99/157 [00:49<00:28, 2.02it/s] Validation DataLoader 0: 64%|██████████▏ | 100/157 [00:49<00:28, 2.02it/s] Validation DataLoader 0: 64%|██████████▎ | 101/157 [00:49<00:27, 2.02it/s] Validation DataLoader 0: 65%|██████████▍ | 102/157 [00:50<00:27, 2.02it/s] Validation DataLoader 0: 66%|██████████▍ | 103/157 [00:51<00:26, 2.02it/s] Validation DataLoader 0: 66%|██████████▌ | 104/157 [00:51<00:26, 2.02it/s] Validation DataLoader 0: 67%|██████████▋ | 105/157 [00:52<00:25, 2.02it/s] Validation DataLoader 0: 68%|██████████▊ | 106/157 [00:52<00:25, 2.02it/s] Validation DataLoader 0: 68%|██████████▉ | 107/157 [00:52<00:24, 2.02it/s] Validation DataLoader 0: 69%|███████████ | 108/157 [00:53<00:24, 2.02it/s] Validation DataLoader 0: 69%|███████████ | 109/157 [00:53<00:23, 2.02it/s] Validation DataLoader 0: 70%|███████████▏ | 110/157 [00:54<00:23, 2.02it/s] Validation DataLoader 0: 71%|███████████▎ | 111/157 [00:54<00:22, 2.02it/s] Validation DataLoader 0: 71%|███████████▍ | 112/157 [00:55<00:22, 2.02it/s] Validation DataLoader 0: 72%|███████████▌ | 113/157 [00:55<00:21, 2.02it/s] Validation DataLoader 0: 73%|███████████▌ | 114/157 [00:56<00:21, 2.02it/s] Validation DataLoader 0: 73%|███████████▋ | 115/157 [00:56<00:20, 2.02it/s] Validation DataLoader 0: 74%|███████████▊ | 116/157 [00:57<00:20, 2.02it/s] Validation DataLoader 0: 75%|███████████▉ | 117/157 [00:57<00:19, 2.02it/s] Validation DataLoader 0: 75%|████████████ | 118/157 [00:58<00:19, 2.02it/s] Validation DataLoader 0: 76%|████████████▏ | 119/157 [00:58<00:18, 2.02it/s] Validation DataLoader 0: 76%|████████████▏ | 120/157 [00:59<00:18, 2.02it/s] Validation DataLoader 0: 77%|████████████▎ | 121/157 [00:59<00:17, 2.02it/s] Validation DataLoader 0: 78%|████████████▍ | 122/157 [01:00<00:17, 2.02it/s] Validation DataLoader 0: 78%|████████████▌ | 123/157 [01:00<00:16, 2.03it/s] Validation DataLoader 0: 79%|████████████▋ | 124/157 [01:01<00:16, 2.03it/s] Validation DataLoader 0: 80%|████████████▋ | 125/157 [01:01<00:15, 2.03it/s] Validation DataLoader 0: 80%|████████████▊ | 126/157 [01:02<00:15, 2.02it/s] Validation DataLoader 0: 81%|████████████▉ | 127/157 [01:02<00:14, 2.02it/s] Validation DataLoader 0: 82%|█████████████ | 128/157 [01:03<00:14, 2.02it/s] Validation DataLoader 0: 82%|█████████████▏ | 129/157 [01:03<00:13, 2.02it/s] Validation DataLoader 0: 83%|█████████████▏ | 130/157 [01:04<00:13, 2.02it/s] Validation DataLoader 0: 83%|█████████████▎ | 131/157 [01:04<00:12, 2.02it/s] Validation DataLoader 0: 84%|█████████████▍ | 132/157 [01:05<00:12, 2.02it/s] Validation DataLoader 0: 85%|█████████████▌ | 133/157 [01:05<00:11, 2.02it/s] Validation DataLoader 0: 85%|█████████████▋ | 134/157 [01:06<00:11, 2.02it/s] Validation DataLoader 0: 86%|█████████████▊ | 135/157 [01:07<00:10, 2.01it/s] Validation DataLoader 0: 87%|█████████████▊ | 136/157 [01:07<00:10, 2.02it/s] Validation DataLoader 0: 87%|█████████████▉ | 137/157 [01:07<00:09, 2.02it/s] Validation DataLoader 0: 88%|██████████████ | 138/157 [01:08<00:09, 2.02it/s] Validation DataLoader 0: 89%|██████████████▏ | 139/157 [01:08<00:08, 2.02it/s] Validation DataLoader 0: 89%|██████████████▎ | 140/157 [01:09<00:08, 2.01it/s] Validation DataLoader 0: 90%|██████████████▎ | 141/157 [01:09<00:07, 2.02it/s] Validation DataLoader 0: 90%|██████████████▍ | 142/157 [01:10<00:07, 2.02it/s] Validation DataLoader 0: 91%|██████████████▌ | 143/157 [01:10<00:06, 2.02it/s] Validation DataLoader 0: 92%|██████████████▋ | 144/157 [01:11<00:06, 2.01it/s] Validation DataLoader 0: 92%|██████████████▊ | 145/157 [01:11<00:05, 2.02it/s] Validation DataLoader 0: 93%|██████████████▉ | 146/157 [01:12<00:05, 2.01it/s] Validation DataLoader 0: 94%|██████████████▉ | 147/157 [01:13<00:04, 2.01it/s] Validation DataLoader 0: 94%|███████████████ | 148/157 [01:13<00:04, 2.01it/s] Validation DataLoader 0: 95%|███████████████▏| 149/157 [01:14<00:03, 2.01it/s] Validation DataLoader 0: 96%|███████████████▎| 150/157 [01:14<00:03, 2.01it/s] Validation DataLoader 0: 96%|███████████████▍| 151/157 [01:15<00:02, 2.01it/s] Validation DataLoader 0: 97%|███████████████▍| 152/157 [01:15<00:02, 2.01it/s] Validation DataLoader 0: 97%|███████████████▌| 153/157 [01:16<00:01, 2.01it/s] Validation DataLoader 0: 98%|███████████████▋| 154/157 [01:16<00:01, 2.01it/s] Validation DataLoader 0: 99%|███████████████▊| 155/157 [01:17<00:00, 2.01it/s] Validation DataLoader 0: 99%|███████████████▉| 156/157 [01:17<00:00, 2.01it/s] Epoch 0: 100%|█| 351/351 [09:46<00:00, 1.67s/it, v_num=cj4f, val_loss=1.830, va Epoch 1: 100%|█| 351/351 [18:04<00:00, 3.09s/it, v_num=cj4f, val_loss=1.830, va Validation: 0it [00:00, ?it/s] Validation: 0%| | 0/157 [00:00<?, ?it/s] Validation DataLoader 0: 0%| | 0/157 [00:00<?, ?it/s] Validation DataLoader 0: 1%| | 1/157 [00:00<01:08, 2.29it/s] Validation DataLoader 0: 1%|▏ | 2/157 [00:00<01:08, 2.27it/s] Validation DataLoader 0: 2%|▎ | 3/157 [00:01<01:07, 2.28it/s] Validation DataLoader 0: 3%|▍ | 4/157 [00:01<01:07, 2.28it/s] Validation DataLoader 0: 3%|▌ | 5/157 [00:02<01:06, 2.29it/s] Validation DataLoader 0: 4%|▋ | 6/157 [00:02<01:07, 2.24it/s] Validation DataLoader 0: 4%|▊ | 7/157 [00:03<01:09, 2.15it/s] Validation DataLoader 0: 5%|▉ | 8/157 [00:03<01:09, 2.16it/s] Validation DataLoader 0: 6%|█ | 9/157 [00:04<01:07, 2.18it/s] Validation DataLoader 0: 6%|█ | 10/157 [00:04<01:06, 2.20it/s] Validation DataLoader 0: 7%|█▏ | 11/157 [00:05<01:08, 2.14it/s] Validation DataLoader 0: 8%|█▎ | 12/157 [00:05<01:07, 2.15it/s] Validation DataLoader 0: 8%|█▍ | 13/157 [00:06<01:07, 2.13it/s] Validation DataLoader 0: 9%|█▌ | 14/157 [00:06<01:06, 2.15it/s] Validation DataLoader 0: 10%|█▌ | 15/157 [00:06<01:05, 2.16it/s] Validation DataLoader 0: 10%|█▋ | 16/157 [00:07<01:04, 2.18it/s] Validation DataLoader 0: 11%|█▊ | 17/157 [00:07<01:04, 2.19it/s] Validation DataLoader 0: 11%|█▉ | 18/157 [00:08<01:03, 2.20it/s] Validation DataLoader 0: 12%|██ | 19/157 [00:08<01:02, 2.20it/s] Validation DataLoader 0: 13%|██▏ | 20/157 [00:09<01:02, 2.20it/s] Validation DataLoader 0: 13%|██▎ | 21/157 [00:09<01:01, 2.21it/s] Validation DataLoader 0: 14%|██▍ | 22/157 [00:09<01:00, 2.22it/s] Validation DataLoader 0: 15%|██▍ | 23/157 [00:10<01:00, 2.21it/s] Validation DataLoader 0: 15%|██▌ | 24/157 [00:10<00:59, 2.22it/s] Validation DataLoader 0: 16%|██▋ | 25/157 [00:11<00:59, 2.23it/s] Validation DataLoader 0: 17%|██▊ | 26/157 [00:11<00:58, 2.23it/s] Validation DataLoader 0: 17%|██▉ | 27/157 [00:12<00:58, 2.22it/s] Validation DataLoader 0: 18%|███ | 28/157 [00:12<00:58, 2.20it/s] Validation DataLoader 0: 18%|███▏ | 29/157 [00:13<00:58, 2.18it/s] Validation DataLoader 0: 19%|███▏ | 30/157 [00:13<00:58, 2.16it/s] Validation DataLoader 0: 20%|███▎ | 31/157 [00:14<00:58, 2.15it/s] Validation DataLoader 0: 20%|███▍ | 32/157 [00:14<00:58, 2.14it/s] Validation DataLoader 0: 21%|███▌ | 33/157 [00:15<00:58, 2.13it/s] Validation DataLoader 0: 22%|███▋ | 34/157 [00:16<00:58, 2.12it/s] Validation DataLoader 0: 22%|███▊ | 35/157 [00:16<00:58, 2.10it/s] Validation DataLoader 0: 23%|███▉ | 36/157 [00:17<00:57, 2.10it/s] Validation DataLoader 0: 24%|████ | 37/157 [00:17<00:57, 2.10it/s] Validation DataLoader 0: 24%|████ | 38/157 [00:18<00:56, 2.10it/s] Validation DataLoader 0: 25%|████▏ | 39/157 [00:18<00:56, 2.09it/s] Validation DataLoader 0: 25%|████▎ | 40/157 [00:19<00:55, 2.09it/s] Validation DataLoader 0: 26%|████▍ | 41/157 [00:19<00:55, 2.10it/s] Validation DataLoader 0: 27%|████▌ | 42/157 [00:20<00:54, 2.09it/s] Validation DataLoader 0: 27%|████▋ | 43/157 [00:20<00:54, 2.09it/s] Validation DataLoader 0: 28%|████▊ | 44/157 [00:20<00:53, 2.10it/s] Validation DataLoader 0: 29%|████▊ | 45/157 [00:21<00:53, 2.10it/s] Validation DataLoader 0: 29%|████▉ | 46/157 [00:21<00:52, 2.10it/s] Validation DataLoader 0: 30%|█████ | 47/157 [00:22<00:52, 2.10it/s] Validation DataLoader 0: 31%|█████▏ | 48/157 [00:22<00:51, 2.10it/s] Validation DataLoader 0: 31%|█████▎ | 49/157 [00:23<00:51, 2.09it/s] Validation DataLoader 0: 32%|█████▍ | 50/157 [00:24<00:51, 2.08it/s] Validation DataLoader 0: 32%|█████▌ | 51/157 [00:24<00:50, 2.09it/s] Validation DataLoader 0: 33%|█████▋ | 52/157 [00:24<00:50, 2.09it/s] Validation DataLoader 0: 34%|█████▋ | 53/157 [00:25<00:49, 2.10it/s] Validation DataLoader 0: 34%|█████▊ | 54/157 [00:25<00:49, 2.10it/s] Validation DataLoader 0: 35%|█████▉ | 55/157 [00:26<00:48, 2.11it/s] Validation DataLoader 0: 36%|██████ | 56/157 [00:26<00:47, 2.11it/s] Validation DataLoader 0: 36%|██████▏ | 57/157 [00:27<00:47, 2.10it/s] Validation DataLoader 0: 37%|██████▎ | 58/157 [00:27<00:47, 2.10it/s] Validation DataLoader 0: 38%|██████▍ | 59/157 [00:28<00:46, 2.09it/s] Validation DataLoader 0: 38%|██████▍ | 60/157 [00:28<00:46, 2.09it/s] Validation DataLoader 0: 39%|██████▌ | 61/157 [00:29<00:45, 2.09it/s] Validation DataLoader 0: 39%|██████▋ | 62/157 [00:29<00:45, 2.10it/s] Validation DataLoader 0: 40%|██████▊ | 63/157 [00:29<00:44, 2.10it/s] Validation DataLoader 0: 41%|██████▉ | 64/157 [00:30<00:44, 2.10it/s] Validation DataLoader 0: 41%|███████ | 65/157 [00:30<00:43, 2.11it/s] Validation DataLoader 0: 42%|███████▏ | 66/157 [00:31<00:43, 2.10it/s] Validation DataLoader 0: 43%|███████▎ | 67/157 [00:32<00:43, 2.09it/s] Validation DataLoader 0: 43%|███████▎ | 68/157 [00:32<00:42, 2.09it/s] Validation DataLoader 0: 44%|███████▍ | 69/157 [00:33<00:42, 2.09it/s] Validation DataLoader 0: 45%|███████▌ | 70/157 [00:33<00:41, 2.08it/s] Validation DataLoader 0: 45%|███████▋ | 71/157 [00:34<00:41, 2.08it/s] Validation DataLoader 0: 46%|███████▊ | 72/157 [00:34<00:40, 2.08it/s] Validation DataLoader 0: 46%|███████▉ | 73/157 [00:35<00:40, 2.08it/s] Validation DataLoader 0: 47%|████████ | 74/157 [00:35<00:39, 2.08it/s] Validation DataLoader 0: 48%|████████ | 75/157 [00:36<00:39, 2.08it/s] Validation DataLoader 0: 48%|████████▏ | 76/157 [00:36<00:38, 2.08it/s] Validation DataLoader 0: 49%|████████▎ | 77/157 [00:36<00:38, 2.08it/s] Validation DataLoader 0: 50%|████████▍ | 78/157 [00:37<00:37, 2.08it/s] Validation DataLoader 0: 50%|████████▌ | 79/157 [00:37<00:37, 2.08it/s] Validation DataLoader 0: 51%|████████▋ | 80/157 [00:38<00:36, 2.08it/s] Validation DataLoader 0: 52%|████████▊ | 81/157 [00:38<00:36, 2.08it/s] Validation DataLoader 0: 52%|████████▉ | 82/157 [00:39<00:35, 2.08it/s] Validation DataLoader 0: 53%|████████▉ | 83/157 [00:39<00:35, 2.08it/s] Validation DataLoader 0: 54%|█████████ | 84/157 [00:40<00:35, 2.08it/s] Validation DataLoader 0: 54%|█████████▏ | 85/157 [00:40<00:34, 2.08it/s] Validation DataLoader 0: 55%|█████████▎ | 86/157 [00:41<00:34, 2.08it/s] Validation DataLoader 0: 55%|█████████▍ | 87/157 [00:41<00:33, 2.08it/s] Validation DataLoader 0: 56%|█████████▌ | 88/157 [00:42<00:33, 2.07it/s] Validation DataLoader 0: 57%|█████████▋ | 89/157 [00:43<00:32, 2.06it/s] Validation DataLoader 0: 57%|█████████▋ | 90/157 [00:43<00:32, 2.06it/s] Validation DataLoader 0: 58%|█████████▊ | 91/157 [00:44<00:32, 2.05it/s] Validation DataLoader 0: 59%|█████████▉ | 92/157 [00:44<00:31, 2.05it/s] Validation DataLoader 0: 59%|██████████ | 93/157 [00:45<00:31, 2.05it/s] Validation DataLoader 0: 60%|██████████▏ | 94/157 [00:45<00:30, 2.05it/s] Validation DataLoader 0: 61%|██████████▎ | 95/157 [00:46<00:30, 2.05it/s] Validation DataLoader 0: 61%|██████████▍ | 96/157 [00:46<00:29, 2.05it/s] Validation DataLoader 0: 62%|██████████▌ | 97/157 [00:47<00:29, 2.05it/s] Validation DataLoader 0: 62%|██████████▌ | 98/157 [00:47<00:28, 2.04it/s] Validation DataLoader 0: 63%|██████████▋ | 99/157 [00:48<00:28, 2.04it/s] Validation DataLoader 0: 64%|██████████▏ | 100/157 [00:49<00:28, 2.03it/s] Validation DataLoader 0: 64%|██████████▎ | 101/157 [00:49<00:27, 2.03it/s] Validation DataLoader 0: 65%|██████████▍ | 102/157 [00:50<00:27, 2.03it/s] Validation DataLoader 0: 66%|██████████▍ | 103/157 [00:50<00:26, 2.03it/s] Validation DataLoader 0: 66%|██████████▌ | 104/157 [00:51<00:26, 2.03it/s] Validation DataLoader 0: 67%|██████████▋ | 105/157 [00:51<00:25, 2.03it/s] Validation DataLoader 0: 68%|██████████▊ | 106/157 [00:52<00:25, 2.03it/s] Validation DataLoader 0: 68%|██████████▉ | 107/157 [00:52<00:24, 2.03it/s] Validation DataLoader 0: 69%|███████████ | 108/157 [00:53<00:24, 2.03it/s] Validation DataLoader 0: 69%|███████████ | 109/157 [00:53<00:23, 2.03it/s] Validation DataLoader 0: 70%|███████████▏ | 110/157 [00:54<00:23, 2.03it/s] Validation DataLoader 0: 71%|███████████▎ | 111/157 [00:54<00:22, 2.03it/s] Validation DataLoader 0: 71%|███████████▍ | 112/157 [00:55<00:22, 2.03it/s] Validation DataLoader 0: 72%|███████████▌ | 113/157 [00:55<00:21, 2.03it/s] Validation DataLoader 0: 73%|███████████▌ | 114/157 [00:56<00:21, 2.02it/s] Validation DataLoader 0: 73%|███████████▋ | 115/157 [00:56<00:20, 2.03it/s] Validation DataLoader 0: 74%|███████████▊ | 116/157 [00:57<00:20, 2.03it/s] Validation DataLoader 0: 75%|███████████▉ | 117/157 [00:57<00:19, 2.03it/s] Validation DataLoader 0: 75%|████████████ | 118/157 [00:58<00:19, 2.03it/s] Validation DataLoader 0: 76%|████████████▏ | 119/157 [00:58<00:18, 2.02it/s] Validation DataLoader 0: 76%|████████████▏ | 120/157 [00:59<00:18, 2.02it/s] Validation DataLoader 0: 77%|████████████▎ | 121/157 [00:59<00:17, 2.02it/s] Validation DataLoader 0: 78%|████████████▍ | 122/157 [01:00<00:17, 2.02it/s] Validation DataLoader 0: 78%|████████████▌ | 123/157 [01:01<00:16, 2.01it/s] Validation DataLoader 0: 79%|████████████▋ | 124/157 [01:01<00:16, 2.00it/s] Validation DataLoader 0: 80%|████████████▋ | 125/157 [01:02<00:15, 2.00it/s] Validation DataLoader 0: 80%|████████████▊ | 126/157 [01:03<00:15, 2.00it/s] Validation DataLoader 0: 81%|████████████▉ | 127/157 [01:03<00:15, 2.00it/s] Validation DataLoader 0: 82%|█████████████ | 128/157 [01:04<00:14, 2.00it/s] Validation DataLoader 0: 82%|█████████████▏ | 129/157 [01:04<00:14, 2.00it/s] Validation DataLoader 0: 83%|█████████████▏ | 130/157 [01:05<00:13, 2.00it/s] Validation DataLoader 0: 83%|█████████████▎ | 131/157 [01:05<00:13, 2.00it/s] Validation DataLoader 0: 84%|█████████████▍ | 132/157 [01:06<00:12, 2.00it/s] Validation DataLoader 0: 85%|█████████████▌ | 133/157 [01:06<00:12, 2.00it/s] Validation DataLoader 0: 85%|█████████████▋ | 134/157 [01:07<00:11, 2.00it/s] Validation DataLoader 0: 86%|█████████████▊ | 135/157 [01:07<00:11, 1.99it/s] Validation DataLoader 0: 87%|█████████████▊ | 136/157 [01:08<00:10, 1.99it/s] Validation DataLoader 0: 87%|█████████████▉ | 137/157 [01:08<00:10, 1.99it/s] Validation DataLoader 0: 88%|██████████████ | 138/157 [01:09<00:09, 1.99it/s] Validation DataLoader 0: 89%|██████████████▏ | 139/157 [01:09<00:09, 1.99it/s] Validation DataLoader 0: 89%|██████████████▎ | 140/157 [01:10<00:08, 1.99it/s] Validation DataLoader 0: 90%|██████████████▎ | 141/157 [01:10<00:08, 1.99it/s] Validation DataLoader 0: 90%|██████████████▍ | 142/157 [01:11<00:07, 1.99it/s] Validation DataLoader 0: 91%|██████████████▌ | 143/157 [01:11<00:07, 1.99it/s] Validation DataLoader 0: 92%|██████████████▋ | 144/157 [01:12<00:06, 1.99it/s] Validation DataLoader 0: 92%|██████████████▊ | 145/157 [01:13<00:06, 1.99it/s] Validation DataLoader 0: 93%|██████████████▉ | 146/157 [01:13<00:05, 1.98it/s] Validation DataLoader 0: 94%|██████████████▉ | 147/157 [01:14<00:05, 1.98it/s] Validation DataLoader 0: 94%|███████████████ | 148/157 [01:14<00:04, 1.98it/s] Validation DataLoader 0: 95%|███████████████▏| 149/157 [01:15<00:04, 1.97it/s] Validation DataLoader 0: 96%|███████████████▎| 150/157 [01:15<00:03, 1.97it/s] Validation DataLoader 0: 96%|███████████████▍| 151/157 [01:16<00:03, 1.97it/s] Validation DataLoader 0: 97%|███████████████▍| 152/157 [01:17<00:02, 1.97it/s] Validation DataLoader 0: 97%|███████████████▌| 153/157 [01:17<00:02, 1.97it/s] Validation DataLoader 0: 98%|███████████████▋| 154/157 [01:18<00:01, 1.97it/s] Validation DataLoader 0: 99%|███████████████▊| 155/157 [01:18<00:01, 1.97it/s] Validation DataLoader 0: 99%|███████████████▉| 156/157 [01:19<00:00, 1.97it/s] Epoch 1: 100%|█| 351/351 [19:24<00:00, 3.32s/it, v_num=cj4f, val_loss=1.720, va Epoch 2: 100%|█| 351/351 [08:46<00:00, 1.50s/it, v_num=cj4f, val_loss=1.720, va Validation: 0it [00:00, ?it/s] Validation: 0%| | 0/157 [00:00<?, ?it/s] Validation DataLoader 0: 0%| | 0/157 [00:00<?, ?it/s] Validation DataLoader 0: 1%| | 1/157 [00:00<01:22, 1.90it/s] Validation DataLoader 0: 1%|▏ | 2/157 [00:00<01:16, 2.02it/s] Validation DataLoader 0: 2%|▎ | 3/157 [00:01<01:14, 2.06it/s] Validation DataLoader 0: 3%|▍ | 4/157 [00:02<01:19, 1.93it/s] Validation DataLoader 0: 3%|▌ | 5/157 [00:02<01:17, 1.97it/s] Validation DataLoader 0: 4%|▋ | 6/157 [00:03<01:19, 1.91it/s] Validation DataLoader 0: 4%|▊ | 7/157 [00:03<01:17, 1.94it/s] Validation DataLoader 0: 5%|▉ | 8/157 [00:04<01:15, 1.96it/s] Validation DataLoader 0: 6%|█ | 9/157 [00:04<01:15, 1.95it/s] Validation DataLoader 0: 6%|█ | 10/157 [00:05<01:14, 1.97it/s] Validation DataLoader 0: 7%|█▏ | 11/157 [00:05<01:15, 1.94it/s] Validation DataLoader 0: 8%|█▎ | 12/157 [00:06<01:14, 1.96it/s] Validation DataLoader 0: 8%|█▍ | 13/157 [00:06<01:14, 1.93it/s] Validation DataLoader 0: 9%|█▌ | 14/157 [00:07<01:14, 1.91it/s] Validation DataLoader 0: 10%|█▌ | 15/157 [00:07<01:15, 1.89it/s] Validation DataLoader 0: 10%|█▋ | 16/157 [00:08<01:14, 1.90it/s] Validation DataLoader 0: 11%|█▊ | 17/157 [00:08<01:13, 1.92it/s] Validation DataLoader 0: 11%|█▉ | 18/157 [00:09<01:12, 1.93it/s] Validation DataLoader 0: 12%|██ | 19/157 [00:09<01:11, 1.93it/s] Validation DataLoader 0: 13%|██▏ | 20/157 [00:10<01:10, 1.94it/s] Validation DataLoader 0: 13%|██▎ | 21/157 [00:10<01:09, 1.95it/s] Validation DataLoader 0: 14%|██▍ | 22/157 [00:11<01:08, 1.96it/s] Validation DataLoader 0: 15%|██▍ | 23/157 [00:11<01:08, 1.94it/s] Validation DataLoader 0: 15%|██▌ | 24/157 [00:12<01:08, 1.95it/s] Validation DataLoader 0: 16%|██▋ | 25/157 [00:12<01:07, 1.96it/s] Validation DataLoader 0: 17%|██▊ | 26/157 [00:13<01:06, 1.97it/s] Validation DataLoader 0: 17%|██▉ | 27/157 [00:13<01:05, 1.97it/s] Validation DataLoader 0: 18%|███ | 28/157 [00:14<01:05, 1.97it/s] Validation DataLoader 0: 18%|███▏ | 29/157 [00:14<01:05, 1.96it/s] Validation DataLoader 0: 19%|███▏ | 30/157 [00:15<01:04, 1.96it/s] Validation DataLoader 0: 20%|███▎ | 31/157 [00:15<01:04, 1.97it/s] Validation DataLoader 0: 20%|███▍ | 32/157 [00:16<01:03, 1.96it/s] Validation DataLoader 0: 21%|███▌ | 33/157 [00:16<01:03, 1.96it/s] Validation DataLoader 0: 22%|███▋ | 34/157 [00:17<01:02, 1.96it/s] Validation DataLoader 0: 22%|███▊ | 35/157 [00:17<01:02, 1.96it/s] Validation DataLoader 0: 23%|███▉ | 36/157 [00:18<01:01, 1.96it/s] Validation DataLoader 0: 24%|████ | 37/157 [00:18<01:01, 1.97it/s] Validation DataLoader 0: 24%|████ | 38/157 [00:19<01:00, 1.97it/s] Validation DataLoader 0: 25%|████▏ | 39/157 [00:19<00:59, 1.98it/s] Validation DataLoader 0: 25%|████▎ | 40/157 [00:20<00:59, 1.97it/s] Validation DataLoader 0: 26%|████▍ | 41/157 [00:20<00:58, 1.97it/s] Validation DataLoader 0: 27%|████▌ | 42/157 [00:21<00:58, 1.96it/s] Validation DataLoader 0: 27%|████▋ | 43/157 [00:22<00:58, 1.95it/s] Validation DataLoader 0: 28%|████▊ | 44/157 [00:22<00:58, 1.94it/s] Validation DataLoader 0: 29%|████▊ | 45/157 [00:23<00:57, 1.94it/s] Validation DataLoader 0: 29%|████▉ | 46/157 [00:23<00:57, 1.94it/s] Validation DataLoader 0: 30%|█████ | 47/157 [00:24<00:56, 1.95it/s] Validation DataLoader 0: 31%|█████▏ | 48/157 [00:24<00:55, 1.95it/s] Validation DataLoader 0: 31%|█████▎ | 49/157 [00:25<00:55, 1.95it/s] Validation DataLoader 0: 32%|█████▍ | 50/157 [00:25<00:54, 1.96it/s] Validation DataLoader 0: 32%|█████▌ | 51/157 [00:26<00:54, 1.96it/s] Validation DataLoader 0: 33%|█████▋ | 52/157 [00:26<00:53, 1.96it/s] Validation DataLoader 0: 34%|█████▋ | 53/157 [00:26<00:52, 1.97it/s] Validation DataLoader 0: 34%|█████▊ | 54/157 [00:27<00:52, 1.97it/s] Validation DataLoader 0: 35%|█████▉ | 55/157 [00:27<00:51, 1.97it/s] Validation DataLoader 0: 36%|██████ | 56/157 [00:28<00:51, 1.98it/s] Validation DataLoader 0: 36%|██████▏ | 57/157 [00:28<00:50, 1.98it/s] Validation DataLoader 0: 37%|██████▎ | 58/157 [00:29<00:49, 1.98it/s] Validation DataLoader 0: 38%|██████▍ | 59/157 [00:29<00:49, 1.98it/s] Validation DataLoader 0: 38%|██████▍ | 60/157 [00:30<00:48, 1.99it/s] Validation DataLoader 0: 39%|██████▌ | 61/157 [00:30<00:48, 1.99it/s] Validation DataLoader 0: 39%|██████▋ | 62/157 [00:31<00:47, 1.99it/s] Validation DataLoader 0: 40%|██████▊ | 63/157 [00:31<00:47, 1.99it/s] Validation DataLoader 0: 41%|██████▉ | 64/157 [00:32<00:46, 1.99it/s] Validation DataLoader 0: 41%|███████ | 65/157 [00:32<00:46, 1.99it/s] Validation DataLoader 0: 42%|███████▏ | 66/157 [00:33<00:45, 1.99it/s] Validation DataLoader 0: 43%|███████▎ | 67/157 [00:33<00:45, 1.99it/s] Validation DataLoader 0: 43%|███████▎ | 68/157 [00:34<00:44, 1.99it/s] Validation DataLoader 0: 44%|███████▍ | 69/157 [00:34<00:44, 2.00it/s] Validation DataLoader 0: 45%|███████▌ | 70/157 [00:35<00:43, 2.00it/s] Validation DataLoader 0: 45%|███████▋ | 71/157 [00:35<00:43, 2.00it/s] Validation DataLoader 0: 46%|███████▊ | 72/157 [00:36<00:42, 2.00it/s] Validation DataLoader 0: 46%|███████▉ | 73/157 [00:36<00:41, 2.00it/s] Validation DataLoader 0: 47%|████████ | 74/157 [00:36<00:41, 2.00it/s] Validation DataLoader 0: 48%|████████ | 75/157 [00:37<00:40, 2.00it/s] Validation DataLoader 0: 48%|████████▏ | 76/157 [00:37<00:40, 2.00it/s] Validation DataLoader 0: 49%|████████▎ | 77/157 [00:38<00:40, 2.00it/s] Validation DataLoader 0: 50%|████████▍ | 78/157 [00:39<00:39, 1.99it/s] Validation DataLoader 0: 50%|████████▌ | 79/157 [00:39<00:39, 1.98it/s] Validation DataLoader 0: 51%|████████▋ | 80/157 [00:40<00:38, 1.98it/s] Validation DataLoader 0: 52%|████████▊ | 81/157 [00:40<00:38, 1.99it/s] Validation DataLoader 0: 52%|████████▉ | 82/157 [00:41<00:37, 1.98it/s] Validation DataLoader 0: 53%|████████▉ | 83/157 [00:41<00:37, 1.98it/s] Validation DataLoader 0: 54%|█████████ | 84/157 [00:42<00:36, 1.98it/s] Validation DataLoader 0: 54%|█████████▏ | 85/157 [00:42<00:36, 1.99it/s] Validation DataLoader 0: 55%|█████████▎ | 86/157 [00:43<00:35, 1.99it/s] Validation DataLoader 0: 55%|█████████▍ | 87/157 [00:43<00:35, 1.99it/s] Validation DataLoader 0: 56%|█████████▌ | 88/157 [00:44<00:34, 1.99it/s] Validation DataLoader 0: 57%|█████████▋ | 89/157 [00:44<00:34, 1.99it/s] Validation DataLoader 0: 57%|█████████▋ | 90/157 [00:45<00:33, 1.98it/s] Validation DataLoader 0: 58%|█████████▊ | 91/157 [00:45<00:33, 1.98it/s] Validation DataLoader 0: 59%|█████████▉ | 92/157 [00:46<00:32, 1.98it/s] Validation DataLoader 0: 59%|██████████ | 93/157 [00:46<00:32, 1.99it/s] Validation DataLoader 0: 60%|██████████▏ | 94/157 [00:47<00:31, 1.98it/s] Validation DataLoader 0: 61%|██████████▎ | 95/157 [00:47<00:31, 1.98it/s] Validation DataLoader 0: 61%|██████████▍ | 96/157 [00:48<00:30, 1.98it/s] Validation DataLoader 0: 62%|██████████▌ | 97/157 [00:48<00:30, 1.98it/s] Validation DataLoader 0: 62%|██████████▌ | 98/157 [00:49<00:29, 1.98it/s] Validation DataLoader 0: 63%|██████████▋ | 99/157 [00:49<00:29, 1.98it/s] Validation DataLoader 0: 64%|██████████▏ | 100/157 [00:50<00:28, 1.99it/s] Validation DataLoader 0: 64%|██████████▎ | 101/157 [00:50<00:28, 1.99it/s] Validation DataLoader 0: 65%|██████████▍ | 102/157 [00:51<00:27, 1.99it/s] Validation DataLoader 0: 66%|██████████▍ | 103/157 [00:51<00:27, 1.99it/s] Validation DataLoader 0: 66%|██████████▌ | 104/157 [00:52<00:26, 1.98it/s] Validation DataLoader 0: 67%|██████████▋ | 105/157 [00:52<00:26, 1.99it/s] Validation DataLoader 0: 68%|██████████▊ | 106/157 [00:53<00:25, 1.98it/s] Validation DataLoader 0: 68%|██████████▉ | 107/157 [00:54<00:25, 1.98it/s] Validation DataLoader 0: 69%|███████████ | 108/157 [00:54<00:24, 1.98it/s] Validation DataLoader 0: 69%|███████████ | 109/157 [00:55<00:24, 1.98it/s] Validation DataLoader 0: 70%|███████████▏ | 110/157 [00:55<00:23, 1.98it/s] Validation DataLoader 0: 71%|███████████▎ | 111/157 [00:55<00:23, 1.98it/s] Validation DataLoader 0: 71%|███████████▍ | 112/157 [00:56<00:22, 1.98it/s] Validation DataLoader 0: 72%|███████████▌ | 113/157 [00:57<00:22, 1.98it/s] Validation DataLoader 0: 73%|███████████▌ | 114/157 [00:57<00:21, 1.98it/s] Validation DataLoader 0: 73%|███████████▋ | 115/157 [00:58<00:21, 1.98it/s] Validation DataLoader 0: 74%|███████████▊ | 116/157 [00:58<00:20, 1.98it/s] Validation DataLoader 0: 75%|███████████▉ | 117/157 [00:59<00:20, 1.98it/s] Validation DataLoader 0: 75%|████████████ | 118/157 [00:59<00:19, 1.98it/s] Validation DataLoader 0: 76%|████████████▏ | 119/157 [01:00<00:19, 1.98it/s] Validation DataLoader 0: 76%|████████████▏ | 120/157 [01:00<00:18, 1.98it/s] Validation DataLoader 0: 77%|████████████▎ | 121/157 [01:01<00:18, 1.98it/s] Validation DataLoader 0: 78%|████████████▍ | 122/157 [01:01<00:17, 1.98it/s] Validation DataLoader 0: 78%|████████████▌ | 123/157 [01:02<00:17, 1.97it/s] Validation DataLoader 0: 79%|████████████▋ | 124/157 [01:02<00:16, 1.98it/s] Validation DataLoader 0: 80%|████████████▋ | 125/157 [01:03<00:16, 1.98it/s] Validation DataLoader 0: 80%|████████████▊ | 126/157 [01:03<00:15, 1.98it/s] Validation DataLoader 0: 81%|████████████▉ | 127/157 [01:04<00:15, 1.97it/s] Validation DataLoader 0: 82%|█████████████ | 128/157 [01:04<00:14, 1.97it/s] Validation DataLoader 0: 82%|█████████████▏ | 129/157 [01:05<00:14, 1.98it/s] Validation DataLoader 0: 83%|█████████████▏ | 130/157 [01:05<00:13, 1.98it/s] Validation DataLoader 0: 83%|█████████████▎ | 131/157 [01:06<00:13, 1.98it/s] Validation DataLoader 0: 84%|█████████████▍ | 132/157 [01:06<00:12, 1.98it/s] Validation DataLoader 0: 85%|█████████████▌ | 133/157 [01:07<00:12, 1.98it/s] Validation DataLoader 0: 85%|█████████████▋ | 134/157 [01:07<00:11, 1.98it/s] Validation DataLoader 0: 86%|█████████████▊ | 135/157 [01:08<00:11, 1.98it/s] Validation DataLoader 0: 87%|█████████████▊ | 136/157 [01:08<00:10, 1.98it/s] Validation DataLoader 0: 87%|█████████████▉ | 137/157 [01:09<00:10, 1.98it/s] Validation DataLoader 0: 88%|██████████████ | 138/157 [01:09<00:09, 1.98it/s] Validation DataLoader 0: 89%|██████████████▏ | 139/157 [01:10<00:09, 1.99it/s] Validation DataLoader 0: 89%|██████████████▎ | 140/157 [01:10<00:08, 1.99it/s] Validation DataLoader 0: 90%|██████████████▎ | 141/157 [01:10<00:08, 1.99it/s] Validation DataLoader 0: 90%|██████████████▍ | 142/157 [01:11<00:07, 1.99it/s] Validation DataLoader 0: 91%|██████████████▌ | 143/157 [01:12<00:07, 1.98it/s] Validation DataLoader 0: 92%|██████████████▋ | 144/157 [01:12<00:06, 1.99it/s] Validation DataLoader 0: 92%|██████████████▊ | 145/157 [01:12<00:06, 1.99it/s] Validation DataLoader 0: 93%|██████████████▉ | 146/157 [01:13<00:05, 1.99it/s] Validation DataLoader 0: 94%|██████████████▉ | 147/157 [01:13<00:05, 1.99it/s] Validation DataLoader 0: 94%|███████████████ | 148/157 [01:14<00:04, 1.99it/s] Validation DataLoader 0: 95%|███████████████▏| 149/157 [01:15<00:04, 1.99it/s] Validation DataLoader 0: 96%|███████████████▎| 150/157 [01:15<00:03, 1.99it/s] Validation DataLoader 0: 96%|███████████████▍| 151/157 [01:16<00:03, 1.98it/s] Validation DataLoader 0: 97%|███████████████▍| 152/157 [01:16<00:02, 1.99it/s] Validation DataLoader 0: 97%|███████████████▌| 153/157 [01:17<00:02, 1.99it/s] Validation DataLoader 0: 98%|███████████████▋| 154/157 [01:17<00:01, 1.98it/s] Validation DataLoader 0: 99%|███████████████▊| 155/157 [01:18<00:01, 1.98it/s] Validation DataLoader 0: 99%|███████████████▉| 156/157 [01:18<00:00, 1.99it/s] Epoch 2: 100%|█| 351/351 [10:05<00:00, 1.72s/it, v_num=cj4f, val_loss=1.650, va Epoch 3: 100%|█| 351/351 [08:18<00:00, 1.42s/it, v_num=cj4f, val_loss=1.650, va Validation: 0it [00:00, ?it/s] Validation: 0%| | 0/157 [00:00<?, ?it/s] Validation DataLoader 0: 0%| | 0/157 [00:00<?, ?it/s] Validation DataLoader 0: 1%| | 1/157 [00:00<01:17, 2.01it/s] Validation DataLoader 0: 1%|▏ | 2/157 [00:00<01:14, 2.08it/s] Validation DataLoader 0: 2%|▎ | 3/157 [00:01<01:13, 2.09it/s] Validation DataLoader 0: 3%|▍ | 4/157 [00:01<01:12, 2.11it/s] Validation DataLoader 0: 3%|▌ | 5/157 [00:02<01:11, 2.12it/s] Validation DataLoader 0: 4%|▋ | 6/157 [00:02<01:12, 2.09it/s] Validation DataLoader 0: 4%|▊ | 7/157 [00:03<01:11, 2.09it/s] Validation DataLoader 0: 5%|▉ | 8/157 [00:03<01:12, 2.06it/s] Validation DataLoader 0: 6%|█ | 9/157 [00:04<01:11, 2.07it/s] Validation DataLoader 0: 6%|█ | 10/157 [00:04<01:11, 2.05it/s] Validation DataLoader 0: 7%|█▏ | 11/157 [00:05<01:12, 2.02it/s] Validation DataLoader 0: 8%|█▎ | 12/157 [00:05<01:11, 2.03it/s] Validation DataLoader 0: 8%|█▍ | 13/157 [00:06<01:10, 2.04it/s] Validation DataLoader 0: 9%|█▌ | 14/157 [00:06<01:10, 2.04it/s] Validation DataLoader 0: 10%|█▌ | 15/157 [00:07<01:09, 2.05it/s] Validation DataLoader 0: 10%|█▋ | 16/157 [00:07<01:08, 2.06it/s] Validation DataLoader 0: 11%|█▊ | 17/157 [00:08<01:08, 2.06it/s] Validation DataLoader 0: 11%|█▉ | 18/157 [00:08<01:07, 2.06it/s] Validation DataLoader 0: 12%|██ | 19/157 [00:09<01:06, 2.07it/s] Validation DataLoader 0: 13%|██▏ | 20/157 [00:09<01:06, 2.07it/s] Validation DataLoader 0: 13%|██▎ | 21/157 [00:10<01:05, 2.07it/s] Validation DataLoader 0: 14%|██▍ | 22/157 [00:10<01:04, 2.08it/s] Validation DataLoader 0: 15%|██▍ | 23/157 [00:11<01:04, 2.08it/s] Validation DataLoader 0: 15%|██▌ | 24/157 [00:11<01:03, 2.08it/s] Validation DataLoader 0: 16%|██▋ | 25/157 [00:11<01:03, 2.09it/s] Validation DataLoader 0: 17%|██▊ | 26/157 [00:12<01:02, 2.09it/s] Validation DataLoader 0: 17%|██▉ | 27/157 [00:12<01:02, 2.09it/s] Validation DataLoader 0: 18%|███ | 28/157 [00:13<01:01, 2.09it/s] Validation DataLoader 0: 18%|███▏ | 29/157 [00:13<01:01, 2.08it/s] Validation DataLoader 0: 19%|███▏ | 30/157 [00:14<01:00, 2.08it/s] Validation DataLoader 0: 20%|███▎ | 31/157 [00:14<01:00, 2.09it/s] Validation DataLoader 0: 20%|███▍ | 32/157 [00:15<01:00, 2.08it/s] Validation DataLoader 0: 21%|███▌ | 33/157 [00:15<00:59, 2.08it/s] Validation DataLoader 0: 22%|███▋ | 34/157 [00:16<00:59, 2.07it/s] Validation DataLoader 0: 22%|███▊ | 35/157 [00:16<00:58, 2.07it/s] Validation DataLoader 0: 23%|███▉ | 36/157 [00:17<00:58, 2.07it/s] Validation DataLoader 0: 24%|████ | 37/157 [00:17<00:57, 2.07it/s] Validation DataLoader 0: 24%|████ | 38/157 [00:18<00:57, 2.08it/s] Validation DataLoader 0: 25%|████▏ | 39/157 [00:18<00:56, 2.08it/s] Validation DataLoader 0: 25%|████▎ | 40/157 [00:19<00:56, 2.08it/s] Validation DataLoader 0: 26%|████▍ | 41/157 [00:19<00:55, 2.08it/s] Validation DataLoader 0: 27%|████▌ | 42/157 [00:20<00:55, 2.08it/s] Validation DataLoader 0: 27%|████▋ | 43/157 [00:20<00:54, 2.08it/s] Validation DataLoader 0: 28%|████▊ | 44/157 [00:21<00:54, 2.07it/s] Validation DataLoader 0: 29%|████▊ | 45/157 [00:21<00:54, 2.06it/s] Validation DataLoader 0: 29%|████▉ | 46/157 [00:22<00:54, 2.04it/s] Validation DataLoader 0: 30%|█████ | 47/157 [00:23<00:54, 2.03it/s] Validation DataLoader 0: 31%|█████▏ | 48/157 [00:23<00:53, 2.02it/s] Validation DataLoader 0: 31%|█████▎ | 49/157 [00:24<00:53, 2.03it/s] Validation DataLoader 0: 32%|█████▍ | 50/157 [00:24<00:52, 2.03it/s] Validation DataLoader 0: 32%|█████▌ | 51/157 [00:25<00:52, 2.02it/s] Validation DataLoader 0: 33%|█████▋ | 52/157 [00:25<00:51, 2.03it/s] Validation DataLoader 0: 34%|█████▋ | 53/157 [00:26<00:51, 2.02it/s] Validation DataLoader 0: 34%|█████▊ | 54/157 [00:26<00:51, 2.01it/s] Validation DataLoader 0: 35%|█████▉ | 55/157 [00:27<00:50, 2.01it/s] Validation DataLoader 0: 36%|██████ | 56/157 [00:27<00:50, 2.01it/s] Validation DataLoader 0: 36%|██████▏ | 57/157 [00:28<00:49, 2.00it/s] Validation DataLoader 0: 37%|██████▎ | 58/157 [00:29<00:49, 2.00it/s] Validation DataLoader 0: 38%|██████▍ | 59/157 [00:29<00:49, 1.99it/s] Validation DataLoader 0: 38%|██████▍ | 60/157 [00:30<00:48, 1.99it/s] Validation DataLoader 0: 39%|██████▌ | 61/157 [00:30<00:48, 1.99it/s] Validation DataLoader 0: 39%|██████▋ | 62/157 [00:31<00:47, 1.99it/s] Validation DataLoader 0: 40%|██████▊ | 63/157 [00:31<00:47, 2.00it/s] Validation DataLoader 0: 41%|██████▉ | 64/157 [00:32<00:46, 2.00it/s] Validation DataLoader 0: 41%|███████ | 65/157 [00:32<00:45, 2.00it/s] Validation DataLoader 0: 42%|███████▏ | 66/157 [00:32<00:45, 2.00it/s] Validation DataLoader 0: 43%|███████▎ | 67/157 [00:33<00:44, 2.00it/s] Validation DataLoader 0: 43%|███████▎ | 68/157 [00:33<00:44, 2.00it/s] Validation DataLoader 0: 44%|███████▍ | 69/157 [00:34<00:44, 2.00it/s] Validation DataLoader 0: 45%|███████▌ | 70/157 [00:35<00:43, 2.00it/s] Validation DataLoader 0: 45%|███████▋ | 71/157 [00:35<00:42, 2.00it/s] Validation DataLoader 0: 46%|███████▊ | 72/157 [00:36<00:42, 2.00it/s] Validation DataLoader 0: 46%|███████▉ | 73/157 [00:36<00:42, 2.00it/s] Validation DataLoader 0: 47%|████████ | 74/157 [00:37<00:41, 2.00it/s] Validation DataLoader 0: 48%|████████ | 75/157 [00:37<00:41, 1.99it/s] Validation DataLoader 0: 48%|████████▏ | 76/157 [00:38<00:40, 1.99it/s] Validation DataLoader 0: 49%|████████▎ | 77/157 [00:38<00:40, 1.99it/s] Validation DataLoader 0: 50%|████████▍ | 78/157 [00:39<00:39, 1.99it/s] Validation DataLoader 0: 50%|████████▌ | 79/157 [00:39<00:39, 1.99it/s] Validation DataLoader 0: 51%|████████▋ | 80/157 [00:40<00:38, 1.99it/s] Validation DataLoader 0: 52%|████████▊ | 81/157 [00:40<00:38, 1.99it/s] Validation DataLoader 0: 52%|████████▉ | 82/157 [00:41<00:37, 2.00it/s] Validation DataLoader 0: 53%|████████▉ | 83/157 [00:41<00:37, 2.00it/s] Validation DataLoader 0: 54%|█████████ | 84/157 [00:42<00:36, 2.00it/s] Validation DataLoader 0: 54%|█████████▏ | 85/157 [00:42<00:35, 2.00it/s] Validation DataLoader 0: 55%|█████████▎ | 86/157 [00:42<00:35, 2.00it/s] Validation DataLoader 0: 55%|█████████▍ | 87/157 [00:43<00:34, 2.00it/s] Validation DataLoader 0: 56%|█████████▌ | 88/157 [00:43<00:34, 2.01it/s] Validation DataLoader 0: 57%|█████████▋ | 89/157 [00:44<00:33, 2.01it/s] Validation DataLoader 0: 57%|█████████▋ | 90/157 [00:44<00:33, 2.01it/s] Validation DataLoader 0: 58%|█████████▊ | 91/157 [00:45<00:32, 2.01it/s] Validation DataLoader 0: 59%|█████████▉ | 92/157 [00:45<00:32, 2.01it/s] Validation DataLoader 0: 59%|██████████ | 93/157 [00:46<00:31, 2.01it/s] Validation DataLoader 0: 60%|██████████▏ | 94/157 [00:46<00:31, 2.01it/s] Validation DataLoader 0: 61%|██████████▎ | 95/157 [00:47<00:30, 2.01it/s] Validation DataLoader 0: 61%|██████████▍ | 96/157 [00:47<00:30, 2.01it/s] Validation DataLoader 0: 62%|██████████▌ | 97/157 [00:48<00:29, 2.02it/s] Validation DataLoader 0: 62%|██████████▌ | 98/157 [00:48<00:29, 2.01it/s] Validation DataLoader 0: 63%|██████████▋ | 99/157 [00:49<00:28, 2.02it/s] Validation DataLoader 0: 64%|██████████▏ | 100/157 [00:49<00:28, 2.01it/s] Validation DataLoader 0: 64%|██████████▎ | 101/157 [00:50<00:27, 2.01it/s] Validation DataLoader 0: 65%|██████████▍ | 102/157 [00:50<00:27, 2.00it/s] Validation DataLoader 0: 66%|██████████▍ | 103/157 [00:51<00:26, 2.00it/s] Validation DataLoader 0: 66%|██████████▌ | 104/157 [00:51<00:26, 2.00it/s] Validation DataLoader 0: 67%|██████████▋ | 105/157 [00:52<00:25, 2.00it/s] Validation DataLoader 0: 68%|██████████▊ | 106/157 [00:52<00:25, 2.00it/s] Validation DataLoader 0: 68%|██████████▉ | 107/157 [00:53<00:24, 2.00it/s] Validation DataLoader 0: 69%|███████████ | 108/157 [00:53<00:24, 2.00it/s] Validation DataLoader 0: 69%|███████████ | 109/157 [00:54<00:23, 2.01it/s] Validation DataLoader 0: 70%|███████████▏ | 110/157 [00:54<00:23, 2.01it/s] Validation DataLoader 0: 71%|███████████▎ | 111/157 [00:55<00:22, 2.01it/s] Validation DataLoader 0: 71%|███████████▍ | 112/157 [00:55<00:22, 2.01it/s] Validation DataLoader 0: 72%|███████████▌ | 113/157 [00:56<00:21, 2.01it/s] Validation DataLoader 0: 73%|███████████▌ | 114/157 [00:56<00:21, 2.01it/s] Validation DataLoader 0: 73%|███████████▋ | 115/157 [00:57<00:20, 2.01it/s] Validation DataLoader 0: 74%|███████████▊ | 116/157 [00:57<00:20, 2.01it/s] Validation DataLoader 0: 75%|███████████▉ | 117/157 [00:58<00:19, 2.01it/s] Validation DataLoader 0: 75%|████████████ | 118/157 [00:58<00:19, 2.01it/s] Validation DataLoader 0: 76%|████████████▏ | 119/157 [00:59<00:18, 2.01it/s] Validation DataLoader 0: 76%|████████████▏ | 120/157 [00:59<00:18, 2.01it/s] Validation DataLoader 0: 77%|████████████▎ | 121/157 [01:00<00:17, 2.01it/s] Validation DataLoader 0: 78%|████████████▍ | 122/157 [01:00<00:17, 2.01it/s] Validation DataLoader 0: 78%|████████████▌ | 123/157 [01:01<00:16, 2.01it/s] Validation DataLoader 0: 79%|████████████▋ | 124/157 [01:01<00:16, 2.01it/s] Validation DataLoader 0: 80%|████████████▋ | 125/157 [01:02<00:15, 2.01it/s] Validation DataLoader 0: 80%|████████████▊ | 126/157 [01:02<00:15, 2.01it/s] Validation DataLoader 0: 81%|████████████▉ | 127/157 [01:03<00:14, 2.01it/s] Validation DataLoader 0: 82%|█████████████ | 128/157 [01:03<00:14, 2.01it/s] Validation DataLoader 0: 82%|█████████████▏ | 129/157 [01:04<00:13, 2.01it/s] Validation DataLoader 0: 83%|█████████████▏ | 130/157 [01:04<00:13, 2.01it/s] Validation DataLoader 0: 83%|█████████████▎ | 131/157 [01:05<00:12, 2.01it/s] Validation DataLoader 0: 84%|█████████████▍ | 132/157 [01:05<00:12, 2.01it/s] Validation DataLoader 0: 85%|█████████████▌ | 133/157 [01:06<00:11, 2.01it/s] Validation DataLoader 0: 85%|█████████████▋ | 134/157 [01:06<00:11, 2.01it/s] Validation DataLoader 0: 86%|█████████████▊ | 135/157 [01:07<00:10, 2.01it/s] Validation DataLoader 0: 87%|█████████████▊ | 136/157 [01:07<00:10, 2.01it/s] Validation DataLoader 0: 87%|█████████████▉ | 137/157 [01:08<00:09, 2.01it/s] Validation DataLoader 0: 88%|██████████████ | 138/157 [01:08<00:09, 2.01it/s] Validation DataLoader 0: 89%|██████████████▏ | 139/157 [01:09<00:08, 2.01it/s] Validation DataLoader 0: 89%|██████████████▎ | 140/157 [01:09<00:08, 2.01it/s] Validation DataLoader 0: 90%|██████████████▎ | 141/157 [01:10<00:07, 2.01it/s] Validation DataLoader 0: 90%|██████████████▍ | 142/157 [01:10<00:07, 2.01it/s] Validation DataLoader 0: 91%|██████████████▌ | 143/157 [01:11<00:06, 2.01it/s] Validation DataLoader 0: 92%|██████████████▋ | 144/157 [01:11<00:06, 2.01it/s] Validation DataLoader 0: 92%|██████████████▊ | 145/157 [01:12<00:05, 2.01it/s] Validation DataLoader 0: 93%|██████████████▉ | 146/157 [01:12<00:05, 2.01it/s] Validation DataLoader 0: 94%|██████████████▉ | 147/157 [01:13<00:04, 2.01it/s] Validation DataLoader 0: 94%|███████████████ | 148/157 [01:13<00:04, 2.01it/s] Validation DataLoader 0: 95%|███████████████▏| 149/157 [01:13<00:03, 2.01it/s] Validation DataLoader 0: 96%|███████████████▎| 150/157 [01:14<00:03, 2.01it/s] Validation DataLoader 0: 96%|███████████████▍| 151/157 [01:15<00:02, 2.01it/s] Validation DataLoader 0: 97%|███████████████▍| 152/157 [01:15<00:02, 2.01it/s] Validation DataLoader 0: 97%|███████████████▌| 153/157 [01:15<00:01, 2.01it/s] Validation DataLoader 0: 98%|███████████████▋| 154/157 [01:16<00:01, 2.01it/s] Validation DataLoader 0: 99%|███████████████▊| 155/157 [01:17<00:00, 2.01it/s] Validation DataLoader 0: 99%|███████████████▉| 156/157 [01:17<00:00, 2.01it/s] Epoch 3: 100%|█| 351/351 [09:36<00:00, 1.64s/it, v_num=cj4f, val_loss=1.610, va Epoch 4: 100%|█| 351/351 [08:19<00:00, 1.42s/it, v_num=cj4f, val_loss=1.610, va Validation: 0it [00:00, ?it/s] Validation: 0%| | 0/157 [00:00<?, ?it/s] Validation DataLoader 0: 0%| | 0/157 [00:00<?, ?it/s] Validation DataLoader 0: 1%| | 1/157 [00:00<01:28, 1.77it/s] Validation DataLoader 0: 1%|▏ | 2/157 [00:01<01:19, 1.94it/s] Validation DataLoader 0: 2%|▎ | 3/157 [00:01<01:16, 2.01it/s] Validation DataLoader 0: 3%|▍ | 4/157 [00:01<01:14, 2.04it/s] Validation DataLoader 0: 3%|▌ | 5/157 [00:02<01:13, 2.06it/s] Validation DataLoader 0: 4%|▋ | 6/157 [00:02<01:13, 2.04it/s] Validation DataLoader 0: 4%|▊ | 7/157 [00:03<01:12, 2.06it/s] Validation DataLoader 0: 5%|▉ | 8/157 [00:03<01:11, 2.07it/s] Validation DataLoader 0: 6%|█ | 9/157 [00:04<01:12, 2.04it/s] Validation DataLoader 0: 6%|█ | 10/157 [00:04<01:11, 2.05it/s] Validation DataLoader 0: 7%|█▏ | 11/157 [00:05<01:10, 2.06it/s] Validation DataLoader 0: 8%|█▎ | 12/157 [00:05<01:10, 2.07it/s] Validation DataLoader 0: 8%|█▍ | 13/157 [00:06<01:09, 2.07it/s] Validation DataLoader 0: 9%|█▌ | 14/157 [00:06<01:08, 2.08it/s] Validation DataLoader 0: 10%|█▌ | 15/157 [00:07<01:09, 2.04it/s] Validation DataLoader 0: 10%|█▋ | 16/157 [00:07<01:09, 2.04it/s] Validation DataLoader 0: 11%|█▊ | 17/157 [00:08<01:09, 2.02it/s] Validation DataLoader 0: 11%|█▉ | 18/157 [00:08<01:08, 2.03it/s] Validation DataLoader 0: 12%|██ | 19/157 [00:09<01:07, 2.03it/s] Validation DataLoader 0: 13%|██▏ | 20/157 [00:09<01:07, 2.04it/s] Validation DataLoader 0: 13%|██▎ | 21/157 [00:10<01:06, 2.04it/s] Validation DataLoader 0: 14%|██▍ | 22/157 [00:10<01:05, 2.05it/s] Validation DataLoader 0: 15%|██▍ | 23/157 [00:11<01:06, 2.03it/s] Validation DataLoader 0: 15%|██▌ | 24/157 [00:11<01:05, 2.04it/s] Validation DataLoader 0: 16%|██▋ | 25/157 [00:12<01:05, 2.02it/s] Validation DataLoader 0: 17%|██▊ | 26/157 [00:12<01:04, 2.02it/s] Validation DataLoader 0: 17%|██▉ | 27/157 [00:13<01:04, 2.03it/s] Validation DataLoader 0: 18%|███ | 28/157 [00:13<01:04, 2.01it/s] Validation DataLoader 0: 18%|███▏ | 29/157 [00:14<01:04, 2.00it/s] Validation DataLoader 0: 19%|███▏ | 30/157 [00:15<01:03, 1.99it/s] Validation DataLoader 0: 20%|███▎ | 31/157 [00:15<01:03, 1.98it/s] Validation DataLoader 0: 20%|███▍ | 32/157 [00:16<01:03, 1.98it/s] Validation DataLoader 0: 21%|███▌ | 33/157 [00:16<01:02, 1.98it/s] Validation DataLoader 0: 22%|███▋ | 34/157 [00:17<01:01, 1.99it/s] Validation DataLoader 0: 22%|███▊ | 35/157 [00:17<01:01, 1.99it/s] Validation DataLoader 0: 23%|███▉ | 36/157 [00:18<01:00, 2.00it/s] Validation DataLoader 0: 24%|████ | 37/157 [00:18<01:00, 1.98it/s] Validation DataLoader 0: 24%|████ | 38/157 [00:19<00:59, 1.99it/s] Validation DataLoader 0: 25%|████▏ | 39/157 [00:19<00:59, 1.98it/s] Validation DataLoader 0: 25%|████▎ | 40/157 [00:20<00:59, 1.98it/s] Validation DataLoader 0: 26%|████▍ | 41/157 [00:20<00:58, 1.99it/s] Validation DataLoader 0: 27%|████▌ | 42/157 [00:21<00:58, 1.98it/s] Validation DataLoader 0: 27%|████▋ | 43/157 [00:21<00:57, 1.98it/s] Validation DataLoader 0: 28%|████▊ | 44/157 [00:22<00:57, 1.97it/s] Validation DataLoader 0: 29%|████▊ | 45/157 [00:22<00:56, 1.97it/s] Validation DataLoader 0: 29%|████▉ | 46/157 [00:23<00:56, 1.98it/s] Validation DataLoader 0: 30%|█████ | 47/157 [00:23<00:55, 1.98it/s] Validation DataLoader 0: 31%|█████▏ | 48/157 [00:24<00:55, 1.97it/s] Validation DataLoader 0: 31%|█████▎ | 49/157 [00:24<00:54, 1.97it/s] Validation DataLoader 0: 32%|█████▍ | 50/157 [00:25<00:54, 1.98it/s] Validation DataLoader 0: 32%|█████▌ | 51/157 [00:25<00:53, 1.98it/s] Validation DataLoader 0: 33%|█████▋ | 52/157 [00:26<00:52, 1.98it/s] Validation DataLoader 0: 34%|█████▋ | 53/157 [00:26<00:52, 1.98it/s] Validation DataLoader 0: 34%|█████▊ | 54/157 [00:27<00:51, 1.98it/s] Validation DataLoader 0: 35%|█████▉ | 55/157 [00:27<00:51, 1.99it/s] Validation DataLoader 0: 36%|██████ | 56/157 [00:28<00:50, 1.99it/s] Validation DataLoader 0: 36%|██████▏ | 57/157 [00:28<00:50, 1.99it/s] Validation DataLoader 0: 37%|██████▎ | 58/157 [00:29<00:49, 1.99it/s] Validation DataLoader 0: 38%|██████▍ | 59/157 [00:29<00:49, 1.99it/s] Validation DataLoader 0: 38%|██████▍ | 60/157 [00:30<00:48, 1.99it/s] Validation DataLoader 0: 39%|██████▌ | 61/157 [00:30<00:48, 1.99it/s] Validation DataLoader 0: 39%|██████▋ | 62/157 [00:31<00:47, 1.99it/s] Validation DataLoader 0: 40%|██████▊ | 63/157 [00:31<00:47, 2.00it/s] Validation DataLoader 0: 41%|██████▉ | 64/157 [00:32<00:46, 2.00it/s] Validation DataLoader 0: 41%|███████ | 65/157 [00:32<00:46, 2.00it/s] Validation DataLoader 0: 42%|███████▏ | 66/157 [00:33<00:45, 2.00it/s] Validation DataLoader 0: 43%|███████▎ | 67/157 [00:33<00:45, 2.00it/s] Validation DataLoader 0: 43%|███████▎ | 68/157 [00:33<00:44, 2.00it/s] Validation DataLoader 0: 44%|███████▍ | 69/157 [00:34<00:43, 2.00it/s] Validation DataLoader 0: 45%|███████▌ | 70/157 [00:34<00:43, 2.01it/s] Validation DataLoader 0: 45%|███████▋ | 71/157 [00:35<00:42, 2.01it/s] Validation DataLoader 0: 46%|███████▊ | 72/157 [00:35<00:42, 2.01it/s] Validation DataLoader 0: 46%|███████▉ | 73/157 [00:36<00:41, 2.00it/s] Validation DataLoader 0: 47%|████████ | 74/157 [00:36<00:41, 2.01it/s] Validation DataLoader 0: 48%|████████ | 75/157 [00:37<00:40, 2.00it/s] Validation DataLoader 0: 48%|████████▏ | 76/157 [00:38<00:40, 2.00it/s] Validation DataLoader 0: 49%|████████▎ | 77/157 [00:38<00:39, 2.00it/s] Validation DataLoader 0: 50%|████████▍ | 78/157 [00:38<00:39, 2.00it/s] Validation DataLoader 0: 50%|████████▌ | 79/157 [00:39<00:39, 2.00it/s] Validation DataLoader 0: 51%|████████▋ | 80/157 [00:40<00:38, 1.99it/s] Validation DataLoader 0: 52%|████████▊ | 81/157 [00:40<00:38, 1.99it/s] Validation DataLoader 0: 52%|████████▉ | 82/157 [00:41<00:37, 1.99it/s] Validation DataLoader 0: 53%|████████▉ | 83/157 [00:41<00:37, 1.99it/s] Validation DataLoader 0: 54%|█████████ | 84/157 [00:42<00:36, 1.98it/s] Validation DataLoader 0: 54%|█████████▏ | 85/157 [00:42<00:36, 1.99it/s] Validation DataLoader 0: 55%|█████████▎ | 86/157 [00:43<00:35, 1.98it/s] Validation DataLoader 0: 55%|█████████▍ | 87/157 [00:43<00:35, 1.98it/s] Validation DataLoader 0: 56%|█████████▌ | 88/157 [00:44<00:34, 1.99it/s] Validation DataLoader 0: 57%|█████████▋ | 89/157 [00:44<00:34, 1.98it/s] Validation DataLoader 0: 57%|█████████▋ | 90/157 [00:45<00:33, 1.98it/s] Validation DataLoader 0: 58%|█████████▊ | 91/157 [00:45<00:33, 1.98it/s] Validation DataLoader 0: 59%|█████████▉ | 92/157 [00:46<00:32, 1.98it/s] Validation DataLoader 0: 59%|██████████ | 93/157 [00:46<00:32, 1.98it/s] Validation DataLoader 0: 60%|██████████▏ | 94/157 [00:47<00:31, 1.98it/s] Validation DataLoader 0: 61%|██████████▎ | 95/157 [00:47<00:31, 1.99it/s] Validation DataLoader 0: 61%|██████████▍ | 96/157 [00:48<00:30, 1.98it/s] Validation DataLoader 0: 62%|██████████▌ | 97/157 [00:48<00:30, 1.98it/s] Validation DataLoader 0: 62%|██████████▌ | 98/157 [00:49<00:29, 1.98it/s] Validation DataLoader 0: 63%|██████████▋ | 99/157 [00:49<00:29, 1.98it/s] Validation DataLoader 0: 64%|██████████▏ | 100/157 [00:50<00:28, 1.98it/s] Validation DataLoader 0: 64%|██████████▎ | 101/157 [00:50<00:28, 1.98it/s] Validation DataLoader 0: 65%|██████████▍ | 102/157 [00:51<00:27, 1.99it/s] Validation DataLoader 0: 66%|██████████▍ | 103/157 [00:51<00:27, 1.99it/s] Validation DataLoader 0: 66%|██████████▌ | 104/157 [00:52<00:26, 1.99it/s] Validation DataLoader 0: 67%|██████████▋ | 105/157 [00:52<00:26, 1.99it/s] Validation DataLoader 0: 68%|██████████▊ | 106/157 [00:53<00:25, 1.99it/s] Validation DataLoader 0: 68%|██████████▉ | 107/157 [00:53<00:25, 1.99it/s] Validation DataLoader 0: 69%|███████████ | 108/157 [00:54<00:24, 1.99it/s] Validation DataLoader 0: 69%|███████████ | 109/157 [00:54<00:24, 1.99it/s] Validation DataLoader 0: 70%|███████████▏ | 110/157 [00:55<00:23, 1.99it/s] Validation DataLoader 0: 71%|███████████▎ | 111/157 [00:55<00:23, 1.99it/s] Validation DataLoader 0: 71%|███████████▍ | 112/157 [00:56<00:22, 1.99it/s] Validation DataLoader 0: 72%|███████████▌ | 113/157 [00:56<00:22, 1.99it/s] Validation DataLoader 0: 73%|███████████▌ | 114/157 [00:57<00:21, 2.00it/s] Validation DataLoader 0: 73%|███████████▋ | 115/157 [00:57<00:21, 2.00it/s] Validation DataLoader 0: 74%|███████████▊ | 116/157 [00:58<00:20, 1.99it/s] Validation DataLoader 0: 75%|███████████▉ | 117/157 [00:58<00:20, 1.99it/s] Validation DataLoader 0: 75%|████████████ | 118/157 [00:59<00:19, 1.99it/s] Validation DataLoader 0: 76%|████████████▏ | 119/157 [00:59<00:19, 1.99it/s] Validation DataLoader 0: 76%|████████████▏ | 120/157 [01:00<00:18, 2.00it/s] Validation DataLoader 0: 77%|████████████▎ | 121/157 [01:00<00:18, 1.99it/s] Validation DataLoader 0: 78%|████████████▍ | 122/157 [01:01<00:17, 2.00it/s] Validation DataLoader 0: 78%|████████████▌ | 123/157 [01:01<00:17, 1.99it/s] Validation DataLoader 0: 79%|████████████▋ | 124/157 [01:02<00:16, 2.00it/s] Validation DataLoader 0: 80%|████████████▋ | 125/157 [01:02<00:16, 2.00it/s] Validation DataLoader 0: 80%|████████████▊ | 126/157 [01:03<00:15, 1.99it/s] Validation DataLoader 0: 81%|████████████▉ | 127/157 [01:03<00:15, 2.00it/s] Validation DataLoader 0: 82%|█████████████ | 128/157 [01:04<00:14, 1.99it/s] Validation DataLoader 0: 82%|█████████████▏ | 129/157 [01:04<00:14, 1.99it/s] Validation DataLoader 0: 83%|█████████████▏ | 130/157 [01:05<00:13, 1.99it/s] Validation DataLoader 0: 83%|█████████████▎ | 131/157 [01:05<00:13, 1.99it/s] Validation DataLoader 0: 84%|█████████████▍ | 132/157 [01:06<00:12, 1.99it/s] Validation DataLoader 0: 85%|█████████████▌ | 133/157 [01:06<00:12, 2.00it/s] Validation DataLoader 0: 85%|█████████████▋ | 134/157 [01:07<00:11, 1.99it/s] Validation DataLoader 0: 86%|█████████████▊ | 135/157 [01:07<00:11, 1.99it/s] Validation DataLoader 0: 87%|█████████████▊ | 136/157 [01:08<00:10, 1.99it/s] Validation DataLoader 0: 87%|█████████████▉ | 137/157 [01:08<00:10, 1.99it/s] Validation DataLoader 0: 88%|██████████████ | 138/157 [01:09<00:09, 1.99it/s] Validation DataLoader 0: 89%|██████████████▏ | 139/157 [01:09<00:09, 1.99it/s] Validation DataLoader 0: 89%|██████████████▎ | 140/157 [01:10<00:08, 1.99it/s] Validation DataLoader 0: 90%|██████████████▎ | 141/157 [01:10<00:08, 1.99it/s] Validation DataLoader 0: 90%|██████████████▍ | 142/157 [01:11<00:07, 1.99it/s] Validation DataLoader 0: 91%|██████████████▌ | 143/157 [01:11<00:07, 1.99it/s] Validation DataLoader 0: 92%|██████████████▋ | 144/157 [01:12<00:06, 1.99it/s] Validation DataLoader 0: 92%|██████████████▊ | 145/157 [01:12<00:06, 1.99it/s] Validation DataLoader 0: 93%|██████████████▉ | 146/157 [01:13<00:05, 1.99it/s] Validation DataLoader 0: 94%|██████████████▉ | 147/157 [01:13<00:05, 1.99it/s] Validation DataLoader 0: 94%|███████████████ | 148/157 [01:14<00:04, 1.99it/s] Validation DataLoader 0: 95%|███████████████▏| 149/157 [01:14<00:04, 1.99it/s] Validation DataLoader 0: 96%|███████████████▎| 150/157 [01:15<00:03, 1.99it/s] Validation DataLoader 0: 96%|███████████████▍| 151/157 [01:15<00:03, 1.99it/s] Validation DataLoader 0: 97%|███████████████▍| 152/157 [01:16<00:02, 1.99it/s] Validation DataLoader 0: 97%|███████████████▌| 153/157 [01:16<00:02, 1.99it/s] Validation DataLoader 0: 98%|███████████████▋| 154/157 [01:17<00:01, 1.99it/s] Validation DataLoader 0: 99%|███████████████▊| 155/157 [01:17<00:01, 1.99it/s] Validation DataLoader 0: 99%|███████████████▉| 156/157 [01:18<00:00, 1.99it/s] Epoch 4: 100%|█| 351/351 [09:37<00:00, 1.65s/it, v_num=cj4f, val_loss=1.570, va Epoch 4: 100%|█| 351/351 [09:37<00:00, 1.65s/it, v_num=cj4f, val_loss=1.570, va
`Trainer.fit` stopped: `max_epochs=5` reached.
Epoch 4: 100%|█| 351/351 [09:37<00:00, 1.65s/it, v_num=cj4f, val_loss=1.570, va
Evalua el modelo¶
In [16]:
# Evalua el modelo en el conjunto de prueba retenido
trainer.test(model,dm)
Files already downloaded and verified
Files already downloaded and verified
Testing DataLoader 0: 100%|███████████████████| 313/313 [02:24<00:00, 2.16it/s]
────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────
Runningstage.testing metric DataLoader 0
────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────
test_acc 0.439300000667572
test_loss 1.5343555212020874
────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────
Out[16]:
[{'test_loss': 1.5343555212020874, 'test_acc': 0.439300000667572}]
In [ ]: