18.2  Sentiment Analysis: Using Recurrent Neural Networks

Like word similarity and analogy tasks, we can also apply pretrained word vectors to sentiment analysis. Since the IMDb review dataset in Section 18.1 is not very big, using text representations that were pretrained on large-scale corpora may reduce overfitting of the model. As a specific example illustrated in Figure 18.2.1, we will represent each token using the pretrained GloVe model, and feed these token representations into a multilayer bidirectional RNN to obtain the text sequence representation, which will be transformed into sentiment analysis outputs (Maas et al. 2011). For the same downstream application, we will consider a different architectural choice later.

Figure 18.2.1: This section feeds pretrained GloVe to an RNN-based architecture for sentiment analysis. 
from d2l import torch as d2l
import torch
from torch import nn

batch_size = 64
train_iter, test_iter, vocab = d2l.load_data_imdb(batch_size)
from d2l import tensorflow as d2l
import tensorflow as tf
import keras
import numpy as np

batch_size = 64
train_iter, test_iter, vocab = d2l.load_data_imdb(batch_size)
# d2l.load_array uses shuffle(buffer_size=1000), which is too small for
# the IMDb training set (25000 examples ordered as 12500 positives then
# 12500 negatives). Reshuffle the full dataset so each epoch sees a
# properly mixed class distribution, matching the PyTorch/JAX behavior.
train_iter = (train_iter.unbatch()
              .shuffle(25000, reshuffle_each_iteration=True)
              .batch(batch_size))
from d2l import jax as d2l
import jax
from jax import numpy as jnp
from flax import nnx
import optax
import numpy as np

batch_size = 128
train_iter, test_iter, vocab = d2l.load_data_imdb(batch_size)
from d2l import mxnet as d2l
from mxnet import gluon, init, np, npx
from mxnet.gluon import nn, rnn
npx.set_np()

batch_size = 64
train_iter, test_iter, vocab = d2l.load_data_imdb(batch_size)

18.2.1 Representing Single Text with RNNs

In text classification tasks, such as sentiment analysis, a varying-length text sequence will be transformed into fixed-length categories. In the following BiRNN class, while each token of a text sequence gets its individual pretrained GloVe representation via the embedding layer (self.embedding), the entire sequence is encoded by a bidirectional RNN (self.encoder). More concretely, the hidden states (at the last layer) of the bidirectional LSTM at both the initial and final time steps are concatenated as the representation of the text sequence. This single text representation is then transformed into output categories by a fully connected layer (self.decoder) with two outputs (“positive” and “negative”).

class BiRNN(nn.Module):
    def __init__(self, vocab_size, embed_size, num_hiddens,
                 num_layers, **kwargs):
        super(BiRNN, self).__init__(**kwargs)
        self.embedding = nn.Embedding(vocab_size, embed_size)
        # Set `bidirectional` to True to get a bidirectional RNN
        self.encoder = nn.LSTM(embed_size, num_hiddens, num_layers=num_layers,
                                bidirectional=True)
        self.decoder = nn.Linear(4 * num_hiddens, 2)

    def forward(self, inputs):
        # The shape of `inputs` is (batch size, no. of time steps). Because
        # LSTM requires its input's first dimension to be the temporal
        # dimension, the input is transposed before obtaining token
        # representations. The output shape is (no. of time steps, batch size,
        # word vector dimension)
        embeddings = self.embedding(inputs.T)
        self.encoder.flatten_parameters()
        # Returns hidden states of the last hidden layer at different time
        # steps. The shape of `outputs` is (no. of time steps, batch size,
        # 2 * no. of hidden units)
        outputs, _ = self.encoder(embeddings)
        # Concatenate the hidden states at the initial and final time steps as
        # the input of the fully connected layer. Its shape is (batch size,
        # 4 * no. of hidden units)
        encoding = torch.cat((outputs[0], outputs[-1]), dim=1)
        outs = self.decoder(encoding)
        return outs
class BiRNN(d2l.Classifier):
    def __init__(self, vocab_size, embed_size, num_hiddens, num_layers,
                 **kwargs):
        super().__init__(**kwargs)
        self.embedding = keras.layers.Embedding(vocab_size, embed_size)
        # Stack bidirectional LSTM layers; all layers return the full
        # sequence so we can concatenate the initial- and final-step
        # hidden states downstream.
        self.encoder = keras.Sequential([
            keras.layers.Bidirectional(
                keras.layers.LSTM(num_hiddens, return_sequences=True))
            for _ in range(num_layers - 1)
        ] + [
            keras.layers.Bidirectional(
                keras.layers.LSTM(num_hiddens, return_sequences=True))
        ])
        self.decoder = keras.layers.Dense(2)

    def call(self, inputs, training=False):
        # inputs shape: (batch_size, num_steps)
        embeddings = self.embedding(inputs)
        # outputs shape: (batch_size, num_steps, 2 * num_hiddens)
        outputs = self.encoder(embeddings, training=training)
        # Concatenate hidden states at initial and final time steps
        # Shape: (batch_size, 4 * num_hiddens)
        encoding = tf.concat([outputs[:, 0, :], outputs[:, -1, :]], axis=1)
        outs = self.decoder(encoding)
        return outs
class BiRNN(nnx.Module):
    def __init__(self, vocab_size, embed_size, num_hiddens, num_layers,
                 rngs=None):
        rngs = nnx.Rngs(params=0, carry=1) if rngs is None else rngs
        self.embedding = nnx.Embed(vocab_size, embed_size, rngs=rngs)
        self.forward_rnns = nnx.List([])
        self.backward_rnns = nnx.List([])
        for i in range(num_layers):
            num_inputs = embed_size if i == 0 else 2 * num_hiddens
            self.forward_rnns.append(nnx.RNN(
                nnx.LSTMCell(num_inputs, num_hiddens, rngs=rngs), rngs=rngs))
            self.backward_rnns.append(nnx.RNN(
                nnx.LSTMCell(num_inputs, num_hiddens, rngs=rngs),
                reverse=True, keep_order=True, rngs=rngs))
        self.decoder = nnx.Linear(4 * num_hiddens, 2, rngs=rngs)

    def __call__(self, inputs):
        # The shape of `inputs` is (batch size, no. of time steps)
        embeddings = self.embedding(inputs)
        outputs = embeddings
        for forward_rnn, backward_rnn in zip(
                self.forward_rnns, self.backward_rnns):
            outputs = jnp.concatenate(
                [forward_rnn(outputs), backward_rnn(outputs)], axis=-1)
        # Each endpoint contains both directions, so concatenating the first
        # and last time steps produces 4 * num_hiddens features.
        encoding = jnp.concatenate([outputs[:, 0, :], outputs[:, -1, :]],
                                   axis=1)
        outs = self.decoder(encoding)
        return outs
class BiRNN(nn.Block):
    def __init__(self, vocab_size, embed_size, num_hiddens,
                 num_layers):
        super().__init__()
        self.embedding = nn.Embedding(vocab_size, embed_size)
        # Set `bidirectional` to True to get a bidirectional RNN
        self.encoder = rnn.LSTM(num_hiddens, num_layers=num_layers,
                                bidirectional=True, input_size=embed_size)
        self.decoder = nn.Dense(2)

    def forward(self, inputs):
        # The shape of `inputs` is (batch size, no. of time steps). Because
        # LSTM requires its input's first dimension to be the temporal
        # dimension, the input is transposed before obtaining token
        # representations. The output shape is (no. of time steps, batch size,
        # word vector dimension)
        embeddings = self.embedding(inputs.T)
        # Returns hidden states of the last hidden layer at different time
        # steps. The shape of `outputs` is (no. of time steps, batch size,
        # 2 * no. of hidden units)
        outputs = self.encoder(embeddings)
        # Concatenate the hidden states at the initial and final time steps as
        # the input of the fully connected layer. Its shape is (batch size,
        # 4 * no. of hidden units)
        encoding = np.concatenate((outputs[0], outputs[-1]), axis=1)
        outs = self.decoder(encoding)
        return outs

Let’s construct a bidirectional RNN with two hidden layers to represent single text for sentiment analysis.

embed_size, num_hiddens, num_layers, devices = 100, 100, 2, d2l.try_all_gpus()
net = BiRNN(len(vocab), embed_size, num_hiddens, num_layers)
def init_weights(module):
    if type(module) == nn.Linear:
        nn.init.xavier_uniform_(module.weight)
    if type(module) == nn.LSTM:
        for param in module._flat_weights_names:
            if "weight" in param:
                nn.init.xavier_uniform_(module._parameters[param])
net.apply(init_weights);
# Build the model by calling it once on a dummy input
dummy_input = tf.zeros((1, 500), dtype=tf.int32)
net(dummy_input)
<tf.Tensor: shape=(1, 2), dtype=float32, numpy=array([[ 0.02640162, -0.01238832]], dtype=float32)>
# NNX modules create their parameters in the constructor.
d2l.check_shape(net(jnp.ones((1, 500), dtype=jnp.int32)), (1, 2))
# Per-block init: Gluon 2.0's Xavier rejects 1D weights, and the fused LSTM
# has 1D internal weights. Initialize Xavier on the 2D blocks; let the LSTM
# use its default initializer.
net.embedding.initialize(init.Xavier(), ctx=devices)
net.encoder.initialize(ctx=devices)
net.decoder.initialize(init.Xavier(), ctx=devices)

18.2.2 Loading Pretrained Word Vectors

Below we load the pretrained 100-dimensional (needs to be consistent with embed_size) GloVe embeddings for tokens in the vocabulary.

glove_embedding = d2l.TokenEmbedding('glove.6b.100d')

Print the shape of the vectors for all the tokens in the vocabulary.

embeds = glove_embedding[vocab.idx_to_token]
embeds.shape
torch.Size([49346, 100])
TensorShape([49346, 100])
(49346, 100)
(49346, 100)

We use these pretrained word vectors to represent tokens in the reviews and will not update these vectors during training.

net.embedding.weight.data.copy_(embeds)
net.embedding.weight.requires_grad = False
net.embedding.set_weights([np.array(embeds)])
net.embedding.trainable = False
# Store the pretrained table as non-trainable NNX data.
net.embedding.embedding = nnx.data(jnp.array(embeds))
net.embedding.weight.set_data(embeds)
for p in net.embedding.collect_params().values():
    p.grad_req = 'null'

18.2.3 Training and Evaluating the Model

Now we can train the bidirectional RNN for sentiment analysis.

lr, num_epochs = 0.01, 5
trainer = torch.optim.Adam(net.parameters(), lr=lr)
loss = nn.CrossEntropyLoss(reduction="none")
d2l.train_ch13(net, train_iter, test_iter, loss, trainer, num_epochs, devices)
loss 0.287, train acc 0.879, test acc 0.847
3658.0 examples/sec on [device(type='cuda', index=0)]

lr, num_epochs = 0.01, 5
net.compile(optimizer=keras.optimizers.Adam(lr),
            loss=keras.losses.SparseCategoricalCrossentropy(from_logits=True),
            metrics=['accuracy'])
net.fit(train_iter, validation_data=test_iter, epochs=num_epochs)
Epoch 1/5
      1/Unknown 11s 11s/step - accuracy: 0.3906 - loss: 0.6990
      2/Unknown 11s 57ms/step - accuracy: 0.4062 - loss: 1.0841
      3/Unknown 11s 68ms/step - accuracy: 0.4080 - loss: 1.1449
      4/Unknown 11s 76ms/step - accuracy: 0.4066 - loss: 1.1417
      5/Unknown 11s 78ms/step - accuracy: 0.4121 - loss: 1.1224
      6/Unknown 11s 79ms/step - accuracy: 0.4181 - loss: 1.0997
      7/Unknown 11s 80ms/step - accuracy: 0.4221 - loss: 1.0776
      8/Unknown 12s 82ms/step - accuracy: 0.4260 - loss: 1.0572
      9/Unknown 12s 84ms/step - accuracy: 0.4294 - loss: 1.0386
     10/Unknown 12s 83ms/step - accuracy: 0.4312 - loss: 1.0222
     11/Unknown 12s 81ms/step - accuracy: 0.4325 - loss: 1.0074
     12/Unknown 12s 79ms/step - accuracy: 0.4337 - loss: 0.9939
     13/Unknown 12s 77ms/step - accuracy: 0.4348 - loss: 0.9816
     14/Unknown 12s 76ms/step - accuracy: 0.4354 - loss: 0.9705
     15/Unknown 12s 76ms/step - accuracy: 0.4362 - loss: 0.9604
     16/Unknown 12s 75ms/step - accuracy: 0.4367 - loss: 0.9510
     17/Unknown 12s 73ms/step - accuracy: 0.4373 - loss: 0.9424
     18/Unknown 12s 75ms/step - accuracy: 0.4377 - loss: 0.9344
     19/Unknown 12s 75ms/step - accuracy: 0.4380 - loss: 0.9269
     20/Unknown 12s 76ms/step - accuracy: 0.4384 - loss: 0.9200
     21/Unknown 12s 77ms/step - accuracy: 0.4389 - loss: 0.9134
     22/Unknown 13s 78ms/step - accuracy: 0.4395 - loss: 0.9073
     23/Unknown 13s 77ms/step - accuracy: 0.4401 - loss: 0.9016
     24/Unknown 13s 77ms/step - accuracy: 0.4407 - loss: 0.8962
     25/Unknown 13s 76ms/step - accuracy: 0.4413 - loss: 0.8911
     26/Unknown 13s 76ms/step - accuracy: 0.4419 - loss: 0.8863
     27/Unknown 13s 76ms/step - accuracy: 0.4426 - loss: 0.8817
     28/Unknown 13s 75ms/step - accuracy: 0.4434 - loss: 0.8774
     29/Unknown 13s 76ms/step - accuracy: 0.4442 - loss: 0.8733
     30/Unknown 13s 76ms/step - accuracy: 0.4452 - loss: 0.8693
     31/Unknown 13s 77ms/step - accuracy: 0.4462 - loss: 0.8656
     32/Unknown 13s 77ms/step - accuracy: 0.4472 - loss: 0.8620
     33/Unknown 13s 77ms/step - accuracy: 0.4481 - loss: 0.8586
     34/Unknown 13s 77ms/step - accuracy: 0.4491 - loss: 0.8554
     35/Unknown 14s 76ms/step - accuracy: 0.4501 - loss: 0.8522
     36/Unknown 14s 76ms/step - accuracy: 0.4510 - loss: 0.8492
     37/Unknown 14s 76ms/step - accuracy: 0.4518 - loss: 0.8464
     38/Unknown 14s 76ms/step - accuracy: 0.4526 - loss: 0.8437
     39/Unknown 14s 76ms/step - accuracy: 0.4534 - loss: 0.8411
     40/Unknown 14s 76ms/step - accuracy: 0.4541 - loss: 0.8385
     41/Unknown 14s 76ms/step - accuracy: 0.4548 - loss: 0.8361
     42/Unknown 14s 77ms/step - accuracy: 0.4554 - loss: 0.8338
     43/Unknown 14s 77ms/step - accuracy: 0.4561 - loss: 0.8316
     44/Unknown 14s 77ms/step - accuracy: 0.4567 - loss: 0.8294
     45/Unknown 14s 76ms/step - accuracy: 0.4573 - loss: 0.8273
     46/Unknown 14s 76ms/step - accuracy: 0.4580 - loss: 0.8253
     47/Unknown 14s 77ms/step - accuracy: 0.4586 - loss: 0.8233
     48/Unknown 15s 76ms/step - accuracy: 0.4593 - loss: 0.8214
     49/Unknown 15s 77ms/step - accuracy: 0.4600 - loss: 0.8196
     50/Unknown 15s 77ms/step - accuracy: 0.4607 - loss: 0.8178
     51/Unknown 15s 77ms/step - accuracy: 0.4613 - loss: 0.8160
     52/Unknown 15s 77ms/step - accuracy: 0.4620 - loss: 0.8143
     53/Unknown 15s 77ms/step - accuracy: 0.4627 - loss: 0.8127
     54/Unknown 15s 77ms/step - accuracy: 0.4633 - loss: 0.8111
     55/Unknown 15s 76ms/step - accuracy: 0.4639 - loss: 0.8096
     56/Unknown 15s 76ms/step - accuracy: 0.4646 - loss: 0.8081
     57/Unknown 15s 76ms/step - accuracy: 0.4652 - loss: 0.8066
     58/Unknown 15s 76ms/step - accuracy: 0.4658 - loss: 0.8052
     59/Unknown 15s 76ms/step - accuracy: 0.4665 - loss: 0.8038
     60/Unknown 15s 76ms/step - accuracy: 0.4671 - loss: 0.8024
     61/Unknown 15s 76ms/step - accuracy: 0.4677 - loss: 0.8011
     62/Unknown 16s 75ms/step - accuracy: 0.4682 - loss: 0.7998
     63/Unknown 16s 75ms/step - accuracy: 0.4688 - loss: 0.7986
     64/Unknown 16s 75ms/step - accuracy: 0.4694 - loss: 0.7973
     65/Unknown 16s 75ms/step - accuracy: 0.4699 - loss: 0.7961
     66/Unknown 16s 74ms/step - accuracy: 0.4705 - loss: 0.7950
     67/Unknown 16s 74ms/step - accuracy: 0.4710 - loss: 0.7938
     68/Unknown 16s 74ms/step - accuracy: 0.4716 - loss: 0.7927
     69/Unknown 16s 74ms/step - accuracy: 0.4721 - loss: 0.7916
     70/Unknown 16s 74ms/step - accuracy: 0.4727 - loss: 0.7905
     71/Unknown 16s 74ms/step - accuracy: 0.4732 - loss: 0.7894
     72/Unknown 16s 73ms/step - accuracy: 0.4737 - loss: 0.7884
     73/Unknown 16s 73ms/step - accuracy: 0.4742 - loss: 0.7874
     74/Unknown 16s 73ms/step - accuracy: 0.4747 - loss: 0.7865
     75/Unknown 16s 74ms/step - accuracy: 0.4753 - loss: 0.7855
     76/Unknown 16s 74ms/step - accuracy: 0.4758 - loss: 0.7845
     77/Unknown 17s 74ms/step - accuracy: 0.4763 - loss: 0.7836
     78/Unknown 17s 74ms/step - accuracy: 0.4769 - loss: 0.7827
     79/Unknown 17s 74ms/step - accuracy: 0.4774 - loss: 0.7818
     80/Unknown 17s 74ms/step - accuracy: 0.4779 - loss: 0.7810
     81/Unknown 17s 75ms/step - accuracy: 0.4784 - loss: 0.7801
     82/Unknown 17s 75ms/step - accuracy: 0.4789 - loss: 0.7793
     83/Unknown 17s 75ms/step - accuracy: 0.4794 - loss: 0.7784
     84/Unknown 17s 75ms/step - accuracy: 0.4800 - loss: 0.7776
     85/Unknown 17s 75ms/step - accuracy: 0.4805 - loss: 0.7768
     86/Unknown 17s 75ms/step - accuracy: 0.4810 - loss: 0.7760
     87/Unknown 17s 75ms/step - accuracy: 0.4815 - loss: 0.7753
     88/Unknown 17s 74ms/step - accuracy: 0.4820 - loss: 0.7745
     89/Unknown 17s 75ms/step - accuracy: 0.4825 - loss: 0.7738
     90/Unknown 18s 74ms/step - accuracy: 0.4830 - loss: 0.7731
     91/Unknown 18s 74ms/step - accuracy: 0.4834 - loss: 0.7724
     92/Unknown 18s 74ms/step - accuracy: 0.4839 - loss: 0.7717
     93/Unknown 18s 74ms/step - accuracy: 0.4843 - loss: 0.7710
     94/Unknown 18s 74ms/step - accuracy: 0.4848 - loss: 0.7703
     95/Unknown 18s 74ms/step - accuracy: 0.4852 - loss: 0.7697
     96/Unknown 18s 74ms/step - accuracy: 0.4856 - loss: 0.7690
     97/Unknown 18s 75ms/step - accuracy: 0.4861 - loss: 0.7684
     98/Unknown 18s 75ms/step - accuracy: 0.4865 - loss: 0.7678
     99/Unknown 18s 75ms/step - accuracy: 0.4869 - loss: 0.7672
    100/Unknown 18s 75ms/step - accuracy: 0.4874 - loss: 0.7666
    101/Unknown 18s 75ms/step - accuracy: 0.4878 - loss: 0.7660
    102/Unknown 19s 75ms/step - accuracy: 0.4882 - loss: 0.7654
    103/Unknown 19s 75ms/step - accuracy: 0.4886 - loss: 0.7648
    104/Unknown 19s 76ms/step - accuracy: 0.4891 - loss: 0.7642
    105/Unknown 19s 76ms/step - accuracy: 0.4895 - loss: 0.7636
    106/Unknown 19s 76ms/step - accuracy: 0.4899 - loss: 0.7631
    107/Unknown 19s 75ms/step - accuracy: 0.4903 - loss: 0.7625
    108/Unknown 19s 75ms/step - accuracy: 0.4907 - loss: 0.7620
    109/Unknown 19s 76ms/step - accuracy: 0.4911 - loss: 0.7614
    110/Unknown 19s 76ms/step - accuracy: 0.4915 - loss: 0.7609
    111/Unknown 19s 76ms/step - accuracy: 0.4919 - loss: 0.7604
    112/Unknown 19s 76ms/step - accuracy: 0.4924 - loss: 0.7598
    113/Unknown 19s 76ms/step - accuracy: 0.4928 - loss: 0.7593
    114/Unknown 20s 76ms/step - accuracy: 0.4932 - loss: 0.7588
    115/Unknown 20s 76ms/step - accuracy: 0.4937 - loss: 0.7583
    116/Unknown 20s 76ms/step - accuracy: 0.4941 - loss: 0.7577
    117/Unknown 20s 76ms/step - accuracy: 0.4946 - loss: 0.7572
    118/Unknown 20s 76ms/step - accuracy: 0.4950 - loss: 0.7567
    119/Unknown 20s 76ms/step - accuracy: 0.4954 - loss: 0.7562
    120/Unknown 20s 76ms/step - accuracy: 0.4959 - loss: 0.7557
    121/Unknown 20s 76ms/step - accuracy: 0.4963 - loss: 0.7552
    122/Unknown 20s 76ms/step - accuracy: 0.4967 - loss: 0.7548
    123/Unknown 20s 77ms/step - accuracy: 0.4971 - loss: 0.7543
    124/Unknown 20s 77ms/step - accuracy: 0.4975 - loss: 0.7538
    125/Unknown 20s 77ms/step - accuracy: 0.4979 - loss: 0.7534
    126/Unknown 21s 77ms/step - accuracy: 0.4983 - loss: 0.7530
    127/Unknown 21s 77ms/step - accuracy: 0.4986 - loss: 0.7525
    128/Unknown 21s 77ms/step - accuracy: 0.4990 - loss: 0.7521
    129/Unknown 21s 77ms/step - accuracy: 0.4994 - loss: 0.7517
    130/Unknown 21s 77ms/step - accuracy: 0.4998 - loss: 0.7513
    131/Unknown 21s 77ms/step - accuracy: 0.5002 - loss: 0.7509
    132/Unknown 21s 77ms/step - accuracy: 0.5005 - loss: 0.7505
    133/Unknown 21s 77ms/step - accuracy: 0.5009 - loss: 0.7501
    134/Unknown 21s 76ms/step - accuracy: 0.5013 - loss: 0.7497
    135/Unknown 21s 76ms/step - accuracy: 0.5017 - loss: 0.7493
    136/Unknown 21s 76ms/step - accuracy: 0.5021 - loss: 0.7489
    137/Unknown 21s 76ms/step - accuracy: 0.5025 - loss: 0.7485
    138/Unknown 21s 76ms/step - accuracy: 0.5029 - loss: 0.7481
    139/Unknown 21s 76ms/step - accuracy: 0.5033 - loss: 0.7477
    140/Unknown 22s 76ms/step - accuracy: 0.5037 - loss: 0.7473
    141/Unknown 22s 76ms/step - accuracy: 0.5040 - loss: 0.7469
    142/Unknown 22s 76ms/step - accuracy: 0.5044 - loss: 0.7465
    143/Unknown 22s 76ms/step - accuracy: 0.5048 - loss: 0.7461
    144/Unknown 22s 76ms/step - accuracy: 0.5052 - loss: 0.7457
    145/Unknown 22s 76ms/step - accuracy: 0.5056 - loss: 0.7453
    146/Unknown 22s 76ms/step - accuracy: 0.5060 - loss: 0.7449
    147/Unknown 22s 76ms/step - accuracy: 0.5064 - loss: 0.7446
    148/Unknown 22s 76ms/step - accuracy: 0.5068 - loss: 0.7442
    149/Unknown 22s 76ms/step - accuracy: 0.5071 - loss: 0.7438
    150/Unknown 22s 76ms/step - accuracy: 0.5075 - loss: 0.7435
    151/Unknown 22s 76ms/step - accuracy: 0.5079 - loss: 0.7431
    152/Unknown 22s 76ms/step - accuracy: 0.5082 - loss: 0.7427
    153/Unknown 22s 76ms/step - accuracy: 0.5086 - loss: 0.7424
    154/Unknown 23s 76ms/step - accuracy: 0.5089 - loss: 0.7420
    155/Unknown 23s 76ms/step - accuracy: 0.5092 - loss: 0.7417
    156/Unknown 23s 76ms/step - accuracy: 0.5095 - loss: 0.7414
    157/Unknown 23s 76ms/step - accuracy: 0.5099 - loss: 0.7410
    158/Unknown 23s 76ms/step - accuracy: 0.5102 - loss: 0.7407
    159/Unknown 23s 76ms/step - accuracy: 0.5105 - loss: 0.7404
    160/Unknown 23s 76ms/step - accuracy: 0.5108 - loss: 0.7400
    161/Unknown 23s 76ms/step - accuracy: 0.5112 - loss: 0.7397
    162/Unknown 23s 76ms/step - accuracy: 0.5115 - loss: 0.7394
    163/Unknown 23s 76ms/step - accuracy: 0.5118 - loss: 0.7390
    164/Unknown 23s 76ms/step - accuracy: 0.5122 - loss: 0.7387
    165/Unknown 23s 76ms/step - accuracy: 0.5125 - loss: 0.7384
    166/Unknown 23s 76ms/step - accuracy: 0.5129 - loss: 0.7381
    167/Unknown 24s 76ms/step - accuracy: 0.5132 - loss: 0.7377
    168/Unknown 24s 76ms/step - accuracy: 0.5135 - loss: 0.7374
    169/Unknown 24s 76ms/step - accuracy: 0.5139 - loss: 0.7371
    170/Unknown 24s 76ms/step - accuracy: 0.5142 - loss: 0.7367
    171/Unknown 24s 76ms/step - accuracy: 0.5146 - loss: 0.7364
    172/Unknown 24s 76ms/step - accuracy: 0.5149 - loss: 0.7361
    173/Unknown 24s 76ms/step - accuracy: 0.5153 - loss: 0.7357
    174/Unknown 24s 76ms/step - accuracy: 0.5156 - loss: 0.7354
    175/Unknown 24s 76ms/step - accuracy: 0.5160 - loss: 0.7351
    176/Unknown 24s 76ms/step - accuracy: 0.5163 - loss: 0.7347
    177/Unknown 24s 76ms/step - accuracy: 0.5167 - loss: 0.7344
    178/Unknown 24s 76ms/step - accuracy: 0.5171 - loss: 0.7341
    179/Unknown 24s 76ms/step - accuracy: 0.5174 - loss: 0.7337
    180/Unknown 24s 76ms/step - accuracy: 0.5178 - loss: 0.7334
    181/Unknown 25s 76ms/step - accuracy: 0.5181 - loss: 0.7331
    182/Unknown 25s 76ms/step - accuracy: 0.5185 - loss: 0.7327
    183/Unknown 25s 76ms/step - accuracy: 0.5188 - loss: 0.7324
    184/Unknown 25s 76ms/step - accuracy: 0.5192 - loss: 0.7321
    185/Unknown 25s 76ms/step - accuracy: 0.5195 - loss: 0.7318
    186/Unknown 25s 76ms/step - accuracy: 0.5199 - loss: 0.7314
    187/Unknown 25s 76ms/step - accuracy: 0.5202 - loss: 0.7311
    188/Unknown 25s 76ms/step - accuracy: 0.5205 - loss: 0.7308
    189/Unknown 25s 76ms/step - accuracy: 0.5209 - loss: 0.7305
    190/Unknown 25s 76ms/step - accuracy: 0.5212 - loss: 0.7301
    191/Unknown 25s 76ms/step - accuracy: 0.5216 - loss: 0.7298
    192/Unknown 25s 76ms/step - accuracy: 0.5219 - loss: 0.7295
    193/Unknown 25s 76ms/step - accuracy: 0.5223 - loss: 0.7292
    194/Unknown 26s 76ms/step - accuracy: 0.5226 - loss: 0.7289
    195/Unknown 26s 76ms/step - accuracy: 0.5230 - loss: 0.7285
    196/Unknown 26s 76ms/step - accuracy: 0.5233 - loss: 0.7282
    197/Unknown 26s 76ms/step - accuracy: 0.5236 - loss: 0.7279
    198/Unknown 26s 76ms/step - accuracy: 0.5240 - loss: 0.7276
    199/Unknown 26s 76ms/step - accuracy: 0.5243 - loss: 0.7273
    200/Unknown 26s 76ms/step - accuracy: 0.5247 - loss: 0.7269
    201/Unknown 26s 76ms/step - accuracy: 0.5250 - loss: 0.7266
    202/Unknown 26s 75ms/step - accuracy: 0.5254 - loss: 0.7263
    203/Unknown 26s 75ms/step - accuracy: 0.5257 - loss: 0.7260
    204/Unknown 26s 75ms/step - accuracy: 0.5261 - loss: 0.7256
    205/Unknown 26s 75ms/step - accuracy: 0.5264 - loss: 0.7253
    206/Unknown 26s 75ms/step - accuracy: 0.5268 - loss: 0.7250
    207/Unknown 26s 75ms/step - accuracy: 0.5271 - loss: 0.7247
    208/Unknown 27s 75ms/step - accuracy: 0.5275 - loss: 0.7244
    209/Unknown 27s 75ms/step - accuracy: 0.5278 - loss: 0.7240
    210/Unknown 27s 75ms/step - accuracy: 0.5282 - loss: 0.7237
    211/Unknown 27s 76ms/step - accuracy: 0.5285 - loss: 0.7234
    212/Unknown 27s 76ms/step - accuracy: 0.5289 - loss: 0.7231
    213/Unknown 27s 76ms/step - accuracy: 0.5292 - loss: 0.7228
    214/Unknown 27s 76ms/step - accuracy: 0.5296 - loss: 0.7224
    215/Unknown 27s 76ms/step - accuracy: 0.5299 - loss: 0.7221
    216/Unknown 27s 76ms/step - accuracy: 0.5303 - loss: 0.7218
    217/Unknown 27s 76ms/step - accuracy: 0.5306 - loss: 0.7215
    218/Unknown 27s 76ms/step - accuracy: 0.5310 - loss: 0.7211
    219/Unknown 27s 76ms/step - accuracy: 0.5313 - loss: 0.7208
    220/Unknown 28s 76ms/step - accuracy: 0.5317 - loss: 0.7205
    221/Unknown 28s 76ms/step - accuracy: 0.5320 - loss: 0.7202
    222/Unknown 28s 76ms/step - accuracy: 0.5324 - loss: 0.7198
    223/Unknown 28s 76ms/step - accuracy: 0.5328 - loss: 0.7195
    224/Unknown 28s 76ms/step - accuracy: 0.5331 - loss: 0.7192
    225/Unknown 28s 76ms/step - accuracy: 0.5335 - loss: 0.7189
    226/Unknown 28s 76ms/step - accuracy: 0.5338 - loss: 0.7186
    227/Unknown 28s 76ms/step - accuracy: 0.5342 - loss: 0.7182
    228/Unknown 28s 76ms/step - accuracy: 0.5345 - loss: 0.7179
    229/Unknown 28s 76ms/step - accuracy: 0.5348 - loss: 0.7176
    230/Unknown 28s 76ms/step - accuracy: 0.5352 - loss: 0.7173
    231/Unknown 28s 76ms/step - accuracy: 0.5355 - loss: 0.7170
    232/Unknown 28s 76ms/step - accuracy: 0.5359 - loss: 0.7167
    233/Unknown 28s 75ms/step - accuracy: 0.5362 - loss: 0.7164
    234/Unknown 28s 75ms/step - accuracy: 0.5365 - loss: 0.7161
    235/Unknown 29s 75ms/step - accuracy: 0.5369 - loss: 0.7158
    236/Unknown 29s 75ms/step - accuracy: 0.5372 - loss: 0.7155
    237/Unknown 29s 75ms/step - accuracy: 0.5375 - loss: 0.7152
    238/Unknown 29s 75ms/step - accuracy: 0.5379 - loss: 0.7149
    239/Unknown 29s 75ms/step - accuracy: 0.5382 - loss: 0.7146
    240/Unknown 29s 75ms/step - accuracy: 0.5385 - loss: 0.7143
    241/Unknown 29s 75ms/step - accuracy: 0.5389 - loss: 0.7140
    242/Unknown 29s 75ms/step - accuracy: 0.5392 - loss: 0.7137
    243/Unknown 29s 75ms/step - accuracy: 0.5395 - loss: 0.7134
    244/Unknown 29s 75ms/step - accuracy: 0.5399 - loss: 0.7132
    245/Unknown 29s 75ms/step - accuracy: 0.5402 - loss: 0.7129
    246/Unknown 29s 75ms/step - accuracy: 0.5405 - loss: 0.7126
    247/Unknown 29s 75ms/step - accuracy: 0.5409 - loss: 0.7123
    248/Unknown 29s 75ms/step - accuracy: 0.5412 - loss: 0.7120
    249/Unknown 29s 75ms/step - accuracy: 0.5415 - loss: 0.7117
    250/Unknown 30s 75ms/step - accuracy: 0.5418 - loss: 0.7114
    251/Unknown 30s 75ms/step - accuracy: 0.5422 - loss: 0.7111
    252/Unknown 30s 75ms/step - accuracy: 0.5425 - loss: 0.7108
    253/Unknown 30s 75ms/step - accuracy: 0.5428 - loss: 0.7105
    254/Unknown 30s 75ms/step - accuracy: 0.5432 - loss: 0.7102
    255/Unknown 30s 75ms/step - accuracy: 0.5435 - loss: 0.7099
    256/Unknown 30s 75ms/step - accuracy: 0.5438 - loss: 0.7096
    257/Unknown 30s 75ms/step - accuracy: 0.5442 - loss: 0.7093
    258/Unknown 30s 75ms/step - accuracy: 0.5445 - loss: 0.7091
    259/Unknown 30s 75ms/step - accuracy: 0.5448 - loss: 0.7088
    260/Unknown 30s 75ms/step - accuracy: 0.5451 - loss: 0.7085
    261/Unknown 30s 75ms/step - accuracy: 0.5455 - loss: 0.7082
    262/Unknown 31s 75ms/step - accuracy: 0.5458 - loss: 0.7079
    263/Unknown 31s 75ms/step - accuracy: 0.5461 - loss: 0.7076
    264/Unknown 31s 75ms/step - accuracy: 0.5464 - loss: 0.7073
    265/Unknown 31s 75ms/step - accuracy: 0.5468 - loss: 0.7070
    266/Unknown 31s 75ms/step - accuracy: 0.5471 - loss: 0.7067
    267/Unknown 31s 75ms/step - accuracy: 0.5474 - loss: 0.7064
    268/Unknown 31s 75ms/step - accuracy: 0.5477 - loss: 0.7061
    269/Unknown 31s 75ms/step - accuracy: 0.5481 - loss: 0.7058
    270/Unknown 31s 75ms/step - accuracy: 0.5484 - loss: 0.7055
    271/Unknown 31s 75ms/step - accuracy: 0.5487 - loss: 0.7052
    272/Unknown 31s 75ms/step - accuracy: 0.5490 - loss: 0.7049
    273/Unknown 31s 75ms/step - accuracy: 0.5493 - loss: 0.7046
    274/Unknown 31s 75ms/step - accuracy: 0.5497 - loss: 0.7043
    275/Unknown 32s 75ms/step - accuracy: 0.5500 - loss: 0.7041
    276/Unknown 32s 75ms/step - accuracy: 0.5503 - loss: 0.7038
    277/Unknown 32s 75ms/step - accuracy: 0.5506 - loss: 0.7035
    278/Unknown 32s 75ms/step - accuracy: 0.5509 - loss: 0.7032
    279/Unknown 32s 75ms/step - accuracy: 0.5513 - loss: 0.7029
    280/Unknown 32s 75ms/step - accuracy: 0.5516 - loss: 0.7026
    281/Unknown 32s 75ms/step - accuracy: 0.5519 - loss: 0.7023
    282/Unknown 32s 75ms/step - accuracy: 0.5522 - loss: 0.7020
    283/Unknown 32s 75ms/step - accuracy: 0.5525 - loss: 0.7017
    284/Unknown 32s 75ms/step - accuracy: 0.5528 - loss: 0.7014
    285/Unknown 32s 76ms/step - accuracy: 0.5532 - loss: 0.7011
    286/Unknown 32s 76ms/step - accuracy: 0.5535 - loss: 0.7008
    287/Unknown 33s 76ms/step - accuracy: 0.5538 - loss: 0.7005
    288/Unknown 33s 76ms/step - accuracy: 0.5541 - loss: 0.7002
    289/Unknown 33s 76ms/step - accuracy: 0.5544 - loss: 0.6999
    290/Unknown 33s 76ms/step - accuracy: 0.5547 - loss: 0.6996
    291/Unknown 33s 75ms/step - accuracy: 0.5551 - loss: 0.6993
    292/Unknown 33s 75ms/step - accuracy: 0.5554 - loss: 0.6990
    293/Unknown 33s 75ms/step - accuracy: 0.5557 - loss: 0.6987
    294/Unknown 33s 75ms/step - accuracy: 0.5560 - loss: 0.6984
    295/Unknown 33s 75ms/step - accuracy: 0.5563 - loss: 0.6981
    296/Unknown 33s 75ms/step - accuracy: 0.5566 - loss: 0.6979
    297/Unknown 33s 75ms/step - accuracy: 0.5569 - loss: 0.6976
    298/Unknown 33s 75ms/step - accuracy: 0.5573 - loss: 0.6973
    299/Unknown 33s 75ms/step - accuracy: 0.5576 - loss: 0.6970
    300/Unknown 33s 75ms/step - accuracy: 0.5579 - loss: 0.6967
    301/Unknown 34s 75ms/step - accuracy: 0.5582 - loss: 0.6964
    302/Unknown 34s 76ms/step - accuracy: 0.5585 - loss: 0.6961
    303/Unknown 34s 76ms/step - accuracy: 0.5588 - loss: 0.6958
    304/Unknown 34s 76ms/step - accuracy: 0.5591 - loss: 0.6955
    305/Unknown 34s 76ms/step - accuracy: 0.5594 - loss: 0.6953
    306/Unknown 34s 76ms/step - accuracy: 0.5597 - loss: 0.6950
    307/Unknown 34s 76ms/step - accuracy: 0.5600 - loss: 0.6947
    308/Unknown 34s 76ms/step - accuracy: 0.5603 - loss: 0.6944
    309/Unknown 34s 76ms/step - accuracy: 0.5606 - loss: 0.6941
    310/Unknown 34s 76ms/step - accuracy: 0.5609 - loss: 0.6938
    311/Unknown 34s 76ms/step - accuracy: 0.5612 - loss: 0.6935
    312/Unknown 34s 76ms/step - accuracy: 0.5615 - loss: 0.6933
    313/Unknown 35s 76ms/step - accuracy: 0.5618 - loss: 0.6930
    314/Unknown 35s 76ms/step - accuracy: 0.5621 - loss: 0.6927
    315/Unknown 35s 76ms/step - accuracy: 0.5624 - loss: 0.6924
    316/Unknown 35s 76ms/step - accuracy: 0.5627 - loss: 0.6921
    317/Unknown 35s 76ms/step - accuracy: 0.5630 - loss: 0.6918
    318/Unknown 35s 76ms/step - accuracy: 0.5633 - loss: 0.6916
    319/Unknown 35s 76ms/step - accuracy: 0.5636 - loss: 0.6913
    320/Unknown 35s 76ms/step - accuracy: 0.5639 - loss: 0.6910
    321/Unknown 35s 76ms/step - accuracy: 0.5642 - loss: 0.6907
    322/Unknown 35s 76ms/step - accuracy: 0.5645 - loss: 0.6904
    323/Unknown 35s 76ms/step - accuracy: 0.5648 - loss: 0.6902
    324/Unknown 35s 76ms/step - accuracy: 0.5651 - loss: 0.6899
    325/Unknown 36s 76ms/step - accuracy: 0.5654 - loss: 0.6896
    326/Unknown 36s 76ms/step - accuracy: 0.5656 - loss: 0.6893
    327/Unknown 36s 76ms/step - accuracy: 0.5659 - loss: 0.6890
    328/Unknown 36s 76ms/step - accuracy: 0.5662 - loss: 0.6888
    329/Unknown 36s 76ms/step - accuracy: 0.5665 - loss: 0.6885
    330/Unknown 36s 76ms/step - accuracy: 0.5668 - loss: 0.6882
    331/Unknown 36s 76ms/step - accuracy: 0.5671 - loss: 0.6879
    332/Unknown 36s 76ms/step - accuracy: 0.5674 - loss: 0.6876
    333/Unknown 36s 76ms/step - accuracy: 0.5677 - loss: 0.6874
    334/Unknown 36s 76ms/step - accuracy: 0.5680 - loss: 0.6871
    335/Unknown 36s 76ms/step - accuracy: 0.5683 - loss: 0.6868
    336/Unknown 36s 76ms/step - accuracy: 0.5685 - loss: 0.6865
    337/Unknown 36s 76ms/step - accuracy: 0.5688 - loss: 0.6863
    338/Unknown 36s 76ms/step - accuracy: 0.5691 - loss: 0.6860
    339/Unknown 37s 76ms/step - accuracy: 0.5694 - loss: 0.6857
    340/Unknown 37s 76ms/step - accuracy: 0.5697 - loss: 0.6854
    341/Unknown 37s 76ms/step - accuracy: 0.5700 - loss: 0.6852
    342/Unknown 37s 76ms/step - accuracy: 0.5703 - loss: 0.6849
    343/Unknown 37s 76ms/step - accuracy: 0.5706 - loss: 0.6846
    344/Unknown 37s 76ms/step - accuracy: 0.5708 - loss: 0.6843
    345/Unknown 37s 76ms/step - accuracy: 0.5711 - loss: 0.6840
    346/Unknown 37s 76ms/step - accuracy: 0.5714 - loss: 0.6838
    347/Unknown 37s 76ms/step - accuracy: 0.5717 - loss: 0.6835
    348/Unknown 37s 76ms/step - accuracy: 0.5720 - loss: 0.6832
    349/Unknown 37s 76ms/step - accuracy: 0.5723 - loss: 0.6829
    350/Unknown 37s 76ms/step - accuracy: 0.5725 - loss: 0.6827
    351/Unknown 37s 75ms/step - accuracy: 0.5728 - loss: 0.6824
    352/Unknown 37s 75ms/step - accuracy: 0.5731 - loss: 0.6821
    353/Unknown 37s 75ms/step - accuracy: 0.5734 - loss: 0.6818
    354/Unknown 38s 75ms/step - accuracy: 0.5737 - loss: 0.6816
    355/Unknown 38s 75ms/step - accuracy: 0.5740 - loss: 0.6813
    356/Unknown 38s 75ms/step - accuracy: 0.5742 - loss: 0.6810
    357/Unknown 38s 75ms/step - accuracy: 0.5745 - loss: 0.6807
    358/Unknown 38s 75ms/step - accuracy: 0.5748 - loss: 0.6805
    359/Unknown 38s 75ms/step - accuracy: 0.5751 - loss: 0.6802
    360/Unknown 38s 75ms/step - accuracy: 0.5753 - loss: 0.6799
    361/Unknown 38s 75ms/step - accuracy: 0.5756 - loss: 0.6797
    362/Unknown 38s 75ms/step - accuracy: 0.5759 - loss: 0.6794
    363/Unknown 38s 75ms/step - accuracy: 0.5762 - loss: 0.6791
    364/Unknown 38s 75ms/step - accuracy: 0.5765 - loss: 0.6788
    365/Unknown 38s 75ms/step - accuracy: 0.5767 - loss: 0.6786
    366/Unknown 38s 75ms/step - accuracy: 0.5770 - loss: 0.6783
    367/Unknown 38s 75ms/step - accuracy: 0.5773 - loss: 0.6780
    368/Unknown 39s 75ms/step - accuracy: 0.5775 - loss: 0.6778
    369/Unknown 39s 75ms/step - accuracy: 0.5778 - loss: 0.6775
    370/Unknown 39s 75ms/step - accuracy: 0.5781 - loss: 0.6772
    371/Unknown 39s 75ms/step - accuracy: 0.5784 - loss: 0.6770
    372/Unknown 39s 75ms/step - accuracy: 0.5786 - loss: 0.6767
    373/Unknown 39s 75ms/step - accuracy: 0.5789 - loss: 0.6764
    374/Unknown 39s 75ms/step - accuracy: 0.5792 - loss: 0.6762
    375/Unknown 39s 75ms/step - accuracy: 0.5794 - loss: 0.6759
    376/Unknown 39s 75ms/step - accuracy: 0.5797 - loss: 0.6757
    377/Unknown 39s 75ms/step - accuracy: 0.5800 - loss: 0.6754
    378/Unknown 39s 75ms/step - accuracy: 0.5802 - loss: 0.6751
    379/Unknown 39s 75ms/step - accuracy: 0.5805 - loss: 0.6749
    380/Unknown 39s 75ms/step - accuracy: 0.5808 - loss: 0.6746
    381/Unknown 40s 75ms/step - accuracy: 0.5810 - loss: 0.6744
    382/Unknown 40s 75ms/step - accuracy: 0.5813 - loss: 0.6741
    383/Unknown 40s 75ms/step - accuracy: 0.5816 - loss: 0.6738
    384/Unknown 40s 75ms/step - accuracy: 0.5818 - loss: 0.6736
    385/Unknown 40s 75ms/step - accuracy: 0.5821 - loss: 0.6733
    386/Unknown 40s 75ms/step - accuracy: 0.5823 - loss: 0.6731
    387/Unknown 40s 75ms/step - accuracy: 0.5826 - loss: 0.6728
    388/Unknown 40s 75ms/step - accuracy: 0.5829 - loss: 0.6726
    389/Unknown 40s 75ms/step - accuracy: 0.5831 - loss: 0.6723
    390/Unknown 40s 75ms/step - accuracy: 0.5834 - loss: 0.6720
    391/Unknown 44s 84ms/step - accuracy: 0.5836 - loss: 0.6718
/home/smola/d2l-neu/.venv-tensorflow/lib/python3.12/site-packages/keras/src/trainers/epoch_iterator.py:164: UserWarning: Your input ran out of data; interrupting training. Make sure that your dataset or generator can generate at least `steps_per_epoch * epochs` batches. You may need to use the `.repeat()` function when building your dataset.
  self._interrupted_warning()
391/391 ━━━━━━━━━━━━━━━━━━━━ 60s 127ms/step - accuracy: 0.6833 - loss: 0.5734 - val_accuracy: 0.7886 - val_loss: 0.4524
Epoch 2/5
  1/391 ━━━━━━━━━━━━━━━━━━━━ 1:53 290ms/step - accuracy: 0.7500 - loss: 0.5402
  2/391 ━━━━━━━━━━━━━━━━━━━━ 28s 72ms/step - accuracy: 0.7773 - loss: 0.4927  
  3/391 ━━━━━━━━━━━━━━━━━━━━ 24s 64ms/step - accuracy: 0.7908 - loss: 0.4762
  4/391 ━━━━━━━━━━━━━━━━━━━━ 24s 64ms/step - accuracy: 0.7972 - loss: 0.4654
  5/391 ━━━━━━━━━━━━━━━━━━━━ 24s 62ms/step - accuracy: 0.8003 - loss: 0.4583
  6/391 ━━━━━━━━━━━━━━━━━━━━ 23s 61ms/step - accuracy: 0.8036 - loss: 0.4517
  7/391 ━━━━━━━━━━━━━━━━━━━━ 24s 64ms/step - accuracy: 0.8055 - loss: 0.4468
  8/391 ━━━━━━━━━━━━━━━━━━━━ 24s 64ms/step - accuracy: 0.8069 - loss: 0.4426
  9/391 ━━━━━━━━━━━━━━━━━━━━ 23s 63ms/step - accuracy: 0.8079 - loss: 0.4390
 10/391 ━━━━━━━━━━━━━━━━━━━━ 24s 63ms/step - accuracy: 0.8087 - loss: 0.4356
 11/391 ━━━━━━━━━━━━━━━━━━━━ 23s 63ms/step - accuracy: 0.8103 - loss: 0.4319
 12/391 ━━━━━━━━━━━━━━━━━━━━ 23s 62ms/step - accuracy: 0.8114 - loss: 0.4295
 13/391 ━━━━━━━━━━━━━━━━━━━━ 23s 62ms/step - accuracy: 0.8120 - loss: 0.4277
 14/391 ━━━━━━━━━━━━━━━━━━━━ 23s 62ms/step - accuracy: 0.8128 - loss: 0.4257
 15/391 ━━━━━━━━━━━━━━━━━━━━ 23s 62ms/step - accuracy: 0.8135 - loss: 0.4241
 16/391 ━━━━━━━━━━━━━━━━━━━━ 23s 62ms/step - accuracy: 0.8142 - loss: 0.4224
 17/391 ━━━━━━━━━━━━━━━━━━━━ 22s 61ms/step - accuracy: 0.8141 - loss: 0.4220
 18/391 ━━━━━━━━━━━━━━━━━━━━ 22s 61ms/step - accuracy: 0.8143 - loss: 0.4212
 19/391 ━━━━━━━━━━━━━━━━━━━━ 22s 61ms/step - accuracy: 0.8143 - loss: 0.4208
 20/391 ━━━━━━━━━━━━━━━━━━━━ 22s 61ms/step - accuracy: 0.8141 - loss: 0.4207
 21/391 ━━━━━━━━━━━━━━━━━━━━ 22s 60ms/step - accuracy: 0.8140 - loss: 0.4207
 22/391 ━━━━━━━━━━━━━━━━━━━━ 22s 60ms/step - accuracy: 0.8140 - loss: 0.4206
 23/391 ━━━━━━━━━━━━━━━━━━━━ 22s 60ms/step - accuracy: 0.8140 - loss: 0.4206
 24/391 ━━━━━━━━━━━━━━━━━━━━ 22s 60ms/step - accuracy: 0.8140 - loss: 0.4207
 25/391 ━━━━━━━━━━━━━━━━━━━━ 22s 60ms/step - accuracy: 0.8139 - loss: 0.4207
 26/391 ━━━━━━━━━━━━━━━━━━━━ 21s 60ms/step - accuracy: 0.8139 - loss: 0.4208
 27/391 ━━━━━━━━━━━━━━━━━━━━ 21s 60ms/step - accuracy: 0.8138 - loss: 0.4208
 28/391 ━━━━━━━━━━━━━━━━━━━━ 21s 60ms/step - accuracy: 0.8138 - loss: 0.4207
 29/391 ━━━━━━━━━━━━━━━━━━━━ 22s 61ms/step - accuracy: 0.8138 - loss: 0.4207
 30/391 ━━━━━━━━━━━━━━━━━━━━ 22s 62ms/step - accuracy: 0.8139 - loss: 0.4206
 31/391 ━━━━━━━━━━━━━━━━━━━━ 22s 62ms/step - accuracy: 0.8140 - loss: 0.4205
 32/391 ━━━━━━━━━━━━━━━━━━━━ 22s 62ms/step - accuracy: 0.8141 - loss: 0.4204
 33/391 ━━━━━━━━━━━━━━━━━━━━ 22s 63ms/step - accuracy: 0.8143 - loss: 0.4201
 34/391 ━━━━━━━━━━━━━━━━━━━━ 22s 64ms/step - accuracy: 0.8144 - loss: 0.4200
 35/391 ━━━━━━━━━━━━━━━━━━━━ 22s 64ms/step - accuracy: 0.8145 - loss: 0.4200
 36/391 ━━━━━━━━━━━━━━━━━━━━ 22s 64ms/step - accuracy: 0.8145 - loss: 0.4200
 37/391 ━━━━━━━━━━━━━━━━━━━━ 22s 64ms/step - accuracy: 0.8146 - loss: 0.4199
 38/391 ━━━━━━━━━━━━━━━━━━━━ 22s 64ms/step - accuracy: 0.8146 - loss: 0.4199
 39/391 ━━━━━━━━━━━━━━━━━━━━ 22s 63ms/step - accuracy: 0.8147 - loss: 0.4199
 40/391 ━━━━━━━━━━━━━━━━━━━━ 22s 63ms/step - accuracy: 0.8147 - loss: 0.4199
 41/391 ━━━━━━━━━━━━━━━━━━━━ 22s 63ms/step - accuracy: 0.8147 - loss: 0.4199
 42/391 ━━━━━━━━━━━━━━━━━━━━ 22s 63ms/step - accuracy: 0.8148 - loss: 0.4199
 43/391 ━━━━━━━━━━━━━━━━━━━━ 21s 63ms/step - accuracy: 0.8149 - loss: 0.4198
 44/391 ━━━━━━━━━━━━━━━━━━━━ 21s 63ms/step - accuracy: 0.8149 - loss: 0.4197
 45/391 ━━━━━━━━━━━━━━━━━━━━ 21s 63ms/step - accuracy: 0.8150 - loss: 0.4197
 46/391 ━━━━━━━━━━━━━━━━━━━━ 21s 63ms/step - accuracy: 0.8150 - loss: 0.4196
 47/391 ━━━━━━━━━━━━━━━━━━━━ 21s 63ms/step - accuracy: 0.8151 - loss: 0.4195
 48/391 ━━━━━━━━━━━━━━━━━━━━ 21s 63ms/step - accuracy: 0.8151 - loss: 0.4194
 49/391 ━━━━━━━━━━━━━━━━━━━━ 21s 63ms/step - accuracy: 0.8152 - loss: 0.4193
 50/391 ━━━━━━━━━━━━━━━━━━━━ 21s 63ms/step - accuracy: 0.8152 - loss: 0.4192
 51/391 ━━━━━━━━━━━━━━━━━━━━ 21s 63ms/step - accuracy: 0.8152 - loss: 0.4191
 52/391 ━━━━━━━━━━━━━━━━━━━━ 21s 63ms/step - accuracy: 0.8153 - loss: 0.4189
 53/391 ━━━━━━━━━━━━━━━━━━━━ 21s 63ms/step - accuracy: 0.8154 - loss: 0.4188
 54/391 ━━━━━━━━━━━━━━━━━━━━ 21s 63ms/step - accuracy: 0.8154 - loss: 0.4187
 55/391 ━━━━━━━━━━━━━━━━━━━━ 21s 63ms/step - accuracy: 0.8154 - loss: 0.4185
 56/391 ━━━━━━━━━━━━━━━━━━━━ 21s 63ms/step - accuracy: 0.8155 - loss: 0.4184
 57/391 ━━━━━━━━━━━━━━━━━━━━ 21s 63ms/step - accuracy: 0.8155 - loss: 0.4183
 58/391 ━━━━━━━━━━━━━━━━━━━━ 20s 63ms/step - accuracy: 0.8155 - loss: 0.4182
 59/391 ━━━━━━━━━━━━━━━━━━━━ 20s 63ms/step - accuracy: 0.8155 - loss: 0.4181
 60/391 ━━━━━━━━━━━━━━━━━━━━ 20s 63ms/step - accuracy: 0.8155 - loss: 0.4180
 61/391 ━━━━━━━━━━━━━━━━━━━━ 20s 63ms/step - accuracy: 0.8155 - loss: 0.4179
 62/391 ━━━━━━━━━━━━━━━━━━━━ 20s 64ms/step - accuracy: 0.8155 - loss: 0.4179
 63/391 ━━━━━━━━━━━━━━━━━━━━ 21s 64ms/step - accuracy: 0.8155 - loss: 0.4178
 64/391 ━━━━━━━━━━━━━━━━━━━━ 21s 64ms/step - accuracy: 0.8155 - loss: 0.4177
 65/391 ━━━━━━━━━━━━━━━━━━━━ 21s 65ms/step - accuracy: 0.8155 - loss: 0.4177
 66/391 ━━━━━━━━━━━━━━━━━━━━ 21s 65ms/step - accuracy: 0.8155 - loss: 0.4176
 67/391 ━━━━━━━━━━━━━━━━━━━━ 21s 65ms/step - accuracy: 0.8155 - loss: 0.4175
 68/391 ━━━━━━━━━━━━━━━━━━━━ 21s 66ms/step - accuracy: 0.8156 - loss: 0.4174
 69/391 ━━━━━━━━━━━━━━━━━━━━ 21s 66ms/step - accuracy: 0.8156 - loss: 0.4174
 70/391 ━━━━━━━━━━━━━━━━━━━━ 21s 66ms/step - accuracy: 0.8156 - loss: 0.4173
 71/391 ━━━━━━━━━━━━━━━━━━━━ 21s 66ms/step - accuracy: 0.8156 - loss: 0.4172
 72/391 ━━━━━━━━━━━━━━━━━━━━ 21s 66ms/step - accuracy: 0.8157 - loss: 0.4170
 73/391 ━━━━━━━━━━━━━━━━━━━━ 21s 67ms/step - accuracy: 0.8158 - loss: 0.4169
 74/391 ━━━━━━━━━━━━━━━━━━━━ 21s 67ms/step - accuracy: 0.8158 - loss: 0.4168
 75/391 ━━━━━━━━━━━━━━━━━━━━ 21s 67ms/step - accuracy: 0.8159 - loss: 0.4167
 76/391 ━━━━━━━━━━━━━━━━━━━━ 21s 67ms/step - accuracy: 0.8159 - loss: 0.4166
 77/391 ━━━━━━━━━━━━━━━━━━━━ 20s 67ms/step - accuracy: 0.8160 - loss: 0.4164
 78/391 ━━━━━━━━━━━━━━━━━━━━ 20s 67ms/step - accuracy: 0.8160 - loss: 0.4163
 79/391 ━━━━━━━━━━━━━━━━━━━━ 20s 67ms/step - accuracy: 0.8160 - loss: 0.4162
 80/391 ━━━━━━━━━━━━━━━━━━━━ 20s 67ms/step - accuracy: 0.8160 - loss: 0.4161
 81/391 ━━━━━━━━━━━━━━━━━━━━ 21s 68ms/step - accuracy: 0.8161 - loss: 0.4160
 82/391 ━━━━━━━━━━━━━━━━━━━━ 21s 68ms/step - accuracy: 0.8161 - loss: 0.4159
 83/391 ━━━━━━━━━━━━━━━━━━━━ 21s 68ms/step - accuracy: 0.8161 - loss: 0.4159
 84/391 ━━━━━━━━━━━━━━━━━━━━ 21s 69ms/step - accuracy: 0.8161 - loss: 0.4158
 85/391 ━━━━━━━━━━━━━━━━━━━━ 20s 69ms/step - accuracy: 0.8161 - loss: 0.4157
 86/391 ━━━━━━━━━━━━━━━━━━━━ 20s 68ms/step - accuracy: 0.8161 - loss: 0.4157
 87/391 ━━━━━━━━━━━━━━━━━━━━ 20s 68ms/step - accuracy: 0.8161 - loss: 0.4157
 88/391 ━━━━━━━━━━━━━━━━━━━━ 20s 68ms/step - accuracy: 0.8160 - loss: 0.4156
 89/391 ━━━━━━━━━━━━━━━━━━━━ 20s 68ms/step - accuracy: 0.8160 - loss: 0.4156
 90/391 ━━━━━━━━━━━━━━━━━━━━ 20s 68ms/step - accuracy: 0.8160 - loss: 0.4156
 91/391 ━━━━━━━━━━━━━━━━━━━━ 20s 68ms/step - accuracy: 0.8160 - loss: 0.4155
 92/391 ━━━━━━━━━━━━━━━━━━━━ 20s 68ms/step - accuracy: 0.8159 - loss: 0.4155
 93/391 ━━━━━━━━━━━━━━━━━━━━ 20s 68ms/step - accuracy: 0.8159 - loss: 0.4154
 94/391 ━━━━━━━━━━━━━━━━━━━━ 20s 68ms/step - accuracy: 0.8159 - loss: 0.4154
 95/391 ━━━━━━━━━━━━━━━━━━━━ 20s 68ms/step - accuracy: 0.8159 - loss: 0.4153
 96/391 ━━━━━━━━━━━━━━━━━━━━ 20s 68ms/step - accuracy: 0.8159 - loss: 0.4152
 97/391 ━━━━━━━━━━━━━━━━━━━━ 20s 68ms/step - accuracy: 0.8159 - loss: 0.4151
 98/391 ━━━━━━━━━━━━━━━━━━━━ 19s 68ms/step - accuracy: 0.8159 - loss: 0.4151
 99/391 ━━━━━━━━━━━━━━━━━━━━ 19s 68ms/step - accuracy: 0.8159 - loss: 0.4150
100/391 ━━━━━━━━━━━━━━━━━━━━ 19s 68ms/step - accuracy: 0.8159 - loss: 0.4150
101/391 ━━━━━━━━━━━━━━━━━━━━ 19s 68ms/step - accuracy: 0.8159 - loss: 0.4149
102/391 ━━━━━━━━━━━━━━━━━━━━ 19s 68ms/step - accuracy: 0.8159 - loss: 0.4149
103/391 ━━━━━━━━━━━━━━━━━━━━ 19s 69ms/step - accuracy: 0.8159 - loss: 0.4148
104/391 ━━━━━━━━━━━━━━━━━━━━ 19s 69ms/step - accuracy: 0.8159 - loss: 0.4148
105/391 ━━━━━━━━━━━━━━━━━━━━ 19s 68ms/step - accuracy: 0.8159 - loss: 0.4147
106/391 ━━━━━━━━━━━━━━━━━━━━ 19s 68ms/step - accuracy: 0.8159 - loss: 0.4147
107/391 ━━━━━━━━━━━━━━━━━━━━ 19s 68ms/step - accuracy: 0.8159 - loss: 0.4146
108/391 ━━━━━━━━━━━━━━━━━━━━ 19s 68ms/step - accuracy: 0.8159 - loss: 0.4146
109/391 ━━━━━━━━━━━━━━━━━━━━ 19s 68ms/step - accuracy: 0.8159 - loss: 0.4145
110/391 ━━━━━━━━━━━━━━━━━━━━ 19s 68ms/step - accuracy: 0.8160 - loss: 0.4145
111/391 ━━━━━━━━━━━━━━━━━━━━ 19s 68ms/step - accuracy: 0.8160 - loss: 0.4144
112/391 ━━━━━━━━━━━━━━━━━━━━ 19s 69ms/step - accuracy: 0.8160 - loss: 0.4144
113/391 ━━━━━━━━━━━━━━━━━━━━ 19s 69ms/step - accuracy: 0.8160 - loss: 0.4143
114/391 ━━━━━━━━━━━━━━━━━━━━ 18s 69ms/step - accuracy: 0.8160 - loss: 0.4143
115/391 ━━━━━━━━━━━━━━━━━━━━ 18s 68ms/step - accuracy: 0.8160 - loss: 0.4143
116/391 ━━━━━━━━━━━━━━━━━━━━ 18s 69ms/step - accuracy: 0.8160 - loss: 0.4142
117/391 ━━━━━━━━━━━━━━━━━━━━ 18s 69ms/step - accuracy: 0.8160 - loss: 0.4142
118/391 ━━━━━━━━━━━━━━━━━━━━ 18s 69ms/step - accuracy: 0.8160 - loss: 0.4141
119/391 ━━━━━━━━━━━━━━━━━━━━ 18s 69ms/step - accuracy: 0.8160 - loss: 0.4141
120/391 ━━━━━━━━━━━━━━━━━━━━ 18s 69ms/step - accuracy: 0.8160 - loss: 0.4140
121/391 ━━━━━━━━━━━━━━━━━━━━ 18s 70ms/step - accuracy: 0.8160 - loss: 0.4140
122/391 ━━━━━━━━━━━━━━━━━━━━ 18s 70ms/step - accuracy: 0.8160 - loss: 0.4139
123/391 ━━━━━━━━━━━━━━━━━━━━ 18s 70ms/step - accuracy: 0.8160 - loss: 0.4139
124/391 ━━━━━━━━━━━━━━━━━━━━ 18s 70ms/step - accuracy: 0.8160 - loss: 0.4138
125/391 ━━━━━━━━━━━━━━━━━━━━ 18s 70ms/step - accuracy: 0.8160 - loss: 0.4138
126/391 ━━━━━━━━━━━━━━━━━━━━ 18s 70ms/step - accuracy: 0.8160 - loss: 0.4137
127/391 ━━━━━━━━━━━━━━━━━━━━ 18s 71ms/step - accuracy: 0.8160 - loss: 0.4137
128/391 ━━━━━━━━━━━━━━━━━━━━ 18s 71ms/step - accuracy: 0.8161 - loss: 0.4136
129/391 ━━━━━━━━━━━━━━━━━━━━ 18s 71ms/step - accuracy: 0.8161 - loss: 0.4136
130/391 ━━━━━━━━━━━━━━━━━━━━ 18s 71ms/step - accuracy: 0.8161 - loss: 0.4135
131/391 ━━━━━━━━━━━━━━━━━━━━ 18s 71ms/step - accuracy: 0.8161 - loss: 0.4135
132/391 ━━━━━━━━━━━━━━━━━━━━ 18s 71ms/step - accuracy: 0.8161 - loss: 0.4134
133/391 ━━━━━━━━━━━━━━━━━━━━ 18s 71ms/step - accuracy: 0.8161 - loss: 0.4134
134/391 ━━━━━━━━━━━━━━━━━━━━ 18s 71ms/step - accuracy: 0.8161 - loss: 0.4133
135/391 ━━━━━━━━━━━━━━━━━━━━ 18s 71ms/step - accuracy: 0.8161 - loss: 0.4133
136/391 ━━━━━━━━━━━━━━━━━━━━ 17s 70ms/step - accuracy: 0.8161 - loss: 0.4132
137/391 ━━━━━━━━━━━━━━━━━━━━ 17s 70ms/step - accuracy: 0.8161 - loss: 0.4131
138/391 ━━━━━━━━━━━━━━━━━━━━ 17s 70ms/step - accuracy: 0.8162 - loss: 0.4131
139/391 ━━━━━━━━━━━━━━━━━━━━ 17s 70ms/step - accuracy: 0.8162 - loss: 0.4130
140/391 ━━━━━━━━━━━━━━━━━━━━ 17s 70ms/step - accuracy: 0.8162 - loss: 0.4130
141/391 ━━━━━━━━━━━━━━━━━━━━ 17s 70ms/step - accuracy: 0.8162 - loss: 0.4129
142/391 ━━━━━━━━━━━━━━━━━━━━ 17s 70ms/step - accuracy: 0.8162 - loss: 0.4129
143/391 ━━━━━━━━━━━━━━━━━━━━ 17s 70ms/step - accuracy: 0.8162 - loss: 0.4128
144/391 ━━━━━━━━━━━━━━━━━━━━ 17s 70ms/step - accuracy: 0.8162 - loss: 0.4128
145/391 ━━━━━━━━━━━━━━━━━━━━ 17s 70ms/step - accuracy: 0.8162 - loss: 0.4127
146/391 ━━━━━━━━━━━━━━━━━━━━ 17s 70ms/step - accuracy: 0.8162 - loss: 0.4126
147/391 ━━━━━━━━━━━━━━━━━━━━ 17s 70ms/step - accuracy: 0.8163 - loss: 0.4126
148/391 ━━━━━━━━━━━━━━━━━━━━ 16s 70ms/step - accuracy: 0.8163 - loss: 0.4125
149/391 ━━━━━━━━━━━━━━━━━━━━ 16s 70ms/step - accuracy: 0.8163 - loss: 0.4125
150/391 ━━━━━━━━━━━━━━━━━━━━ 16s 70ms/step - accuracy: 0.8163 - loss: 0.4124
151/391 ━━━━━━━━━━━━━━━━━━━━ 16s 70ms/step - accuracy: 0.8163 - loss: 0.4124
152/391 ━━━━━━━━━━━━━━━━━━━━ 16s 70ms/step - accuracy: 0.8163 - loss: 0.4123
153/391 ━━━━━━━━━━━━━━━━━━━━ 16s 70ms/step - accuracy: 0.8164 - loss: 0.4122
154/391 ━━━━━━━━━━━━━━━━━━━━ 16s 69ms/step - accuracy: 0.8164 - loss: 0.4122
155/391 ━━━━━━━━━━━━━━━━━━━━ 16s 69ms/step - accuracy: 0.8164 - loss: 0.4121
156/391 ━━━━━━━━━━━━━━━━━━━━ 16s 69ms/step - accuracy: 0.8164 - loss: 0.4121
157/391 ━━━━━━━━━━━━━━━━━━━━ 16s 69ms/step - accuracy: 0.8164 - loss: 0.4120
158/391 ━━━━━━━━━━━━━━━━━━━━ 16s 69ms/step - accuracy: 0.8164 - loss: 0.4120
159/391 ━━━━━━━━━━━━━━━━━━━━ 16s 69ms/step - accuracy: 0.8165 - loss: 0.4119
160/391 ━━━━━━━━━━━━━━━━━━━━ 16s 69ms/step - accuracy: 0.8165 - loss: 0.4119
161/391 ━━━━━━━━━━━━━━━━━━━━ 15s 69ms/step - accuracy: 0.8165 - loss: 0.4118
162/391 ━━━━━━━━━━━━━━━━━━━━ 15s 70ms/step - accuracy: 0.8165 - loss: 0.4118
163/391 ━━━━━━━━━━━━━━━━━━━━ 15s 69ms/step - accuracy: 0.8165 - loss: 0.4117
164/391 ━━━━━━━━━━━━━━━━━━━━ 15s 70ms/step - accuracy: 0.8165 - loss: 0.4117
165/391 ━━━━━━━━━━━━━━━━━━━━ 15s 70ms/step - accuracy: 0.8166 - loss: 0.4116
166/391 ━━━━━━━━━━━━━━━━━━━━ 15s 70ms/step - accuracy: 0.8166 - loss: 0.4116
167/391 ━━━━━━━━━━━━━━━━━━━━ 15s 70ms/step - accuracy: 0.8166 - loss: 0.4115
168/391 ━━━━━━━━━━━━━━━━━━━━ 15s 70ms/step - accuracy: 0.8166 - loss: 0.4115
169/391 ━━━━━━━━━━━━━━━━━━━━ 15s 70ms/step - accuracy: 0.8167 - loss: 0.4114
170/391 ━━━━━━━━━━━━━━━━━━━━ 15s 70ms/step - accuracy: 0.8167 - loss: 0.4113
171/391 ━━━━━━━━━━━━━━━━━━━━ 15s 70ms/step - accuracy: 0.8167 - loss: 0.4113
172/391 ━━━━━━━━━━━━━━━━━━━━ 15s 70ms/step - accuracy: 0.8167 - loss: 0.4112
173/391 ━━━━━━━━━━━━━━━━━━━━ 15s 70ms/step - accuracy: 0.8167 - loss: 0.4112
174/391 ━━━━━━━━━━━━━━━━━━━━ 15s 71ms/step - accuracy: 0.8168 - loss: 0.4111
175/391 ━━━━━━━━━━━━━━━━━━━━ 15s 71ms/step - accuracy: 0.8168 - loss: 0.4111
176/391 ━━━━━━━━━━━━━━━━━━━━ 15s 71ms/step - accuracy: 0.8168 - loss: 0.4110
177/391 ━━━━━━━━━━━━━━━━━━━━ 15s 70ms/step - accuracy: 0.8168 - loss: 0.4110
178/391 ━━━━━━━━━━━━━━━━━━━━ 14s 70ms/step - accuracy: 0.8168 - loss: 0.4109
179/391 ━━━━━━━━━━━━━━━━━━━━ 14s 70ms/step - accuracy: 0.8168 - loss: 0.4109
180/391 ━━━━━━━━━━━━━━━━━━━━ 14s 70ms/step - accuracy: 0.8169 - loss: 0.4108
181/391 ━━━━━━━━━━━━━━━━━━━━ 14s 70ms/step - accuracy: 0.8169 - loss: 0.4108
182/391 ━━━━━━━━━━━━━━━━━━━━ 14s 70ms/step - accuracy: 0.8169 - loss: 0.4108
183/391 ━━━━━━━━━━━━━━━━━━━━ 14s 70ms/step - accuracy: 0.8169 - loss: 0.4107
184/391 ━━━━━━━━━━━━━━━━━━━━ 14s 70ms/step - accuracy: 0.8169 - loss: 0.4107
185/391 ━━━━━━━━━━━━━━━━━━━━ 14s 70ms/step - accuracy: 0.8169 - loss: 0.4106
186/391 ━━━━━━━━━━━━━━━━━━━━ 14s 70ms/step - accuracy: 0.8169 - loss: 0.4106
187/391 ━━━━━━━━━━━━━━━━━━━━ 14s 70ms/step - accuracy: 0.8169 - loss: 0.4106
188/391 ━━━━━━━━━━━━━━━━━━━━ 14s 70ms/step - accuracy: 0.8169 - loss: 0.4105
189/391 ━━━━━━━━━━━━━━━━━━━━ 14s 71ms/step - accuracy: 0.8169 - loss: 0.4105
190/391 ━━━━━━━━━━━━━━━━━━━━ 14s 71ms/step - accuracy: 0.8170 - loss: 0.4104
191/391 ━━━━━━━━━━━━━━━━━━━━ 14s 71ms/step - accuracy: 0.8170 - loss: 0.4104
192/391 ━━━━━━━━━━━━━━━━━━━━ 14s 71ms/step - accuracy: 0.8170 - loss: 0.4104
193/391 ━━━━━━━━━━━━━━━━━━━━ 14s 71ms/step - accuracy: 0.8170 - loss: 0.4103
194/391 ━━━━━━━━━━━━━━━━━━━━ 13s 71ms/step - accuracy: 0.8170 - loss: 0.4103
195/391 ━━━━━━━━━━━━━━━━━━━━ 13s 71ms/step - accuracy: 0.8170 - loss: 0.4103
196/391 ━━━━━━━━━━━━━━━━━━━━ 13s 71ms/step - accuracy: 0.8170 - loss: 0.4103
197/391 ━━━━━━━━━━━━━━━━━━━━ 13s 71ms/step - accuracy: 0.8170 - loss: 0.4102
198/391 ━━━━━━━━━━━━━━━━━━━━ 13s 71ms/step - accuracy: 0.8170 - loss: 0.4102
199/391 ━━━━━━━━━━━━━━━━━━━━ 13s 71ms/step - accuracy: 0.8170 - loss: 0.4102
200/391 ━━━━━━━━━━━━━━━━━━━━ 13s 71ms/step - accuracy: 0.8170 - loss: 0.4101
201/391 ━━━━━━━━━━━━━━━━━━━━ 13s 71ms/step - accuracy: 0.8170 - loss: 0.4101
202/391 ━━━━━━━━━━━━━━━━━━━━ 13s 71ms/step - accuracy: 0.8170 - loss: 0.4101
203/391 ━━━━━━━━━━━━━━━━━━━━ 13s 72ms/step - accuracy: 0.8170 - loss: 0.4101
204/391 ━━━━━━━━━━━━━━━━━━━━ 13s 72ms/step - accuracy: 0.8170 - loss: 0.4100
205/391 ━━━━━━━━━━━━━━━━━━━━ 13s 72ms/step - accuracy: 0.8170 - loss: 0.4100
206/391 ━━━━━━━━━━━━━━━━━━━━ 13s 72ms/step - accuracy: 0.8170 - loss: 0.4100
207/391 ━━━━━━━━━━━━━━━━━━━━ 13s 72ms/step - accuracy: 0.8170 - loss: 0.4100
208/391 ━━━━━━━━━━━━━━━━━━━━ 13s 72ms/step - accuracy: 0.8170 - loss: 0.4099
209/391 ━━━━━━━━━━━━━━━━━━━━ 13s 72ms/step - accuracy: 0.8170 - loss: 0.4099
210/391 ━━━━━━━━━━━━━━━━━━━━ 12s 72ms/step - accuracy: 0.8170 - loss: 0.4099
211/391 ━━━━━━━━━━━━━━━━━━━━ 12s 72ms/step - accuracy: 0.8170 - loss: 0.4099
212/391 ━━━━━━━━━━━━━━━━━━━━ 12s 72ms/step - accuracy: 0.8170 - loss: 0.4099
213/391 ━━━━━━━━━━━━━━━━━━━━ 12s 71ms/step - accuracy: 0.8170 - loss: 0.4099
214/391 ━━━━━━━━━━━━━━━━━━━━ 12s 71ms/step - accuracy: 0.8170 - loss: 0.4098
215/391 ━━━━━━━━━━━━━━━━━━━━ 12s 72ms/step - accuracy: 0.8170 - loss: 0.4098
216/391 ━━━━━━━━━━━━━━━━━━━━ 12s 72ms/step - accuracy: 0.8170 - loss: 0.4098
217/391 ━━━━━━━━━━━━━━━━━━━━ 12s 71ms/step - accuracy: 0.8170 - loss: 0.4098
218/391 ━━━━━━━━━━━━━━━━━━━━ 12s 71ms/step - accuracy: 0.8171 - loss: 0.4097
219/391 ━━━━━━━━━━━━━━━━━━━━ 12s 71ms/step - accuracy: 0.8171 - loss: 0.4097
220/391 ━━━━━━━━━━━━━━━━━━━━ 12s 71ms/step - accuracy: 0.8171 - loss: 0.4097
221/391 ━━━━━━━━━━━━━━━━━━━━ 12s 72ms/step - accuracy: 0.8171 - loss: 0.4097
222/391 ━━━━━━━━━━━━━━━━━━━━ 12s 72ms/step - accuracy: 0.8171 - loss: 0.4096
223/391 ━━━━━━━━━━━━━━━━━━━━ 12s 72ms/step - accuracy: 0.8171 - loss: 0.4096
224/391 ━━━━━━━━━━━━━━━━━━━━ 11s 72ms/step - accuracy: 0.8171 - loss: 0.4096
225/391 ━━━━━━━━━━━━━━━━━━━━ 11s 72ms/step - accuracy: 0.8171 - loss: 0.4095
226/391 ━━━━━━━━━━━━━━━━━━━━ 11s 72ms/step - accuracy: 0.8171 - loss: 0.4095
227/391 ━━━━━━━━━━━━━━━━━━━━ 11s 72ms/step - accuracy: 0.8171 - loss: 0.4095
228/391 ━━━━━━━━━━━━━━━━━━━━ 11s 72ms/step - accuracy: 0.8172 - loss: 0.4094
229/391 ━━━━━━━━━━━━━━━━━━━━ 11s 71ms/step - accuracy: 0.8172 - loss: 0.4094
230/391 ━━━━━━━━━━━━━━━━━━━━ 11s 71ms/step - accuracy: 0.8172 - loss: 0.4094
231/391 ━━━━━━━━━━━━━━━━━━━━ 11s 72ms/step - accuracy: 0.8172 - loss: 0.4094
232/391 ━━━━━━━━━━━━━━━━━━━━ 11s 72ms/step - accuracy: 0.8172 - loss: 0.4093
233/391 ━━━━━━━━━━━━━━━━━━━━ 11s 72ms/step - accuracy: 0.8172 - loss: 0.4093
234/391 ━━━━━━━━━━━━━━━━━━━━ 11s 72ms/step - accuracy: 0.8172 - loss: 0.4093
235/391 ━━━━━━━━━━━━━━━━━━━━ 11s 72ms/step - accuracy: 0.8172 - loss: 0.4092
236/391 ━━━━━━━━━━━━━━━━━━━━ 11s 72ms/step - accuracy: 0.8172 - loss: 0.4092
237/391 ━━━━━━━━━━━━━━━━━━━━ 11s 72ms/step - accuracy: 0.8172 - loss: 0.4092
238/391 ━━━━━━━━━━━━━━━━━━━━ 10s 72ms/step - accuracy: 0.8173 - loss: 0.4092
239/391 ━━━━━━━━━━━━━━━━━━━━ 10s 72ms/step - accuracy: 0.8173 - loss: 0.4091
240/391 ━━━━━━━━━━━━━━━━━━━━ 10s 72ms/step - accuracy: 0.8173 - loss: 0.4091
241/391 ━━━━━━━━━━━━━━━━━━━━ 10s 72ms/step - accuracy: 0.8173 - loss: 0.4091
242/391 ━━━━━━━━━━━━━━━━━━━━ 10s 72ms/step - accuracy: 0.8173 - loss: 0.4090
243/391 ━━━━━━━━━━━━━━━━━━━━ 10s 72ms/step - accuracy: 0.8173 - loss: 0.4090
244/391 ━━━━━━━━━━━━━━━━━━━━ 10s 72ms/step - accuracy: 0.8173 - loss: 0.4090
245/391 ━━━━━━━━━━━━━━━━━━━━ 10s 72ms/step - accuracy: 0.8174 - loss: 0.4089
246/391 ━━━━━━━━━━━━━━━━━━━━ 10s 72ms/step - accuracy: 0.8174 - loss: 0.4089
247/391 ━━━━━━━━━━━━━━━━━━━━ 10s 72ms/step - accuracy: 0.8174 - loss: 0.4089
248/391 ━━━━━━━━━━━━━━━━━━━━ 10s 72ms/step - accuracy: 0.8174 - loss: 0.4088
249/391 ━━━━━━━━━━━━━━━━━━━━ 10s 72ms/step - accuracy: 0.8174 - loss: 0.4088
250/391 ━━━━━━━━━━━━━━━━━━━━ 10s 72ms/step - accuracy: 0.8174 - loss: 0.4088
251/391 ━━━━━━━━━━━━━━━━━━━━ 10s 72ms/step - accuracy: 0.8175 - loss: 0.4088
252/391 ━━━━━━━━━━━━━━━━━━━━ 9s 72ms/step - accuracy: 0.8175 - loss: 0.4087 
253/391 ━━━━━━━━━━━━━━━━━━━━ 9s 72ms/step - accuracy: 0.8175 - loss: 0.4087
254/391 ━━━━━━━━━━━━━━━━━━━━ 9s 72ms/step - accuracy: 0.8175 - loss: 0.4087
255/391 ━━━━━━━━━━━━━━━━━━━━ 9s 72ms/step - accuracy: 0.8175 - loss: 0.4086
256/391 ━━━━━━━━━━━━━━━━━━━━ 9s 72ms/step - accuracy: 0.8175 - loss: 0.4086
257/391 ━━━━━━━━━━━━━━━━━━━━ 9s 72ms/step - accuracy: 0.8176 - loss: 0.4086
258/391 ━━━━━━━━━━━━━━━━━━━━ 9s 72ms/step - accuracy: 0.8176 - loss: 0.4085
259/391 ━━━━━━━━━━━━━━━━━━━━ 9s 72ms/step - accuracy: 0.8176 - loss: 0.4085
260/391 ━━━━━━━━━━━━━━━━━━━━ 9s 72ms/step - accuracy: 0.8176 - loss: 0.4085
261/391 ━━━━━━━━━━━━━━━━━━━━ 9s 72ms/step - accuracy: 0.8176 - loss: 0.4084
262/391 ━━━━━━━━━━━━━━━━━━━━ 9s 72ms/step - accuracy: 0.8176 - loss: 0.4084
263/391 ━━━━━━━━━━━━━━━━━━━━ 9s 72ms/step - accuracy: 0.8177 - loss: 0.4084
264/391 ━━━━━━━━━━━━━━━━━━━━ 9s 72ms/step - accuracy: 0.8177 - loss: 0.4083
265/391 ━━━━━━━━━━━━━━━━━━━━ 9s 72ms/step - accuracy: 0.8177 - loss: 0.4083
266/391 ━━━━━━━━━━━━━━━━━━━━ 8s 72ms/step - accuracy: 0.8177 - loss: 0.4083
267/391 ━━━━━━━━━━━━━━━━━━━━ 8s 72ms/step - accuracy: 0.8177 - loss: 0.4082
268/391 ━━━━━━━━━━━━━━━━━━━━ 8s 72ms/step - accuracy: 0.8178 - loss: 0.4082
269/391 ━━━━━━━━━━━━━━━━━━━━ 8s 72ms/step - accuracy: 0.8178 - loss: 0.4082
270/391 ━━━━━━━━━━━━━━━━━━━━ 8s 71ms/step - accuracy: 0.8178 - loss: 0.4081
271/391 ━━━━━━━━━━━━━━━━━━━━ 8s 71ms/step - accuracy: 0.8178 - loss: 0.4081
272/391 ━━━━━━━━━━━━━━━━━━━━ 8s 71ms/step - accuracy: 0.8178 - loss: 0.4081
273/391 ━━━━━━━━━━━━━━━━━━━━ 8s 71ms/step - accuracy: 0.8178 - loss: 0.4080
274/391 ━━━━━━━━━━━━━━━━━━━━ 8s 71ms/step - accuracy: 0.8179 - loss: 0.4080
275/391 ━━━━━━━━━━━━━━━━━━━━ 8s 71ms/step - accuracy: 0.8179 - loss: 0.4080
276/391 ━━━━━━━━━━━━━━━━━━━━ 8s 71ms/step - accuracy: 0.8179 - loss: 0.4079
277/391 ━━━━━━━━━━━━━━━━━━━━ 8s 71ms/step - accuracy: 0.8179 - loss: 0.4079
278/391 ━━━━━━━━━━━━━━━━━━━━ 8s 71ms/step - accuracy: 0.8179 - loss: 0.4079
279/391 ━━━━━━━━━━━━━━━━━━━━ 8s 71ms/step - accuracy: 0.8179 - loss: 0.4078
280/391 ━━━━━━━━━━━━━━━━━━━━ 7s 71ms/step - accuracy: 0.8180 - loss: 0.4078
281/391 ━━━━━━━━━━━━━━━━━━━━ 7s 71ms/step - accuracy: 0.8180 - loss: 0.4078
282/391 ━━━━━━━━━━━━━━━━━━━━ 7s 71ms/step - accuracy: 0.8180 - loss: 0.4077
283/391 ━━━━━━━━━━━━━━━━━━━━ 7s 71ms/step - accuracy: 0.8180 - loss: 0.4077
284/391 ━━━━━━━━━━━━━━━━━━━━ 7s 71ms/step - accuracy: 0.8180 - loss: 0.4077
285/391 ━━━━━━━━━━━━━━━━━━━━ 7s 71ms/step - accuracy: 0.8180 - loss: 0.4076
286/391 ━━━━━━━━━━━━━━━━━━━━ 7s 71ms/step - accuracy: 0.8181 - loss: 0.4076
287/391 ━━━━━━━━━━━━━━━━━━━━ 7s 71ms/step - accuracy: 0.8181 - loss: 0.4076
288/391 ━━━━━━━━━━━━━━━━━━━━ 7s 71ms/step - accuracy: 0.8181 - loss: 0.4075
289/391 ━━━━━━━━━━━━━━━━━━━━ 7s 71ms/step - accuracy: 0.8181 - loss: 0.4075
290/391 ━━━━━━━━━━━━━━━━━━━━ 7s 71ms/step - accuracy: 0.8181 - loss: 0.4075
291/391 ━━━━━━━━━━━━━━━━━━━━ 7s 71ms/step - accuracy: 0.8181 - loss: 0.4074
292/391 ━━━━━━━━━━━━━━━━━━━━ 7s 71ms/step - accuracy: 0.8181 - loss: 0.4074
293/391 ━━━━━━━━━━━━━━━━━━━━ 6s 71ms/step - accuracy: 0.8181 - loss: 0.4074
294/391 ━━━━━━━━━━━━━━━━━━━━ 6s 71ms/step - accuracy: 0.8182 - loss: 0.4073
295/391 ━━━━━━━━━━━━━━━━━━━━ 6s 71ms/step - accuracy: 0.8182 - loss: 0.4073
296/391 ━━━━━━━━━━━━━━━━━━━━ 6s 71ms/step - accuracy: 0.8182 - loss: 0.4073
297/391 ━━━━━━━━━━━━━━━━━━━━ 6s 71ms/step - accuracy: 0.8182 - loss: 0.4072
298/391 ━━━━━━━━━━━━━━━━━━━━ 6s 71ms/step - accuracy: 0.8182 - loss: 0.4072
299/391 ━━━━━━━━━━━━━━━━━━━━ 6s 71ms/step - accuracy: 0.8182 - loss: 0.4072
300/391 ━━━━━━━━━━━━━━━━━━━━ 6s 71ms/step - accuracy: 0.8182 - loss: 0.4071
301/391 ━━━━━━━━━━━━━━━━━━━━ 6s 71ms/step - accuracy: 0.8182 - loss: 0.4071
302/391 ━━━━━━━━━━━━━━━━━━━━ 6s 71ms/step - accuracy: 0.8183 - loss: 0.4071
303/391 ━━━━━━━━━━━━━━━━━━━━ 6s 71ms/step - accuracy: 0.8183 - loss: 0.4070
304/391 ━━━━━━━━━━━━━━━━━━━━ 6s 71ms/step - accuracy: 0.8183 - loss: 0.4070
305/391 ━━━━━━━━━━━━━━━━━━━━ 6s 71ms/step - accuracy: 0.8183 - loss: 0.4070
306/391 ━━━━━━━━━━━━━━━━━━━━ 6s 71ms/step - accuracy: 0.8183 - loss: 0.4070
307/391 ━━━━━━━━━━━━━━━━━━━━ 5s 71ms/step - accuracy: 0.8183 - loss: 0.4069
308/391 ━━━━━━━━━━━━━━━━━━━━ 5s 71ms/step - accuracy: 0.8183 - loss: 0.4069
309/391 ━━━━━━━━━━━━━━━━━━━━ 5s 71ms/step - accuracy: 0.8183 - loss: 0.4069
310/391 ━━━━━━━━━━━━━━━━━━━━ 5s 71ms/step - accuracy: 0.8183 - loss: 0.4069
311/391 ━━━━━━━━━━━━━━━━━━━━ 5s 71ms/step - accuracy: 0.8184 - loss: 0.4068
312/391 ━━━━━━━━━━━━━━━━━━━━ 5s 71ms/step - accuracy: 0.8184 - loss: 0.4068
313/391 ━━━━━━━━━━━━━━━━━━━━ 5s 71ms/step - accuracy: 0.8184 - loss: 0.4068
314/391 ━━━━━━━━━━━━━━━━━━━━ 5s 71ms/step - accuracy: 0.8184 - loss: 0.4068
315/391 ━━━━━━━━━━━━━━━━━━━━ 5s 71ms/step - accuracy: 0.8184 - loss: 0.4067
316/391 ━━━━━━━━━━━━━━━━━━━━ 5s 71ms/step - accuracy: 0.8184 - loss: 0.4067
317/391 ━━━━━━━━━━━━━━━━━━━━ 5s 71ms/step - accuracy: 0.8184 - loss: 0.4067
318/391 ━━━━━━━━━━━━━━━━━━━━ 5s 71ms/step - accuracy: 0.8184 - loss: 0.4066
319/391 ━━━━━━━━━━━━━━━━━━━━ 5s 71ms/step - accuracy: 0.8184 - loss: 0.4066
320/391 ━━━━━━━━━━━━━━━━━━━━ 5s 71ms/step - accuracy: 0.8185 - loss: 0.4066
321/391 ━━━━━━━━━━━━━━━━━━━━ 4s 71ms/step - accuracy: 0.8185 - loss: 0.4066
322/391 ━━━━━━━━━━━━━━━━━━━━ 4s 71ms/step - accuracy: 0.8185 - loss: 0.4065
323/391 ━━━━━━━━━━━━━━━━━━━━ 4s 71ms/step - accuracy: 0.8185 - loss: 0.4065
324/391 ━━━━━━━━━━━━━━━━━━━━ 4s 71ms/step - accuracy: 0.8185 - loss: 0.4065
325/391 ━━━━━━━━━━━━━━━━━━━━ 4s 71ms/step - accuracy: 0.8185 - loss: 0.4064
326/391 ━━━━━━━━━━━━━━━━━━━━ 4s 71ms/step - accuracy: 0.8185 - loss: 0.4064
327/391 ━━━━━━━━━━━━━━━━━━━━ 4s 71ms/step - accuracy: 0.8185 - loss: 0.4064
328/391 ━━━━━━━━━━━━━━━━━━━━ 4s 71ms/step - accuracy: 0.8186 - loss: 0.4064
329/391 ━━━━━━━━━━━━━━━━━━━━ 4s 71ms/step - accuracy: 0.8186 - loss: 0.4063
330/391 ━━━━━━━━━━━━━━━━━━━━ 4s 71ms/step - accuracy: 0.8186 - loss: 0.4063
331/391 ━━━━━━━━━━━━━━━━━━━━ 4s 71ms/step - accuracy: 0.8186 - loss: 0.4063
332/391 ━━━━━━━━━━━━━━━━━━━━ 4s 71ms/step - accuracy: 0.8186 - loss: 0.4063
333/391 ━━━━━━━━━━━━━━━━━━━━ 4s 71ms/step - accuracy: 0.8186 - loss: 0.4062
334/391 ━━━━━━━━━━━━━━━━━━━━ 4s 71ms/step - accuracy: 0.8186 - loss: 0.4062
335/391 ━━━━━━━━━━━━━━━━━━━━ 3s 71ms/step - accuracy: 0.8186 - loss: 0.4062
336/391 ━━━━━━━━━━━━━━━━━━━━ 3s 71ms/step - accuracy: 0.8186 - loss: 0.4062
337/391 ━━━━━━━━━━━━━━━━━━━━ 3s 71ms/step - accuracy: 0.8186 - loss: 0.4061
338/391 ━━━━━━━━━━━━━━━━━━━━ 3s 71ms/step - accuracy: 0.8187 - loss: 0.4061
339/391 ━━━━━━━━━━━━━━━━━━━━ 3s 71ms/step - accuracy: 0.8187 - loss: 0.4061
340/391 ━━━━━━━━━━━━━━━━━━━━ 3s 71ms/step - accuracy: 0.8187 - loss: 0.4061
341/391 ━━━━━━━━━━━━━━━━━━━━ 3s 71ms/step - accuracy: 0.8187 - loss: 0.4060
342/391 ━━━━━━━━━━━━━━━━━━━━ 3s 71ms/step - accuracy: 0.8187 - loss: 0.4060
343/391 ━━━━━━━━━━━━━━━━━━━━ 3s 70ms/step - accuracy: 0.8187 - loss: 0.4060
344/391 ━━━━━━━━━━━━━━━━━━━━ 3s 71ms/step - accuracy: 0.8187 - loss: 0.4060
345/391 ━━━━━━━━━━━━━━━━━━━━ 3s 71ms/step - accuracy: 0.8187 - loss: 0.4059
346/391 ━━━━━━━━━━━━━━━━━━━━ 3s 71ms/step - accuracy: 0.8187 - loss: 0.4059
347/391 ━━━━━━━━━━━━━━━━━━━━ 3s 71ms/step - accuracy: 0.8187 - loss: 0.4059
348/391 ━━━━━━━━━━━━━━━━━━━━ 3s 71ms/step - accuracy: 0.8187 - loss: 0.4059
349/391 ━━━━━━━━━━━━━━━━━━━━ 2s 71ms/step - accuracy: 0.8188 - loss: 0.4059
350/391 ━━━━━━━━━━━━━━━━━━━━ 2s 70ms/step - accuracy: 0.8188 - loss: 0.4058
351/391 ━━━━━━━━━━━━━━━━━━━━ 2s 70ms/step - accuracy: 0.8188 - loss: 0.4058
352/391 ━━━━━━━━━━━━━━━━━━━━ 2s 70ms/step - accuracy: 0.8188 - loss: 0.4058
353/391 ━━━━━━━━━━━━━━━━━━━━ 2s 70ms/step - accuracy: 0.8188 - loss: 0.4058
354/391 ━━━━━━━━━━━━━━━━━━━━ 2s 70ms/step - accuracy: 0.8188 - loss: 0.4057
355/391 ━━━━━━━━━━━━━━━━━━━━ 2s 70ms/step - accuracy: 0.8188 - loss: 0.4057
356/391 ━━━━━━━━━━━━━━━━━━━━ 2s 70ms/step - accuracy: 0.8188 - loss: 0.4057
357/391 ━━━━━━━━━━━━━━━━━━━━ 2s 70ms/step - accuracy: 0.8188 - loss: 0.4057
358/391 ━━━━━━━━━━━━━━━━━━━━ 2s 71ms/step - accuracy: 0.8188 - loss: 0.4056
359/391 ━━━━━━━━━━━━━━━━━━━━ 2s 71ms/step - accuracy: 0.8188 - loss: 0.4056
360/391 ━━━━━━━━━━━━━━━━━━━━ 2s 71ms/step - accuracy: 0.8188 - loss: 0.4056
361/391 ━━━━━━━━━━━━━━━━━━━━ 2s 71ms/step - accuracy: 0.8189 - loss: 0.4056
362/391 ━━━━━━━━━━━━━━━━━━━━ 2s 71ms/step - accuracy: 0.8189 - loss: 0.4056
363/391 ━━━━━━━━━━━━━━━━━━━━ 1s 71ms/step - accuracy: 0.8189 - loss: 0.4055
364/391 ━━━━━━━━━━━━━━━━━━━━ 1s 71ms/step - accuracy: 0.8189 - loss: 0.4055
365/391 ━━━━━━━━━━━━━━━━━━━━ 1s 71ms/step - accuracy: 0.8189 - loss: 0.4055
366/391 ━━━━━━━━━━━━━━━━━━━━ 1s 70ms/step - accuracy: 0.8189 - loss: 0.4055
367/391 ━━━━━━━━━━━━━━━━━━━━ 1s 70ms/step - accuracy: 0.8189 - loss: 0.4055
368/391 ━━━━━━━━━━━━━━━━━━━━ 1s 71ms/step - accuracy: 0.8189 - loss: 0.4054
369/391 ━━━━━━━━━━━━━━━━━━━━ 1s 70ms/step - accuracy: 0.8189 - loss: 0.4054
370/391 ━━━━━━━━━━━━━━━━━━━━ 1s 70ms/step - accuracy: 0.8189 - loss: 0.4054
371/391 ━━━━━━━━━━━━━━━━━━━━ 1s 70ms/step - accuracy: 0.8189 - loss: 0.4054
372/391 ━━━━━━━━━━━━━━━━━━━━ 1s 70ms/step - accuracy: 0.8189 - loss: 0.4054
373/391 ━━━━━━━━━━━━━━━━━━━━ 1s 70ms/step - accuracy: 0.8190 - loss: 0.4053
374/391 ━━━━━━━━━━━━━━━━━━━━ 1s 70ms/step - accuracy: 0.8190 - loss: 0.4053
375/391 ━━━━━━━━━━━━━━━━━━━━ 1s 70ms/step - accuracy: 0.8190 - loss: 0.4053
376/391 ━━━━━━━━━━━━━━━━━━━━ 1s 70ms/step - accuracy: 0.8190 - loss: 0.4053
377/391 ━━━━━━━━━━━━━━━━━━━━ 0s 70ms/step - accuracy: 0.8190 - loss: 0.4052
378/391 ━━━━━━━━━━━━━━━━━━━━ 0s 70ms/step - accuracy: 0.8190 - loss: 0.4052
379/391 ━━━━━━━━━━━━━━━━━━━━ 0s 70ms/step - accuracy: 0.8190 - loss: 0.4052
380/391 ━━━━━━━━━━━━━━━━━━━━ 0s 70ms/step - accuracy: 0.8190 - loss: 0.4052
381/391 ━━━━━━━━━━━━━━━━━━━━ 0s 70ms/step - accuracy: 0.8190 - loss: 0.4051
382/391 ━━━━━━━━━━━━━━━━━━━━ 0s 70ms/step - accuracy: 0.8190 - loss: 0.4051
383/391 ━━━━━━━━━━━━━━━━━━━━ 0s 70ms/step - accuracy: 0.8190 - loss: 0.4051
384/391 ━━━━━━━━━━━━━━━━━━━━ 0s 70ms/step - accuracy: 0.8191 - loss: 0.4051
385/391 ━━━━━━━━━━━━━━━━━━━━ 0s 70ms/step - accuracy: 0.8191 - loss: 0.4050
386/391 ━━━━━━━━━━━━━━━━━━━━ 0s 70ms/step - accuracy: 0.8191 - loss: 0.4050
387/391 ━━━━━━━━━━━━━━━━━━━━ 0s 71ms/step - accuracy: 0.8191 - loss: 0.4050
388/391 ━━━━━━━━━━━━━━━━━━━━ 0s 70ms/step - accuracy: 0.8191 - loss: 0.4050
389/391 ━━━━━━━━━━━━━━━━━━━━ 0s 70ms/step - accuracy: 0.8191 - loss: 0.4049
390/391 ━━━━━━━━━━━━━━━━━━━━ 0s 71ms/step - accuracy: 0.8191 - loss: 0.4049
391/391 ━━━━━━━━━━━━━━━━━━━━ 0s 76ms/step - accuracy: 0.8191 - loss: 0.4049
391/391 ━━━━━━━━━━━━━━━━━━━━ 45s 114ms/step - accuracy: 0.8230 - loss: 0.3954 - val_accuracy: 0.8266 - val_loss: 0.3770
Epoch 3/5
  1/391 ━━━━━━━━━━━━━━━━━━━━ 1:04 166ms/step - accuracy: 0.8594 - loss: 0.3052
  2/391 ━━━━━━━━━━━━━━━━━━━━ 26s 67ms/step - accuracy: 0.8477 - loss: 0.3431  
  3/391 ━━━━━━━━━━━━━━━━━━━━ 28s 73ms/step - accuracy: 0.8394 - loss: 0.3546
  4/391 ━━━━━━━━━━━━━━━━━━━━ 26s 67ms/step - accuracy: 0.8405 - loss: 0.3558
  5/391 ━━━━━━━━━━━━━━━━━━━━ 28s 73ms/step - accuracy: 0.8424 - loss: 0.3548
  6/391 ━━━━━━━━━━━━━━━━━━━━ 29s 77ms/step - accuracy: 0.8431 - loss: 0.3562
  7/391 ━━━━━━━━━━━━━━━━━━━━ 30s 78ms/step - accuracy: 0.8438 - loss: 0.3565
  8/391 ━━━━━━━━━━━━━━━━━━━━ 30s 80ms/step - accuracy: 0.8433 - loss: 0.3583
  9/391 ━━━━━━━━━━━━━━━━━━━━ 31s 82ms/step - accuracy: 0.8424 - loss: 0.3595
 10/391 ━━━━━━━━━━━━━━━━━━━━ 31s 82ms/step - accuracy: 0.8419 - loss: 0.3604
 11/391 ━━━━━━━━━━━━━━━━━━━━ 31s 83ms/step - accuracy: 0.8414 - loss: 0.3607
 12/391 ━━━━━━━━━━━━━━━━━━━━ 31s 82ms/step - accuracy: 0.8417 - loss: 0.3603
 13/391 ━━━━━━━━━━━━━━━━━━━━ 30s 80ms/step - accuracy: 0.8421 - loss: 0.3598
 14/391 ━━━━━━━━━━━━━━━━━━━━ 29s 78ms/step - accuracy: 0.8423 - loss: 0.3595
 15/391 ━━━━━━━━━━━━━━━━━━━━ 28s 76ms/step - accuracy: 0.8427 - loss: 0.3589
 16/391 ━━━━━━━━━━━━━━━━━━━━ 28s 76ms/step - accuracy: 0.8430 - loss: 0.3587
 17/391 ━━━━━━━━━━━━━━━━━━━━ 28s 77ms/step - accuracy: 0.8432 - loss: 0.3587
 18/391 ━━━━━━━━━━━━━━━━━━━━ 28s 77ms/step - accuracy: 0.8435 - loss: 0.3583
 19/391 ━━━━━━━━━━━━━━━━━━━━ 28s 78ms/step - accuracy: 0.8439 - loss: 0.3579
 20/391 ━━━━━━━━━━━━━━━━━━━━ 28s 77ms/step - accuracy: 0.8442 - loss: 0.3576
 21/391 ━━━━━━━━━━━━━━━━━━━━ 28s 76ms/step - accuracy: 0.8444 - loss: 0.3573
 22/391 ━━━━━━━━━━━━━━━━━━━━ 27s 76ms/step - accuracy: 0.8447 - loss: 0.3569
 23/391 ━━━━━━━━━━━━━━━━━━━━ 28s 76ms/step - accuracy: 0.8451 - loss: 0.3565
 24/391 ━━━━━━━━━━━━━━━━━━━━ 27s 76ms/step - accuracy: 0.8454 - loss: 0.3561
 25/391 ━━━━━━━━━━━━━━━━━━━━ 27s 76ms/step - accuracy: 0.8458 - loss: 0.3557
 26/391 ━━━━━━━━━━━━━━━━━━━━ 27s 76ms/step - accuracy: 0.8461 - loss: 0.3551
 27/391 ━━━━━━━━━━━━━━━━━━━━ 27s 77ms/step - accuracy: 0.8464 - loss: 0.3546
 28/391 ━━━━━━━━━━━━━━━━━━━━ 27s 77ms/step - accuracy: 0.8468 - loss: 0.3540
 29/391 ━━━━━━━━━━━━━━━━━━━━ 27s 77ms/step - accuracy: 0.8471 - loss: 0.3534
 30/391 ━━━━━━━━━━━━━━━━━━━━ 28s 78ms/step - accuracy: 0.8473 - loss: 0.3529
 31/391 ━━━━━━━━━━━━━━━━━━━━ 27s 77ms/step - accuracy: 0.8476 - loss: 0.3524
 32/391 ━━━━━━━━━━━━━━━━━━━━ 27s 77ms/step - accuracy: 0.8479 - loss: 0.3520
 33/391 ━━━━━━━━━━━━━━━━━━━━ 27s 77ms/step - accuracy: 0.8481 - loss: 0.3517
 34/391 ━━━━━━━━━━━━━━━━━━━━ 27s 77ms/step - accuracy: 0.8483 - loss: 0.3513
 35/391 ━━━━━━━━━━━━━━━━━━━━ 27s 77ms/step - accuracy: 0.8484 - loss: 0.3511
 36/391 ━━━━━━━━━━━━━━━━━━━━ 27s 78ms/step - accuracy: 0.8485 - loss: 0.3511
 37/391 ━━━━━━━━━━━━━━━━━━━━ 27s 78ms/step - accuracy: 0.8485 - loss: 0.3512
 38/391 ━━━━━━━━━━━━━━━━━━━━ 27s 78ms/step - accuracy: 0.8486 - loss: 0.3512
 39/391 ━━━━━━━━━━━━━━━━━━━━ 27s 79ms/step - accuracy: 0.8486 - loss: 0.3513
 40/391 ━━━━━━━━━━━━━━━━━━━━ 27s 79ms/step - accuracy: 0.8486 - loss: 0.3513
 41/391 ━━━━━━━━━━━━━━━━━━━━ 27s 79ms/step - accuracy: 0.8487 - loss: 0.3513
 42/391 ━━━━━━━━━━━━━━━━━━━━ 27s 79ms/step - accuracy: 0.8488 - loss: 0.3513
 43/391 ━━━━━━━━━━━━━━━━━━━━ 27s 78ms/step - accuracy: 0.8489 - loss: 0.3513
 44/391 ━━━━━━━━━━━━━━━━━━━━ 27s 78ms/step - accuracy: 0.8491 - loss: 0.3512
 45/391 ━━━━━━━━━━━━━━━━━━━━ 27s 78ms/step - accuracy: 0.8492 - loss: 0.3512
 46/391 ━━━━━━━━━━━━━━━━━━━━ 26s 78ms/step - accuracy: 0.8493 - loss: 0.3511
 47/391 ━━━━━━━━━━━━━━━━━━━━ 27s 79ms/step - accuracy: 0.8494 - loss: 0.3510
 48/391 ━━━━━━━━━━━━━━━━━━━━ 26s 78ms/step - accuracy: 0.8495 - loss: 0.3510
 49/391 ━━━━━━━━━━━━━━━━━━━━ 26s 78ms/step - accuracy: 0.8496 - loss: 0.3510
 50/391 ━━━━━━━━━━━━━━━━━━━━ 26s 78ms/step - accuracy: 0.8497 - loss: 0.3510
 51/391 ━━━━━━━━━━━━━━━━━━━━ 26s 78ms/step - accuracy: 0.8498 - loss: 0.3510
 52/391 ━━━━━━━━━━━━━━━━━━━━ 26s 77ms/step - accuracy: 0.8499 - loss: 0.3510
 53/391 ━━━━━━━━━━━━━━━━━━━━ 25s 77ms/step - accuracy: 0.8500 - loss: 0.3509
 54/391 ━━━━━━━━━━━━━━━━━━━━ 25s 76ms/step - accuracy: 0.8501 - loss: 0.3508
 55/391 ━━━━━━━━━━━━━━━━━━━━ 25s 76ms/step - accuracy: 0.8502 - loss: 0.3508
 56/391 ━━━━━━━━━━━━━━━━━━━━ 25s 76ms/step - accuracy: 0.8502 - loss: 0.3508
 57/391 ━━━━━━━━━━━━━━━━━━━━ 25s 76ms/step - accuracy: 0.8503 - loss: 0.3507
 58/391 ━━━━━━━━━━━━━━━━━━━━ 25s 75ms/step - accuracy: 0.8504 - loss: 0.3507
 59/391 ━━━━━━━━━━━━━━━━━━━━ 25s 76ms/step - accuracy: 0.8504 - loss: 0.3507
 60/391 ━━━━━━━━━━━━━━━━━━━━ 25s 76ms/step - accuracy: 0.8505 - loss: 0.3506
 61/391 ━━━━━━━━━━━━━━━━━━━━ 25s 76ms/step - accuracy: 0.8506 - loss: 0.3506
 62/391 ━━━━━━━━━━━━━━━━━━━━ 25s 77ms/step - accuracy: 0.8506 - loss: 0.3506
 63/391 ━━━━━━━━━━━━━━━━━━━━ 25s 76ms/step - accuracy: 0.8507 - loss: 0.3506
 64/391 ━━━━━━━━━━━━━━━━━━━━ 24s 76ms/step - accuracy: 0.8507 - loss: 0.3505
 65/391 ━━━━━━━━━━━━━━━━━━━━ 24s 76ms/step - accuracy: 0.8508 - loss: 0.3505
 66/391 ━━━━━━━━━━━━━━━━━━━━ 24s 76ms/step - accuracy: 0.8509 - loss: 0.3505
 67/391 ━━━━━━━━━━━━━━━━━━━━ 24s 75ms/step - accuracy: 0.8510 - loss: 0.3504
 68/391 ━━━━━━━━━━━━━━━━━━━━ 24s 75ms/step - accuracy: 0.8510 - loss: 0.3503
 69/391 ━━━━━━━━━━━━━━━━━━━━ 24s 75ms/step - accuracy: 0.8511 - loss: 0.3502
 70/391 ━━━━━━━━━━━━━━━━━━━━ 23s 75ms/step - accuracy: 0.8512 - loss: 0.3502
 71/391 ━━━━━━━━━━━━━━━━━━━━ 23s 74ms/step - accuracy: 0.8512 - loss: 0.3501
 72/391 ━━━━━━━━━━━━━━━━━━━━ 23s 74ms/step - accuracy: 0.8513 - loss: 0.3501
 73/391 ━━━━━━━━━━━━━━━━━━━━ 23s 75ms/step - accuracy: 0.8514 - loss: 0.3500
 74/391 ━━━━━━━━━━━━━━━━━━━━ 23s 75ms/step - accuracy: 0.8514 - loss: 0.3499
 75/391 ━━━━━━━━━━━━━━━━━━━━ 23s 75ms/step - accuracy: 0.8515 - loss: 0.3498
 76/391 ━━━━━━━━━━━━━━━━━━━━ 23s 75ms/step - accuracy: 0.8516 - loss: 0.3498
 77/391 ━━━━━━━━━━━━━━━━━━━━ 23s 75ms/step - accuracy: 0.8516 - loss: 0.3497
 78/391 ━━━━━━━━━━━━━━━━━━━━ 23s 74ms/step - accuracy: 0.8517 - loss: 0.3496
 79/391 ━━━━━━━━━━━━━━━━━━━━ 23s 74ms/step - accuracy: 0.8517 - loss: 0.3495
 80/391 ━━━━━━━━━━━━━━━━━━━━ 23s 74ms/step - accuracy: 0.8518 - loss: 0.3495
 81/391 ━━━━━━━━━━━━━━━━━━━━ 22s 74ms/step - accuracy: 0.8518 - loss: 0.3494
 82/391 ━━━━━━━━━━━━━━━━━━━━ 22s 74ms/step - accuracy: 0.8518 - loss: 0.3493
 83/391 ━━━━━━━━━━━━━━━━━━━━ 22s 74ms/step - accuracy: 0.8519 - loss: 0.3493
 84/391 ━━━━━━━━━━━━━━━━━━━━ 22s 74ms/step - accuracy: 0.8519 - loss: 0.3492
 85/391 ━━━━━━━━━━━━━━━━━━━━ 22s 74ms/step - accuracy: 0.8519 - loss: 0.3492
 86/391 ━━━━━━━━━━━━━━━━━━━━ 22s 74ms/step - accuracy: 0.8519 - loss: 0.3492
 87/391 ━━━━━━━━━━━━━━━━━━━━ 22s 74ms/step - accuracy: 0.8519 - loss: 0.3491
 88/391 ━━━━━━━━━━━━━━━━━━━━ 22s 74ms/step - accuracy: 0.8519 - loss: 0.3491
 89/391 ━━━━━━━━━━━━━━━━━━━━ 22s 74ms/step - accuracy: 0.8519 - loss: 0.3491
 90/391 ━━━━━━━━━━━━━━━━━━━━ 22s 74ms/step - accuracy: 0.8519 - loss: 0.3491
 91/391 ━━━━━━━━━━━━━━━━━━━━ 22s 74ms/step - accuracy: 0.8519 - loss: 0.3491
 92/391 ━━━━━━━━━━━━━━━━━━━━ 22s 74ms/step - accuracy: 0.8519 - loss: 0.3491
 93/391 ━━━━━━━━━━━━━━━━━━━━ 22s 74ms/step - accuracy: 0.8519 - loss: 0.3491
 94/391 ━━━━━━━━━━━━━━━━━━━━ 22s 74ms/step - accuracy: 0.8519 - loss: 0.3490
 95/391 ━━━━━━━━━━━━━━━━━━━━ 21s 74ms/step - accuracy: 0.8519 - loss: 0.3490
 96/391 ━━━━━━━━━━━━━━━━━━━━ 21s 74ms/step - accuracy: 0.8519 - loss: 0.3490
 97/391 ━━━━━━━━━━━━━━━━━━━━ 21s 74ms/step - accuracy: 0.8519 - loss: 0.3490
 98/391 ━━━━━━━━━━━━━━━━━━━━ 21s 74ms/step - accuracy: 0.8518 - loss: 0.3490
 99/391 ━━━━━━━━━━━━━━━━━━━━ 21s 74ms/step - accuracy: 0.8518 - loss: 0.3491
100/391 ━━━━━━━━━━━━━━━━━━━━ 21s 74ms/step - accuracy: 0.8518 - loss: 0.3491
101/391 ━━━━━━━━━━━━━━━━━━━━ 21s 74ms/step - accuracy: 0.8518 - loss: 0.3491
102/391 ━━━━━━━━━━━━━━━━━━━━ 21s 73ms/step - accuracy: 0.8518 - loss: 0.3491
103/391 ━━━━━━━━━━━━━━━━━━━━ 21s 73ms/step - accuracy: 0.8517 - loss: 0.3492
104/391 ━━━━━━━━━━━━━━━━━━━━ 20s 73ms/step - accuracy: 0.8517 - loss: 0.3492
105/391 ━━━━━━━━━━━━━━━━━━━━ 20s 73ms/step - accuracy: 0.8517 - loss: 0.3492
106/391 ━━━━━━━━━━━━━━━━━━━━ 20s 73ms/step - accuracy: 0.8516 - loss: 0.3493
107/391 ━━━━━━━━━━━━━━━━━━━━ 20s 73ms/step - accuracy: 0.8516 - loss: 0.3493
108/391 ━━━━━━━━━━━━━━━━━━━━ 20s 72ms/step - accuracy: 0.8516 - loss: 0.3494
109/391 ━━━━━━━━━━━━━━━━━━━━ 20s 72ms/step - accuracy: 0.8515 - loss: 0.3494
110/391 ━━━━━━━━━━━━━━━━━━━━ 20s 72ms/step - accuracy: 0.8515 - loss: 0.3494
111/391 ━━━━━━━━━━━━━━━━━━━━ 20s 72ms/step - accuracy: 0.8515 - loss: 0.3495
112/391 ━━━━━━━━━━━━━━━━━━━━ 20s 72ms/step - accuracy: 0.8514 - loss: 0.3495
113/391 ━━━━━━━━━━━━━━━━━━━━ 20s 72ms/step - accuracy: 0.8514 - loss: 0.3495
114/391 ━━━━━━━━━━━━━━━━━━━━ 19s 72ms/step - accuracy: 0.8514 - loss: 0.3495
115/391 ━━━━━━━━━━━━━━━━━━━━ 19s 72ms/step - accuracy: 0.8513 - loss: 0.3496
116/391 ━━━━━━━━━━━━━━━━━━━━ 19s 72ms/step - accuracy: 0.8513 - loss: 0.3496
117/391 ━━━━━━━━━━━━━━━━━━━━ 19s 72ms/step - accuracy: 0.8513 - loss: 0.3496
118/391 ━━━━━━━━━━━━━━━━━━━━ 19s 72ms/step - accuracy: 0.8512 - loss: 0.3497
119/391 ━━━━━━━━━━━━━━━━━━━━ 19s 72ms/step - accuracy: 0.8512 - loss: 0.3497
120/391 ━━━━━━━━━━━━━━━━━━━━ 19s 72ms/step - accuracy: 0.8512 - loss: 0.3497
121/391 ━━━━━━━━━━━━━━━━━━━━ 19s 72ms/step - accuracy: 0.8512 - loss: 0.3497
122/391 ━━━━━━━━━━━━━━━━━━━━ 19s 72ms/step - accuracy: 0.8511 - loss: 0.3497
123/391 ━━━━━━━━━━━━━━━━━━━━ 19s 73ms/step - accuracy: 0.8511 - loss: 0.3497
124/391 ━━━━━━━━━━━━━━━━━━━━ 19s 73ms/step - accuracy: 0.8511 - loss: 0.3497
125/391 ━━━━━━━━━━━━━━━━━━━━ 19s 73ms/step - accuracy: 0.8511 - loss: 0.3497
126/391 ━━━━━━━━━━━━━━━━━━━━ 19s 73ms/step - accuracy: 0.8510 - loss: 0.3497
127/391 ━━━━━━━━━━━━━━━━━━━━ 19s 73ms/step - accuracy: 0.8510 - loss: 0.3497
128/391 ━━━━━━━━━━━━━━━━━━━━ 19s 73ms/step - accuracy: 0.8510 - loss: 0.3497
129/391 ━━━━━━━━━━━━━━━━━━━━ 19s 74ms/step - accuracy: 0.8510 - loss: 0.3497
130/391 ━━━━━━━━━━━━━━━━━━━━ 19s 73ms/step - accuracy: 0.8510 - loss: 0.3497
131/391 ━━━━━━━━━━━━━━━━━━━━ 19s 73ms/step - accuracy: 0.8510 - loss: 0.3497
132/391 ━━━━━━━━━━━━━━━━━━━━ 19s 73ms/step - accuracy: 0.8509 - loss: 0.3496
133/391 ━━━━━━━━━━━━━━━━━━━━ 18s 73ms/step - accuracy: 0.8509 - loss: 0.3496
134/391 ━━━━━━━━━━━━━━━━━━━━ 18s 74ms/step - accuracy: 0.8509 - loss: 0.3496
135/391 ━━━━━━━━━━━━━━━━━━━━ 18s 74ms/step - accuracy: 0.8509 - loss: 0.3496
136/391 ━━━━━━━━━━━━━━━━━━━━ 18s 74ms/step - accuracy: 0.8509 - loss: 0.3496
137/391 ━━━━━━━━━━━━━━━━━━━━ 18s 74ms/step - accuracy: 0.8509 - loss: 0.3496
138/391 ━━━━━━━━━━━━━━━━━━━━ 18s 74ms/step - accuracy: 0.8509 - loss: 0.3495
139/391 ━━━━━━━━━━━━━━━━━━━━ 18s 74ms/step - accuracy: 0.8509 - loss: 0.3495
140/391 ━━━━━━━━━━━━━━━━━━━━ 18s 74ms/step - accuracy: 0.8509 - loss: 0.3495
141/391 ━━━━━━━━━━━━━━━━━━━━ 18s 75ms/step - accuracy: 0.8509 - loss: 0.3495
142/391 ━━━━━━━━━━━━━━━━━━━━ 18s 75ms/step - accuracy: 0.8509 - loss: 0.3494
143/391 ━━━━━━━━━━━━━━━━━━━━ 18s 75ms/step - accuracy: 0.8508 - loss: 0.3494
144/391 ━━━━━━━━━━━━━━━━━━━━ 18s 75ms/step - accuracy: 0.8508 - loss: 0.3494
145/391 ━━━━━━━━━━━━━━━━━━━━ 18s 75ms/step - accuracy: 0.8508 - loss: 0.3494
146/391 ━━━━━━━━━━━━━━━━━━━━ 18s 75ms/step - accuracy: 0.8508 - loss: 0.3494
147/391 ━━━━━━━━━━━━━━━━━━━━ 18s 75ms/step - accuracy: 0.8508 - loss: 0.3493
148/391 ━━━━━━━━━━━━━━━━━━━━ 18s 75ms/step - accuracy: 0.8508 - loss: 0.3493
149/391 ━━━━━━━━━━━━━━━━━━━━ 18s 75ms/step - accuracy: 0.8508 - loss: 0.3493
150/391 ━━━━━━━━━━━━━━━━━━━━ 17s 75ms/step - accuracy: 0.8508 - loss: 0.3493
151/391 ━━━━━━━━━━━━━━━━━━━━ 17s 75ms/step - accuracy: 0.8508 - loss: 0.3493
152/391 ━━━━━━━━━━━━━━━━━━━━ 17s 75ms/step - accuracy: 0.8508 - loss: 0.3493
153/391 ━━━━━━━━━━━━━━━━━━━━ 17s 75ms/step - accuracy: 0.8507 - loss: 0.3493
154/391 ━━━━━━━━━━━━━━━━━━━━ 17s 75ms/step - accuracy: 0.8507 - loss: 0.3493
155/391 ━━━━━━━━━━━━━━━━━━━━ 17s 75ms/step - accuracy: 0.8507 - loss: 0.3493
156/391 ━━━━━━━━━━━━━━━━━━━━ 17s 74ms/step - accuracy: 0.8507 - loss: 0.3493
157/391 ━━━━━━━━━━━━━━━━━━━━ 17s 74ms/step - accuracy: 0.8507 - loss: 0.3492
158/391 ━━━━━━━━━━━━━━━━━━━━ 17s 74ms/step - accuracy: 0.8507 - loss: 0.3492
159/391 ━━━━━━━━━━━━━━━━━━━━ 17s 74ms/step - accuracy: 0.8507 - loss: 0.3492
160/391 ━━━━━━━━━━━━━━━━━━━━ 17s 74ms/step - accuracy: 0.8506 - loss: 0.3492
161/391 ━━━━━━━━━━━━━━━━━━━━ 17s 74ms/step - accuracy: 0.8506 - loss: 0.3492
162/391 ━━━━━━━━━━━━━━━━━━━━ 17s 74ms/step - accuracy: 0.8506 - loss: 0.3492
163/391 ━━━━━━━━━━━━━━━━━━━━ 16s 74ms/step - accuracy: 0.8506 - loss: 0.3492
164/391 ━━━━━━━━━━━━━━━━━━━━ 16s 74ms/step - accuracy: 0.8506 - loss: 0.3492
165/391 ━━━━━━━━━━━━━━━━━━━━ 16s 75ms/step - accuracy: 0.8506 - loss: 0.3492
166/391 ━━━━━━━━━━━━━━━━━━━━ 16s 75ms/step - accuracy: 0.8506 - loss: 0.3492
167/391 ━━━━━━━━━━━━━━━━━━━━ 16s 74ms/step - accuracy: 0.8506 - loss: 0.3492
168/391 ━━━━━━━━━━━━━━━━━━━━ 16s 74ms/step - accuracy: 0.8505 - loss: 0.3492
169/391 ━━━━━━━━━━━━━━━━━━━━ 16s 74ms/step - accuracy: 0.8505 - loss: 0.3492
170/391 ━━━━━━━━━━━━━━━━━━━━ 16s 74ms/step - accuracy: 0.8505 - loss: 0.3492
171/391 ━━━━━━━━━━━━━━━━━━━━ 16s 75ms/step - accuracy: 0.8505 - loss: 0.3492
172/391 ━━━━━━━━━━━━━━━━━━━━ 16s 75ms/step - accuracy: 0.8505 - loss: 0.3492
173/391 ━━━━━━━━━━━━━━━━━━━━ 16s 75ms/step - accuracy: 0.8504 - loss: 0.3492
174/391 ━━━━━━━━━━━━━━━━━━━━ 16s 74ms/step - accuracy: 0.8504 - loss: 0.3492
175/391 ━━━━━━━━━━━━━━━━━━━━ 16s 74ms/step - accuracy: 0.8504 - loss: 0.3492
176/391 ━━━━━━━━━━━━━━━━━━━━ 15s 74ms/step - accuracy: 0.8504 - loss: 0.3492
177/391 ━━━━━━━━━━━━━━━━━━━━ 15s 74ms/step - accuracy: 0.8504 - loss: 0.3492
178/391 ━━━━━━━━━━━━━━━━━━━━ 15s 74ms/step - accuracy: 0.8504 - loss: 0.3492
179/391 ━━━━━━━━━━━━━━━━━━━━ 15s 74ms/step - accuracy: 0.8503 - loss: 0.3492
180/391 ━━━━━━━━━━━━━━━━━━━━ 15s 74ms/step - accuracy: 0.8503 - loss: 0.3492
181/391 ━━━━━━━━━━━━━━━━━━━━ 15s 74ms/step - accuracy: 0.8503 - loss: 0.3492
182/391 ━━━━━━━━━━━━━━━━━━━━ 15s 74ms/step - accuracy: 0.8503 - loss: 0.3492
183/391 ━━━━━━━━━━━━━━━━━━━━ 15s 74ms/step - accuracy: 0.8503 - loss: 0.3492
184/391 ━━━━━━━━━━━━━━━━━━━━ 15s 74ms/step - accuracy: 0.8503 - loss: 0.3492
185/391 ━━━━━━━━━━━━━━━━━━━━ 15s 74ms/step - accuracy: 0.8503 - loss: 0.3492
186/391 ━━━━━━━━━━━━━━━━━━━━ 15s 74ms/step - accuracy: 0.8503 - loss: 0.3492
187/391 ━━━━━━━━━━━━━━━━━━━━ 15s 74ms/step - accuracy: 0.8502 - loss: 0.3492
188/391 ━━━━━━━━━━━━━━━━━━━━ 15s 74ms/step - accuracy: 0.8502 - loss: 0.3492
189/391 ━━━━━━━━━━━━━━━━━━━━ 14s 74ms/step - accuracy: 0.8502 - loss: 0.3492
190/391 ━━━━━━━━━━━━━━━━━━━━ 14s 74ms/step - accuracy: 0.8502 - loss: 0.3492
191/391 ━━━━━━━━━━━━━━━━━━━━ 14s 74ms/step - accuracy: 0.8502 - loss: 0.3492
192/391 ━━━━━━━━━━━━━━━━━━━━ 14s 74ms/step - accuracy: 0.8502 - loss: 0.3492
193/391 ━━━━━━━━━━━━━━━━━━━━ 14s 74ms/step - accuracy: 0.8502 - loss: 0.3492
194/391 ━━━━━━━━━━━━━━━━━━━━ 14s 74ms/step - accuracy: 0.8502 - loss: 0.3492
195/391 ━━━━━━━━━━━━━━━━━━━━ 14s 74ms/step - accuracy: 0.8501 - loss: 0.3491
196/391 ━━━━━━━━━━━━━━━━━━━━ 14s 74ms/step - accuracy: 0.8501 - loss: 0.3491
197/391 ━━━━━━━━━━━━━━━━━━━━ 14s 74ms/step - accuracy: 0.8501 - loss: 0.3491
198/391 ━━━━━━━━━━━━━━━━━━━━ 14s 74ms/step - accuracy: 0.8501 - loss: 0.3491
199/391 ━━━━━━━━━━━━━━━━━━━━ 14s 74ms/step - accuracy: 0.8501 - loss: 0.3491
200/391 ━━━━━━━━━━━━━━━━━━━━ 14s 74ms/step - accuracy: 0.8501 - loss: 0.3491
201/391 ━━━━━━━━━━━━━━━━━━━━ 14s 74ms/step - accuracy: 0.8501 - loss: 0.3491
202/391 ━━━━━━━━━━━━━━━━━━━━ 14s 75ms/step - accuracy: 0.8501 - loss: 0.3491
203/391 ━━━━━━━━━━━━━━━━━━━━ 14s 75ms/step - accuracy: 0.8501 - loss: 0.3490
204/391 ━━━━━━━━━━━━━━━━━━━━ 13s 75ms/step - accuracy: 0.8501 - loss: 0.3490
205/391 ━━━━━━━━━━━━━━━━━━━━ 13s 75ms/step - accuracy: 0.8501 - loss: 0.3490
206/391 ━━━━━━━━━━━━━━━━━━━━ 13s 74ms/step - accuracy: 0.8501 - loss: 0.3490
207/391 ━━━━━━━━━━━━━━━━━━━━ 13s 74ms/step - accuracy: 0.8501 - loss: 0.3490
208/391 ━━━━━━━━━━━━━━━━━━━━ 13s 74ms/step - accuracy: 0.8501 - loss: 0.3489
209/391 ━━━━━━━━━━━━━━━━━━━━ 13s 74ms/step - accuracy: 0.8501 - loss: 0.3489
210/391 ━━━━━━━━━━━━━━━━━━━━ 13s 74ms/step - accuracy: 0.8501 - loss: 0.3489
211/391 ━━━━━━━━━━━━━━━━━━━━ 13s 74ms/step - accuracy: 0.8501 - loss: 0.3489
212/391 ━━━━━━━━━━━━━━━━━━━━ 13s 74ms/step - accuracy: 0.8501 - loss: 0.3488
213/391 ━━━━━━━━━━━━━━━━━━━━ 13s 74ms/step - accuracy: 0.8501 - loss: 0.3488
214/391 ━━━━━━━━━━━━━━━━━━━━ 13s 74ms/step - accuracy: 0.8501 - loss: 0.3488
215/391 ━━━━━━━━━━━━━━━━━━━━ 13s 74ms/step - accuracy: 0.8501 - loss: 0.3488
216/391 ━━━━━━━━━━━━━━━━━━━━ 12s 74ms/step - accuracy: 0.8501 - loss: 0.3488
217/391 ━━━━━━━━━━━━━━━━━━━━ 12s 74ms/step - accuracy: 0.8501 - loss: 0.3487
218/391 ━━━━━━━━━━━━━━━━━━━━ 12s 74ms/step - accuracy: 0.8501 - loss: 0.3487
219/391 ━━━━━━━━━━━━━━━━━━━━ 12s 74ms/step - accuracy: 0.8501 - loss: 0.3487
220/391 ━━━━━━━━━━━━━━━━━━━━ 12s 74ms/step - accuracy: 0.8501 - loss: 0.3487
221/391 ━━━━━━━━━━━━━━━━━━━━ 12s 74ms/step - accuracy: 0.8500 - loss: 0.3487
222/391 ━━━━━━━━━━━━━━━━━━━━ 12s 74ms/step - accuracy: 0.8500 - loss: 0.3486
223/391 ━━━━━━━━━━━━━━━━━━━━ 12s 74ms/step - accuracy: 0.8500 - loss: 0.3486
224/391 ━━━━━━━━━━━━━━━━━━━━ 12s 74ms/step - accuracy: 0.8500 - loss: 0.3486
225/391 ━━━━━━━━━━━━━━━━━━━━ 12s 74ms/step - accuracy: 0.8500 - loss: 0.3486
226/391 ━━━━━━━━━━━━━━━━━━━━ 12s 74ms/step - accuracy: 0.8500 - loss: 0.3486
227/391 ━━━━━━━━━━━━━━━━━━━━ 12s 74ms/step - accuracy: 0.8500 - loss: 0.3485
228/391 ━━━━━━━━━━━━━━━━━━━━ 12s 74ms/step - accuracy: 0.8500 - loss: 0.3485
229/391 ━━━━━━━━━━━━━━━━━━━━ 11s 74ms/step - accuracy: 0.8500 - loss: 0.3485
230/391 ━━━━━━━━━━━━━━━━━━━━ 11s 74ms/step - accuracy: 0.8500 - loss: 0.3485
231/391 ━━━━━━━━━━━━━━━━━━━━ 11s 74ms/step - accuracy: 0.8500 - loss: 0.3485
232/391 ━━━━━━━━━━━━━━━━━━━━ 11s 74ms/step - accuracy: 0.8500 - loss: 0.3485
233/391 ━━━━━━━━━━━━━━━━━━━━ 11s 74ms/step - accuracy: 0.8500 - loss: 0.3484
234/391 ━━━━━━━━━━━━━━━━━━━━ 11s 74ms/step - accuracy: 0.8500 - loss: 0.3484
235/391 ━━━━━━━━━━━━━━━━━━━━ 11s 74ms/step - accuracy: 0.8500 - loss: 0.3484
236/391 ━━━━━━━━━━━━━━━━━━━━ 11s 74ms/step - accuracy: 0.8500 - loss: 0.3484
237/391 ━━━━━━━━━━━━━━━━━━━━ 11s 74ms/step - accuracy: 0.8500 - loss: 0.3484
238/391 ━━━━━━━━━━━━━━━━━━━━ 11s 74ms/step - accuracy: 0.8500 - loss: 0.3484
239/391 ━━━━━━━━━━━━━━━━━━━━ 11s 74ms/step - accuracy: 0.8500 - loss: 0.3484
240/391 ━━━━━━━━━━━━━━━━━━━━ 11s 74ms/step - accuracy: 0.8500 - loss: 0.3483
241/391 ━━━━━━━━━━━━━━━━━━━━ 11s 74ms/step - accuracy: 0.8500 - loss: 0.3483
242/391 ━━━━━━━━━━━━━━━━━━━━ 10s 74ms/step - accuracy: 0.8500 - loss: 0.3483
243/391 ━━━━━━━━━━━━━━━━━━━━ 10s 74ms/step - accuracy: 0.8500 - loss: 0.3483
244/391 ━━━━━━━━━━━━━━━━━━━━ 10s 74ms/step - accuracy: 0.8500 - loss: 0.3483
245/391 ━━━━━━━━━━━━━━━━━━━━ 10s 74ms/step - accuracy: 0.8500 - loss: 0.3483
246/391 ━━━━━━━━━━━━━━━━━━━━ 10s 74ms/step - accuracy: 0.8500 - loss: 0.3483
247/391 ━━━━━━━━━━━━━━━━━━━━ 10s 74ms/step - accuracy: 0.8500 - loss: 0.3483
248/391 ━━━━━━━━━━━━━━━━━━━━ 10s 74ms/step - accuracy: 0.8500 - loss: 0.3483
249/391 ━━━━━━━━━━━━━━━━━━━━ 10s 74ms/step - accuracy: 0.8500 - loss: 0.3483
250/391 ━━━━━━━━━━━━━━━━━━━━ 10s 74ms/step - accuracy: 0.8500 - loss: 0.3482
251/391 ━━━━━━━━━━━━━━━━━━━━ 10s 74ms/step - accuracy: 0.8499 - loss: 0.3482
252/391 ━━━━━━━━━━━━━━━━━━━━ 10s 74ms/step - accuracy: 0.8499 - loss: 0.3482
253/391 ━━━━━━━━━━━━━━━━━━━━ 10s 74ms/step - accuracy: 0.8499 - loss: 0.3482
254/391 ━━━━━━━━━━━━━━━━━━━━ 10s 74ms/step - accuracy: 0.8499 - loss: 0.3482
255/391 ━━━━━━━━━━━━━━━━━━━━ 10s 74ms/step - accuracy: 0.8499 - loss: 0.3482
256/391 ━━━━━━━━━━━━━━━━━━━━ 9s 74ms/step - accuracy: 0.8499 - loss: 0.3482 
257/391 ━━━━━━━━━━━━━━━━━━━━ 9s 74ms/step - accuracy: 0.8499 - loss: 0.3482
258/391 ━━━━━━━━━━━━━━━━━━━━ 9s 74ms/step - accuracy: 0.8499 - loss: 0.3482
259/391 ━━━━━━━━━━━━━━━━━━━━ 9s 73ms/step - accuracy: 0.8499 - loss: 0.3482
260/391 ━━━━━━━━━━━━━━━━━━━━ 9s 73ms/step - accuracy: 0.8499 - loss: 0.3481
261/391 ━━━━━━━━━━━━━━━━━━━━ 9s 73ms/step - accuracy: 0.8499 - loss: 0.3481
262/391 ━━━━━━━━━━━━━━━━━━━━ 9s 73ms/step - accuracy: 0.8499 - loss: 0.3481
263/391 ━━━━━━━━━━━━━━━━━━━━ 9s 73ms/step - accuracy: 0.8499 - loss: 0.3481
264/391 ━━━━━━━━━━━━━━━━━━━━ 9s 73ms/step - accuracy: 0.8499 - loss: 0.3481
265/391 ━━━━━━━━━━━━━━━━━━━━ 9s 73ms/step - accuracy: 0.8499 - loss: 0.3481
266/391 ━━━━━━━━━━━━━━━━━━━━ 9s 73ms/step - accuracy: 0.8499 - loss: 0.3481
267/391 ━━━━━━━━━━━━━━━━━━━━ 9s 73ms/step - accuracy: 0.8499 - loss: 0.3481
268/391 ━━━━━━━━━━━━━━━━━━━━ 9s 73ms/step - accuracy: 0.8499 - loss: 0.3481
269/391 ━━━━━━━━━━━━━━━━━━━━ 8s 73ms/step - accuracy: 0.8499 - loss: 0.3481
270/391 ━━━━━━━━━━━━━━━━━━━━ 8s 73ms/step - accuracy: 0.8499 - loss: 0.3480
271/391 ━━━━━━━━━━━━━━━━━━━━ 8s 73ms/step - accuracy: 0.8499 - loss: 0.3480
272/391 ━━━━━━━━━━━━━━━━━━━━ 8s 73ms/step - accuracy: 0.8499 - loss: 0.3480
273/391 ━━━━━━━━━━━━━━━━━━━━ 8s 73ms/step - accuracy: 0.8499 - loss: 0.3480
274/391 ━━━━━━━━━━━━━━━━━━━━ 8s 73ms/step - accuracy: 0.8499 - loss: 0.3480
275/391 ━━━━━━━━━━━━━━━━━━━━ 8s 73ms/step - accuracy: 0.8499 - loss: 0.3480
276/391 ━━━━━━━━━━━━━━━━━━━━ 8s 73ms/step - accuracy: 0.8499 - loss: 0.3480
277/391 ━━━━━━━━━━━━━━━━━━━━ 8s 73ms/step - accuracy: 0.8499 - loss: 0.3480
278/391 ━━━━━━━━━━━━━━━━━━━━ 8s 73ms/step - accuracy: 0.8499 - loss: 0.3480
279/391 ━━━━━━━━━━━━━━━━━━━━ 8s 73ms/step - accuracy: 0.8499 - loss: 0.3480
280/391 ━━━━━━━━━━━━━━━━━━━━ 8s 73ms/step - accuracy: 0.8499 - loss: 0.3480
281/391 ━━━━━━━━━━━━━━━━━━━━ 8s 73ms/step - accuracy: 0.8499 - loss: 0.3480
282/391 ━━━━━━━━━━━━━━━━━━━━ 7s 73ms/step - accuracy: 0.8499 - loss: 0.3480
283/391 ━━━━━━━━━━━━━━━━━━━━ 7s 73ms/step - accuracy: 0.8499 - loss: 0.3480
284/391 ━━━━━━━━━━━━━━━━━━━━ 7s 73ms/step - accuracy: 0.8499 - loss: 0.3480
285/391 ━━━━━━━━━━━━━━━━━━━━ 7s 73ms/step - accuracy: 0.8499 - loss: 0.3480
286/391 ━━━━━━━━━━━━━━━━━━━━ 7s 73ms/step - accuracy: 0.8499 - loss: 0.3480
287/391 ━━━━━━━━━━━━━━━━━━━━ 7s 73ms/step - accuracy: 0.8498 - loss: 0.3480
288/391 ━━━━━━━━━━━━━━━━━━━━ 7s 73ms/step - accuracy: 0.8498 - loss: 0.3479
289/391 ━━━━━━━━━━━━━━━━━━━━ 7s 73ms/step - accuracy: 0.8498 - loss: 0.3479
290/391 ━━━━━━━━━━━━━━━━━━━━ 7s 73ms/step - accuracy: 0.8498 - loss: 0.3479
291/391 ━━━━━━━━━━━━━━━━━━━━ 7s 73ms/step - accuracy: 0.8498 - loss: 0.3479
292/391 ━━━━━━━━━━━━━━━━━━━━ 7s 73ms/step - accuracy: 0.8498 - loss: 0.3479
293/391 ━━━━━━━━━━━━━━━━━━━━ 7s 73ms/step - accuracy: 0.8498 - loss: 0.3479
294/391 ━━━━━━━━━━━━━━━━━━━━ 7s 73ms/step - accuracy: 0.8498 - loss: 0.3479
295/391 ━━━━━━━━━━━━━━━━━━━━ 6s 73ms/step - accuracy: 0.8498 - loss: 0.3479
296/391 ━━━━━━━━━━━━━━━━━━━━ 6s 73ms/step - accuracy: 0.8498 - loss: 0.3479
297/391 ━━━━━━━━━━━━━━━━━━━━ 6s 73ms/step - accuracy: 0.8498 - loss: 0.3479
298/391 ━━━━━━━━━━━━━━━━━━━━ 6s 73ms/step - accuracy: 0.8498 - loss: 0.3479
299/391 ━━━━━━━━━━━━━━━━━━━━ 6s 73ms/step - accuracy: 0.8498 - loss: 0.3479
300/391 ━━━━━━━━━━━━━━━━━━━━ 6s 73ms/step - accuracy: 0.8498 - loss: 0.3479
301/391 ━━━━━━━━━━━━━━━━━━━━ 6s 73ms/step - accuracy: 0.8498 - loss: 0.3479
302/391 ━━━━━━━━━━━━━━━━━━━━ 6s 73ms/step - accuracy: 0.8498 - loss: 0.3479
303/391 ━━━━━━━━━━━━━━━━━━━━ 6s 73ms/step - accuracy: 0.8498 - loss: 0.3479
304/391 ━━━━━━━━━━━━━━━━━━━━ 6s 73ms/step - accuracy: 0.8498 - loss: 0.3479
305/391 ━━━━━━━━━━━━━━━━━━━━ 6s 73ms/step - accuracy: 0.8498 - loss: 0.3479
306/391 ━━━━━━━━━━━━━━━━━━━━ 6s 73ms/step - accuracy: 0.8498 - loss: 0.3479
307/391 ━━━━━━━━━━━━━━━━━━━━ 6s 73ms/step - accuracy: 0.8498 - loss: 0.3479
308/391 ━━━━━━━━━━━━━━━━━━━━ 6s 72ms/step - accuracy: 0.8498 - loss: 0.3479
309/391 ━━━━━━━━━━━━━━━━━━━━ 5s 73ms/step - accuracy: 0.8498 - loss: 0.3479
310/391 ━━━━━━━━━━━━━━━━━━━━ 5s 73ms/step - accuracy: 0.8497 - loss: 0.3479
311/391 ━━━━━━━━━━━━━━━━━━━━ 5s 73ms/step - accuracy: 0.8497 - loss: 0.3479
312/391 ━━━━━━━━━━━━━━━━━━━━ 5s 73ms/step - accuracy: 0.8497 - loss: 0.3479
313/391 ━━━━━━━━━━━━━━━━━━━━ 5s 73ms/step - accuracy: 0.8497 - loss: 0.3479
314/391 ━━━━━━━━━━━━━━━━━━━━ 5s 73ms/step - accuracy: 0.8497 - loss: 0.3479
315/391 ━━━━━━━━━━━━━━━━━━━━ 5s 73ms/step - accuracy: 0.8497 - loss: 0.3479
316/391 ━━━━━━━━━━━━━━━━━━━━ 5s 73ms/step - accuracy: 0.8497 - loss: 0.3479
317/391 ━━━━━━━━━━━━━━━━━━━━ 5s 73ms/step - accuracy: 0.8497 - loss: 0.3479
318/391 ━━━━━━━━━━━━━━━━━━━━ 5s 73ms/step - accuracy: 0.8497 - loss: 0.3479
319/391 ━━━━━━━━━━━━━━━━━━━━ 5s 73ms/step - accuracy: 0.8497 - loss: 0.3479
320/391 ━━━━━━━━━━━━━━━━━━━━ 5s 73ms/step - accuracy: 0.8497 - loss: 0.3479
321/391 ━━━━━━━━━━━━━━━━━━━━ 5s 73ms/step - accuracy: 0.8497 - loss: 0.3479
322/391 ━━━━━━━━━━━━━━━━━━━━ 5s 73ms/step - accuracy: 0.8497 - loss: 0.3479
323/391 ━━━━━━━━━━━━━━━━━━━━ 4s 73ms/step - accuracy: 0.8497 - loss: 0.3478
324/391 ━━━━━━━━━━━━━━━━━━━━ 4s 72ms/step - accuracy: 0.8497 - loss: 0.3478
325/391 ━━━━━━━━━━━━━━━━━━━━ 4s 72ms/step - accuracy: 0.8497 - loss: 0.3478
326/391 ━━━━━━━━━━━━━━━━━━━━ 4s 72ms/step - accuracy: 0.8497 - loss: 0.3478
327/391 ━━━━━━━━━━━━━━━━━━━━ 4s 72ms/step - accuracy: 0.8497 - loss: 0.3478
328/391 ━━━━━━━━━━━━━━━━━━━━ 4s 73ms/step - accuracy: 0.8497 - loss: 0.3478
329/391 ━━━━━━━━━━━━━━━━━━━━ 4s 72ms/step - accuracy: 0.8497 - loss: 0.3478
330/391 ━━━━━━━━━━━━━━━━━━━━ 4s 72ms/step - accuracy: 0.8497 - loss: 0.3478
331/391 ━━━━━━━━━━━━━━━━━━━━ 4s 72ms/step - accuracy: 0.8497 - loss: 0.3478
332/391 ━━━━━━━━━━━━━━━━━━━━ 4s 72ms/step - accuracy: 0.8497 - loss: 0.3478
333/391 ━━━━━━━━━━━━━━━━━━━━ 4s 72ms/step - accuracy: 0.8497 - loss: 0.3478
334/391 ━━━━━━━━━━━━━━━━━━━━ 4s 72ms/step - accuracy: 0.8497 - loss: 0.3478
335/391 ━━━━━━━━━━━━━━━━━━━━ 4s 72ms/step - accuracy: 0.8497 - loss: 0.3478
336/391 ━━━━━━━━━━━━━━━━━━━━ 3s 72ms/step - accuracy: 0.8497 - loss: 0.3478
337/391 ━━━━━━━━━━━━━━━━━━━━ 3s 72ms/step - accuracy: 0.8497 - loss: 0.3478
338/391 ━━━━━━━━━━━━━━━━━━━━ 3s 72ms/step - accuracy: 0.8497 - loss: 0.3478
339/391 ━━━━━━━━━━━━━━━━━━━━ 3s 72ms/step - accuracy: 0.8497 - loss: 0.3478
340/391 ━━━━━━━━━━━━━━━━━━━━ 3s 72ms/step - accuracy: 0.8497 - loss: 0.3478
341/391 ━━━━━━━━━━━━━━━━━━━━ 3s 72ms/step - accuracy: 0.8497 - loss: 0.3477
342/391 ━━━━━━━━━━━━━━━━━━━━ 3s 72ms/step - accuracy: 0.8497 - loss: 0.3477
343/391 ━━━━━━━━━━━━━━━━━━━━ 3s 72ms/step - accuracy: 0.8497 - loss: 0.3477
344/391 ━━━━━━━━━━━━━━━━━━━━ 3s 72ms/step - accuracy: 0.8497 - loss: 0.3477
345/391 ━━━━━━━━━━━━━━━━━━━━ 3s 72ms/step - accuracy: 0.8497 - loss: 0.3477
346/391 ━━━━━━━━━━━━━━━━━━━━ 3s 72ms/step - accuracy: 0.8497 - loss: 0.3477
347/391 ━━━━━━━━━━━━━━━━━━━━ 3s 72ms/step - accuracy: 0.8497 - loss: 0.3477
348/391 ━━━━━━━━━━━━━━━━━━━━ 3s 72ms/step - accuracy: 0.8497 - loss: 0.3477
349/391 ━━━━━━━━━━━━━━━━━━━━ 3s 72ms/step - accuracy: 0.8497 - loss: 0.3477
350/391 ━━━━━━━━━━━━━━━━━━━━ 2s 72ms/step - accuracy: 0.8497 - loss: 0.3477
351/391 ━━━━━━━━━━━━━━━━━━━━ 2s 72ms/step - accuracy: 0.8497 - loss: 0.3477
352/391 ━━━━━━━━━━━━━━━━━━━━ 2s 72ms/step - accuracy: 0.8497 - loss: 0.3477
353/391 ━━━━━━━━━━━━━━━━━━━━ 2s 72ms/step - accuracy: 0.8497 - loss: 0.3477
354/391 ━━━━━━━━━━━━━━━━━━━━ 2s 72ms/step - accuracy: 0.8497 - loss: 0.3477
355/391 ━━━━━━━━━━━━━━━━━━━━ 2s 72ms/step - accuracy: 0.8497 - loss: 0.3477
356/391 ━━━━━━━━━━━━━━━━━━━━ 2s 72ms/step - accuracy: 0.8497 - loss: 0.3476
357/391 ━━━━━━━━━━━━━━━━━━━━ 2s 72ms/step - accuracy: 0.8497 - loss: 0.3476
358/391 ━━━━━━━━━━━━━━━━━━━━ 2s 72ms/step - accuracy: 0.8497 - loss: 0.3476
359/391 ━━━━━━━━━━━━━━━━━━━━ 2s 72ms/step - accuracy: 0.8497 - loss: 0.3476
360/391 ━━━━━━━━━━━━━━━━━━━━ 2s 72ms/step - accuracy: 0.8497 - loss: 0.3476
361/391 ━━━━━━━━━━━━━━━━━━━━ 2s 72ms/step - accuracy: 0.8497 - loss: 0.3476
362/391 ━━━━━━━━━━━━━━━━━━━━ 2s 72ms/step - accuracy: 0.8497 - loss: 0.3476
363/391 ━━━━━━━━━━━━━━━━━━━━ 2s 71ms/step - accuracy: 0.8497 - loss: 0.3476
364/391 ━━━━━━━━━━━━━━━━━━━━ 1s 71ms/step - accuracy: 0.8497 - loss: 0.3476
365/391 ━━━━━━━━━━━━━━━━━━━━ 1s 71ms/step - accuracy: 0.8497 - loss: 0.3476
366/391 ━━━━━━━━━━━━━━━━━━━━ 1s 71ms/step - accuracy: 0.8497 - loss: 0.3476
367/391 ━━━━━━━━━━━━━━━━━━━━ 1s 72ms/step - accuracy: 0.8497 - loss: 0.3476
368/391 ━━━━━━━━━━━━━━━━━━━━ 1s 72ms/step - accuracy: 0.8497 - loss: 0.3476
369/391 ━━━━━━━━━━━━━━━━━━━━ 1s 72ms/step - accuracy: 0.8497 - loss: 0.3476
370/391 ━━━━━━━━━━━━━━━━━━━━ 1s 71ms/step - accuracy: 0.8497 - loss: 0.3476
371/391 ━━━━━━━━━━━━━━━━━━━━ 1s 71ms/step - accuracy: 0.8497 - loss: 0.3476
372/391 ━━━━━━━━━━━━━━━━━━━━ 1s 72ms/step - accuracy: 0.8497 - loss: 0.3476
373/391 ━━━━━━━━━━━━━━━━━━━━ 1s 72ms/step - accuracy: 0.8497 - loss: 0.3476
374/391 ━━━━━━━━━━━━━━━━━━━━ 1s 72ms/step - accuracy: 0.8497 - loss: 0.3476
375/391 ━━━━━━━━━━━━━━━━━━━━ 1s 72ms/step - accuracy: 0.8497 - loss: 0.3476
376/391 ━━━━━━━━━━━━━━━━━━━━ 1s 72ms/step - accuracy: 0.8497 - loss: 0.3476
377/391 ━━━━━━━━━━━━━━━━━━━━ 1s 72ms/step - accuracy: 0.8497 - loss: 0.3476
378/391 ━━━━━━━━━━━━━━━━━━━━ 0s 72ms/step - accuracy: 0.8497 - loss: 0.3476
379/391 ━━━━━━━━━━━━━━━━━━━━ 0s 72ms/step - accuracy: 0.8497 - loss: 0.3476
380/391 ━━━━━━━━━━━━━━━━━━━━ 0s 72ms/step - accuracy: 0.8497 - loss: 0.3475
381/391 ━━━━━━━━━━━━━━━━━━━━ 0s 72ms/step - accuracy: 0.8497 - loss: 0.3475
382/391 ━━━━━━━━━━━━━━━━━━━━ 0s 72ms/step - accuracy: 0.8497 - loss: 0.3475
383/391 ━━━━━━━━━━━━━━━━━━━━ 0s 72ms/step - accuracy: 0.8497 - loss: 0.3475
384/391 ━━━━━━━━━━━━━━━━━━━━ 0s 72ms/step - accuracy: 0.8497 - loss: 0.3475
385/391 ━━━━━━━━━━━━━━━━━━━━ 0s 72ms/step - accuracy: 0.8497 - loss: 0.3475
386/391 ━━━━━━━━━━━━━━━━━━━━ 0s 72ms/step - accuracy: 0.8497 - loss: 0.3475
387/391 ━━━━━━━━━━━━━━━━━━━━ 0s 72ms/step - accuracy: 0.8497 - loss: 0.3475
388/391 ━━━━━━━━━━━━━━━━━━━━ 0s 72ms/step - accuracy: 0.8497 - loss: 0.3475
389/391 ━━━━━━━━━━━━━━━━━━━━ 0s 72ms/step - accuracy: 0.8497 - loss: 0.3475
390/391 ━━━━━━━━━━━━━━━━━━━━ 0s 72ms/step - accuracy: 0.8497 - loss: 0.3475
391/391 ━━━━━━━━━━━━━━━━━━━━ 0s 72ms/step - accuracy: 0.8497 - loss: 0.3475
391/391 ━━━━━━━━━━━━━━━━━━━━ 43s 110ms/step - accuracy: 0.8498 - loss: 0.3450 - val_accuracy: 0.8502 - val_loss: 0.3383
Epoch 4/5
  1/391 ━━━━━━━━━━━━━━━━━━━━ 1:52 288ms/step - accuracy: 0.8750 - loss: 0.3098
  2/391 ━━━━━━━━━━━━━━━━━━━━ 27s 70ms/step - accuracy: 0.8672 - loss: 0.3252  
  3/391 ━━━━━━━━━━━━━━━━━━━━ 24s 63ms/step - accuracy: 0.8681 - loss: 0.3260
  4/391 ━━━━━━━━━━━━━━━━━━━━ 29s 75ms/step - accuracy: 0.8678 - loss: 0.3241
  5/391 ━━━━━━━━━━━━━━━━━━━━ 30s 79ms/step - accuracy: 0.8693 - loss: 0.3204
  6/391 ━━━━━━━━━━━━━━━━━━━━ 30s 78ms/step - accuracy: 0.8702 - loss: 0.3186
  7/391 ━━━━━━━━━━━━━━━━━━━━ 30s 79ms/step - accuracy: 0.8700 - loss: 0.3179
  8/391 ━━━━━━━━━━━━━━━━━━━━ 30s 80ms/step - accuracy: 0.8698 - loss: 0.3173
  9/391 ━━━━━━━━━━━━━━━━━━━━ 30s 79ms/step - accuracy: 0.8698 - loss: 0.3170
 10/391 ━━━━━━━━━━━━━━━━━━━━ 29s 76ms/step - accuracy: 0.8699 - loss: 0.3166
 11/391 ━━━━━━━━━━━━━━━━━━━━ 28s 74ms/step - accuracy: 0.8701 - loss: 0.3162
 12/391 ━━━━━━━━━━━━━━━━━━━━ 27s 72ms/step - accuracy: 0.8704 - loss: 0.3158
 13/391 ━━━━━━━━━━━━━━━━━━━━ 26s 70ms/step - accuracy: 0.8706 - loss: 0.3154
 14/391 ━━━━━━━━━━━━━━━━━━━━ 26s 69ms/step - accuracy: 0.8705 - loss: 0.3157
 15/391 ━━━━━━━━━━━━━━━━━━━━ 25s 68ms/step - accuracy: 0.8704 - loss: 0.3159
 16/391 ━━━━━━━━━━━━━━━━━━━━ 25s 67ms/step - accuracy: 0.8703 - loss: 0.3162
 17/391 ━━━━━━━━━━━━━━━━━━━━ 24s 66ms/step - accuracy: 0.8699 - loss: 0.3169
 18/391 ━━━━━━━━━━━━━━━━━━━━ 24s 66ms/step - accuracy: 0.8696 - loss: 0.3175
 19/391 ━━━━━━━━━━━━━━━━━━━━ 24s 65ms/step - accuracy: 0.8695 - loss: 0.3175
 20/391 ━━━━━━━━━━━━━━━━━━━━ 23s 64ms/step - accuracy: 0.8692 - loss: 0.3176
 21/391 ━━━━━━━━━━━━━━━━━━━━ 23s 64ms/step - accuracy: 0.8691 - loss: 0.3176
 22/391 ━━━━━━━━━━━━━━━━━━━━ 23s 64ms/step - accuracy: 0.8690 - loss: 0.3174
 23/391 ━━━━━━━━━━━━━━━━━━━━ 23s 64ms/step - accuracy: 0.8687 - loss: 0.3176
 24/391 ━━━━━━━━━━━━━━━━━━━━ 23s 64ms/step - accuracy: 0.8685 - loss: 0.3178
 25/391 ━━━━━━━━━━━━━━━━━━━━ 23s 64ms/step - accuracy: 0.8681 - loss: 0.3184
 26/391 ━━━━━━━━━━━━━━━━━━━━ 23s 65ms/step - accuracy: 0.8679 - loss: 0.3188
 27/391 ━━━━━━━━━━━━━━━━━━━━ 24s 66ms/step - accuracy: 0.8677 - loss: 0.3191
 28/391 ━━━━━━━━━━━━━━━━━━━━ 24s 67ms/step - accuracy: 0.8676 - loss: 0.3194
 29/391 ━━━━━━━━━━━━━━━━━━━━ 24s 68ms/step - accuracy: 0.8674 - loss: 0.3196
 30/391 ━━━━━━━━━━━━━━━━━━━━ 25s 70ms/step - accuracy: 0.8673 - loss: 0.3198
 31/391 ━━━━━━━━━━━━━━━━━━━━ 24s 69ms/step - accuracy: 0.8672 - loss: 0.3200
 32/391 ━━━━━━━━━━━━━━━━━━━━ 24s 70ms/step - accuracy: 0.8671 - loss: 0.3202
 33/391 ━━━━━━━━━━━━━━━━━━━━ 24s 69ms/step - accuracy: 0.8670 - loss: 0.3203
 34/391 ━━━━━━━━━━━━━━━━━━━━ 24s 69ms/step - accuracy: 0.8669 - loss: 0.3205
 35/391 ━━━━━━━━━━━━━━━━━━━━ 24s 69ms/step - accuracy: 0.8668 - loss: 0.3206
 36/391 ━━━━━━━━━━━━━━━━━━━━ 24s 68ms/step - accuracy: 0.8667 - loss: 0.3208
 37/391 ━━━━━━━━━━━━━━━━━━━━ 24s 68ms/step - accuracy: 0.8666 - loss: 0.3208
 38/391 ━━━━━━━━━━━━━━━━━━━━ 24s 69ms/step - accuracy: 0.8666 - loss: 0.3207
 39/391 ━━━━━━━━━━━━━━━━━━━━ 24s 69ms/step - accuracy: 0.8666 - loss: 0.3207
 40/391 ━━━━━━━━━━━━━━━━━━━━ 24s 69ms/step - accuracy: 0.8667 - loss: 0.3206
 41/391 ━━━━━━━━━━━━━━━━━━━━ 24s 70ms/step - accuracy: 0.8667 - loss: 0.3205
 42/391 ━━━━━━━━━━━━━━━━━━━━ 24s 71ms/step - accuracy: 0.8667 - loss: 0.3205
 43/391 ━━━━━━━━━━━━━━━━━━━━ 24s 71ms/step - accuracy: 0.8667 - loss: 0.3204
 44/391 ━━━━━━━━━━━━━━━━━━━━ 24s 72ms/step - accuracy: 0.8667 - loss: 0.3205
 45/391 ━━━━━━━━━━━━━━━━━━━━ 24s 72ms/step - accuracy: 0.8667 - loss: 0.3204
 46/391 ━━━━━━━━━━━━━━━━━━━━ 25s 73ms/step - accuracy: 0.8667 - loss: 0.3205
 47/391 ━━━━━━━━━━━━━━━━━━━━ 24s 73ms/step - accuracy: 0.8667 - loss: 0.3204
 48/391 ━━━━━━━━━━━━━━━━━━━━ 24s 73ms/step - accuracy: 0.8667 - loss: 0.3204
 49/391 ━━━━━━━━━━━━━━━━━━━━ 24s 73ms/step - accuracy: 0.8667 - loss: 0.3204
 50/391 ━━━━━━━━━━━━━━━━━━━━ 24s 73ms/step - accuracy: 0.8667 - loss: 0.3203
 51/391 ━━━━━━━━━━━━━━━━━━━━ 24s 73ms/step - accuracy: 0.8667 - loss: 0.3203
 52/391 ━━━━━━━━━━━━━━━━━━━━ 24s 72ms/step - accuracy: 0.8667 - loss: 0.3203
 53/391 ━━━━━━━━━━━━━━━━━━━━ 24s 72ms/step - accuracy: 0.8667 - loss: 0.3203
 54/391 ━━━━━━━━━━━━━━━━━━━━ 24s 72ms/step - accuracy: 0.8668 - loss: 0.3203
 55/391 ━━━━━━━━━━━━━━━━━━━━ 24s 72ms/step - accuracy: 0.8668 - loss: 0.3203
 56/391 ━━━━━━━━━━━━━━━━━━━━ 23s 72ms/step - accuracy: 0.8668 - loss: 0.3203
 57/391 ━━━━━━━━━━━━━━━━━━━━ 23s 71ms/step - accuracy: 0.8669 - loss: 0.3203
 58/391 ━━━━━━━━━━━━━━━━━━━━ 23s 71ms/step - accuracy: 0.8670 - loss: 0.3202
 59/391 ━━━━━━━━━━━━━━━━━━━━ 23s 71ms/step - accuracy: 0.8670 - loss: 0.3202
 60/391 ━━━━━━━━━━━━━━━━━━━━ 23s 71ms/step - accuracy: 0.8671 - loss: 0.3201
 61/391 ━━━━━━━━━━━━━━━━━━━━ 23s 71ms/step - accuracy: 0.8672 - loss: 0.3200
 62/391 ━━━━━━━━━━━━━━━━━━━━ 23s 71ms/step - accuracy: 0.8672 - loss: 0.3200
 63/391 ━━━━━━━━━━━━━━━━━━━━ 23s 71ms/step - accuracy: 0.8672 - loss: 0.3199
 64/391 ━━━━━━━━━━━━━━━━━━━━ 23s 70ms/step - accuracy: 0.8673 - loss: 0.3199
 65/391 ━━━━━━━━━━━━━━━━━━━━ 22s 70ms/step - accuracy: 0.8673 - loss: 0.3198
 66/391 ━━━━━━━━━━━━━━━━━━━━ 22s 70ms/step - accuracy: 0.8674 - loss: 0.3197
 67/391 ━━━━━━━━━━━━━━━━━━━━ 22s 70ms/step - accuracy: 0.8674 - loss: 0.3196
 68/391 ━━━━━━━━━━━━━━━━━━━━ 22s 70ms/step - accuracy: 0.8675 - loss: 0.3195
 69/391 ━━━━━━━━━━━━━━━━━━━━ 22s 69ms/step - accuracy: 0.8675 - loss: 0.3195
 70/391 ━━━━━━━━━━━━━━━━━━━━ 22s 69ms/step - accuracy: 0.8676 - loss: 0.3194
 71/391 ━━━━━━━━━━━━━━━━━━━━ 22s 70ms/step - accuracy: 0.8676 - loss: 0.3193
 72/391 ━━━━━━━━━━━━━━━━━━━━ 22s 70ms/step - accuracy: 0.8677 - loss: 0.3192
 73/391 ━━━━━━━━━━━━━━━━━━━━ 22s 69ms/step - accuracy: 0.8677 - loss: 0.3191
 74/391 ━━━━━━━━━━━━━━━━━━━━ 22s 70ms/step - accuracy: 0.8678 - loss: 0.3190
 75/391 ━━━━━━━━━━━━━━━━━━━━ 22s 70ms/step - accuracy: 0.8678 - loss: 0.3189
 76/391 ━━━━━━━━━━━━━━━━━━━━ 22s 70ms/step - accuracy: 0.8679 - loss: 0.3188
 77/391 ━━━━━━━━━━━━━━━━━━━━ 21s 70ms/step - accuracy: 0.8679 - loss: 0.3188
 78/391 ━━━━━━━━━━━━━━━━━━━━ 21s 70ms/step - accuracy: 0.8680 - loss: 0.3187
 79/391 ━━━━━━━━━━━━━━━━━━━━ 21s 70ms/step - accuracy: 0.8680 - loss: 0.3187
 80/391 ━━━━━━━━━━━━━━━━━━━━ 21s 70ms/step - accuracy: 0.8680 - loss: 0.3186
 81/391 ━━━━━━━━━━━━━━━━━━━━ 21s 70ms/step - accuracy: 0.8681 - loss: 0.3186
 82/391 ━━━━━━━━━━━━━━━━━━━━ 21s 70ms/step - accuracy: 0.8681 - loss: 0.3185
 83/391 ━━━━━━━━━━━━━━━━━━━━ 21s 70ms/step - accuracy: 0.8682 - loss: 0.3185
 84/391 ━━━━━━━━━━━━━━━━━━━━ 21s 70ms/step - accuracy: 0.8682 - loss: 0.3184
 85/391 ━━━━━━━━━━━━━━━━━━━━ 21s 70ms/step - accuracy: 0.8682 - loss: 0.3184
 86/391 ━━━━━━━━━━━━━━━━━━━━ 21s 70ms/step - accuracy: 0.8682 - loss: 0.3184
 87/391 ━━━━━━━━━━━━━━━━━━━━ 21s 70ms/step - accuracy: 0.8683 - loss: 0.3183
 88/391 ━━━━━━━━━━━━━━━━━━━━ 21s 70ms/step - accuracy: 0.8683 - loss: 0.3183
 89/391 ━━━━━━━━━━━━━━━━━━━━ 21s 70ms/step - accuracy: 0.8683 - loss: 0.3182
 90/391 ━━━━━━━━━━━━━━━━━━━━ 20s 70ms/step - accuracy: 0.8684 - loss: 0.3182
 91/391 ━━━━━━━━━━━━━━━━━━━━ 20s 70ms/step - accuracy: 0.8684 - loss: 0.3181
 92/391 ━━━━━━━━━━━━━━━━━━━━ 20s 70ms/step - accuracy: 0.8684 - loss: 0.3180
 93/391 ━━━━━━━━━━━━━━━━━━━━ 20s 70ms/step - accuracy: 0.8685 - loss: 0.3180
 94/391 ━━━━━━━━━━━━━━━━━━━━ 20s 70ms/step - accuracy: 0.8685 - loss: 0.3179
 95/391 ━━━━━━━━━━━━━━━━━━━━ 20s 70ms/step - accuracy: 0.8685 - loss: 0.3178
 96/391 ━━━━━━━━━━━━━━━━━━━━ 20s 70ms/step - accuracy: 0.8686 - loss: 0.3177
 97/391 ━━━━━━━━━━━━━━━━━━━━ 20s 70ms/step - accuracy: 0.8686 - loss: 0.3176
 98/391 ━━━━━━━━━━━━━━━━━━━━ 20s 70ms/step - accuracy: 0.8687 - loss: 0.3175
 99/391 ━━━━━━━━━━━━━━━━━━━━ 20s 70ms/step - accuracy: 0.8687 - loss: 0.3174
100/391 ━━━━━━━━━━━━━━━━━━━━ 20s 71ms/step - accuracy: 0.8688 - loss: 0.3173
101/391 ━━━━━━━━━━━━━━━━━━━━ 20s 71ms/step - accuracy: 0.8688 - loss: 0.3172
102/391 ━━━━━━━━━━━━━━━━━━━━ 20s 70ms/step - accuracy: 0.8689 - loss: 0.3171
103/391 ━━━━━━━━━━━━━━━━━━━━ 20s 70ms/step - accuracy: 0.8689 - loss: 0.3170
104/391 ━━━━━━━━━━━━━━━━━━━━ 20s 70ms/step - accuracy: 0.8689 - loss: 0.3170
105/391 ━━━━━━━━━━━━━━━━━━━━ 20s 70ms/step - accuracy: 0.8690 - loss: 0.3169
106/391 ━━━━━━━━━━━━━━━━━━━━ 19s 70ms/step - accuracy: 0.8690 - loss: 0.3168
107/391 ━━━━━━━━━━━━━━━━━━━━ 19s 70ms/step - accuracy: 0.8690 - loss: 0.3167
108/391 ━━━━━━━━━━━━━━━━━━━━ 19s 70ms/step - accuracy: 0.8691 - loss: 0.3167
109/391 ━━━━━━━━━━━━━━━━━━━━ 19s 70ms/step - accuracy: 0.8691 - loss: 0.3166
110/391 ━━━━━━━━━━━━━━━━━━━━ 19s 70ms/step - accuracy: 0.8691 - loss: 0.3165
111/391 ━━━━━━━━━━━━━━━━━━━━ 19s 70ms/step - accuracy: 0.8692 - loss: 0.3165
112/391 ━━━━━━━━━━━━━━━━━━━━ 19s 70ms/step - accuracy: 0.8692 - loss: 0.3164
113/391 ━━━━━━━━━━━━━━━━━━━━ 19s 70ms/step - accuracy: 0.8692 - loss: 0.3163
114/391 ━━━━━━━━━━━━━━━━━━━━ 19s 70ms/step - accuracy: 0.8693 - loss: 0.3163
115/391 ━━━━━━━━━━━━━━━━━━━━ 19s 70ms/step - accuracy: 0.8693 - loss: 0.3162
116/391 ━━━━━━━━━━━━━━━━━━━━ 19s 70ms/step - accuracy: 0.8693 - loss: 0.3162
117/391 ━━━━━━━━━━━━━━━━━━━━ 19s 71ms/step - accuracy: 0.8693 - loss: 0.3161
118/391 ━━━━━━━━━━━━━━━━━━━━ 19s 71ms/step - accuracy: 0.8693 - loss: 0.3161
119/391 ━━━━━━━━━━━━━━━━━━━━ 19s 71ms/step - accuracy: 0.8693 - loss: 0.3161
120/391 ━━━━━━━━━━━━━━━━━━━━ 19s 71ms/step - accuracy: 0.8693 - loss: 0.3160
121/391 ━━━━━━━━━━━━━━━━━━━━ 19s 71ms/step - accuracy: 0.8693 - loss: 0.3160
122/391 ━━━━━━━━━━━━━━━━━━━━ 18s 70ms/step - accuracy: 0.8694 - loss: 0.3159
123/391 ━━━━━━━━━━━━━━━━━━━━ 18s 70ms/step - accuracy: 0.8694 - loss: 0.3159
124/391 ━━━━━━━━━━━━━━━━━━━━ 18s 70ms/step - accuracy: 0.8694 - loss: 0.3158
125/391 ━━━━━━━━━━━━━━━━━━━━ 18s 70ms/step - accuracy: 0.8694 - loss: 0.3158
126/391 ━━━━━━━━━━━━━━━━━━━━ 18s 70ms/step - accuracy: 0.8694 - loss: 0.3157
127/391 ━━━━━━━━━━━━━━━━━━━━ 18s 70ms/step - accuracy: 0.8694 - loss: 0.3157
128/391 ━━━━━━━━━━━━━━━━━━━━ 18s 70ms/step - accuracy: 0.8694 - loss: 0.3156
129/391 ━━━━━━━━━━━━━━━━━━━━ 18s 71ms/step - accuracy: 0.8694 - loss: 0.3156
130/391 ━━━━━━━━━━━━━━━━━━━━ 18s 70ms/step - accuracy: 0.8694 - loss: 0.3156
131/391 ━━━━━━━━━━━━━━━━━━━━ 18s 70ms/step - accuracy: 0.8694 - loss: 0.3155
132/391 ━━━━━━━━━━━━━━━━━━━━ 18s 70ms/step - accuracy: 0.8694 - loss: 0.3155
133/391 ━━━━━━━━━━━━━━━━━━━━ 18s 70ms/step - accuracy: 0.8695 - loss: 0.3154
134/391 ━━━━━━━━━━━━━━━━━━━━ 18s 71ms/step - accuracy: 0.8695 - loss: 0.3154
135/391 ━━━━━━━━━━━━━━━━━━━━ 18s 71ms/step - accuracy: 0.8695 - loss: 0.3153
136/391 ━━━━━━━━━━━━━━━━━━━━ 18s 71ms/step - accuracy: 0.8695 - loss: 0.3153
137/391 ━━━━━━━━━━━━━━━━━━━━ 17s 71ms/step - accuracy: 0.8695 - loss: 0.3152
138/391 ━━━━━━━━━━━━━━━━━━━━ 17s 71ms/step - accuracy: 0.8695 - loss: 0.3152
139/391 ━━━━━━━━━━━━━━━━━━━━ 17s 70ms/step - accuracy: 0.8695 - loss: 0.3151
140/391 ━━━━━━━━━━━━━━━━━━━━ 17s 70ms/step - accuracy: 0.8695 - loss: 0.3150
141/391 ━━━━━━━━━━━━━━━━━━━━ 17s 70ms/step - accuracy: 0.8695 - loss: 0.3150
142/391 ━━━━━━━━━━━━━━━━━━━━ 17s 70ms/step - accuracy: 0.8695 - loss: 0.3149
143/391 ━━━━━━━━━━━━━━━━━━━━ 17s 70ms/step - accuracy: 0.8695 - loss: 0.3149
144/391 ━━━━━━━━━━━━━━━━━━━━ 17s 70ms/step - accuracy: 0.8695 - loss: 0.3148
145/391 ━━━━━━━━━━━━━━━━━━━━ 17s 71ms/step - accuracy: 0.8695 - loss: 0.3148
146/391 ━━━━━━━━━━━━━━━━━━━━ 17s 71ms/step - accuracy: 0.8695 - loss: 0.3147
147/391 ━━━━━━━━━━━━━━━━━━━━ 17s 71ms/step - accuracy: 0.8695 - loss: 0.3147
148/391 ━━━━━━━━━━━━━━━━━━━━ 17s 71ms/step - accuracy: 0.8695 - loss: 0.3146
149/391 ━━━━━━━━━━━━━━━━━━━━ 17s 71ms/step - accuracy: 0.8695 - loss: 0.3146
150/391 ━━━━━━━━━━━━━━━━━━━━ 17s 71ms/step - accuracy: 0.8695 - loss: 0.3146
151/391 ━━━━━━━━━━━━━━━━━━━━ 17s 71ms/step - accuracy: 0.8695 - loss: 0.3145
152/391 ━━━━━━━━━━━━━━━━━━━━ 17s 71ms/step - accuracy: 0.8696 - loss: 0.3145
153/391 ━━━━━━━━━━━━━━━━━━━━ 17s 72ms/step - accuracy: 0.8696 - loss: 0.3145
154/391 ━━━━━━━━━━━━━━━━━━━━ 17s 72ms/step - accuracy: 0.8696 - loss: 0.3144
155/391 ━━━━━━━━━━━━━━━━━━━━ 16s 72ms/step - accuracy: 0.8696 - loss: 0.3144
156/391 ━━━━━━━━━━━━━━━━━━━━ 16s 72ms/step - accuracy: 0.8696 - loss: 0.3143
157/391 ━━━━━━━━━━━━━━━━━━━━ 16s 72ms/step - accuracy: 0.8696 - loss: 0.3143
158/391 ━━━━━━━━━━━━━━━━━━━━ 16s 72ms/step - accuracy: 0.8696 - loss: 0.3143
159/391 ━━━━━━━━━━━━━━━━━━━━ 16s 72ms/step - accuracy: 0.8696 - loss: 0.3142
160/391 ━━━━━━━━━━━━━━━━━━━━ 16s 72ms/step - accuracy: 0.8696 - loss: 0.3142
161/391 ━━━━━━━━━━━━━━━━━━━━ 16s 73ms/step - accuracy: 0.8696 - loss: 0.3142
162/391 ━━━━━━━━━━━━━━━━━━━━ 16s 73ms/step - accuracy: 0.8696 - loss: 0.3141
163/391 ━━━━━━━━━━━━━━━━━━━━ 16s 73ms/step - accuracy: 0.8696 - loss: 0.3141
164/391 ━━━━━━━━━━━━━━━━━━━━ 16s 73ms/step - accuracy: 0.8696 - loss: 0.3141
165/391 ━━━━━━━━━━━━━━━━━━━━ 16s 73ms/step - accuracy: 0.8696 - loss: 0.3140
166/391 ━━━━━━━━━━━━━━━━━━━━ 16s 73ms/step - accuracy: 0.8696 - loss: 0.3140
167/391 ━━━━━━━━━━━━━━━━━━━━ 16s 73ms/step - accuracy: 0.8696 - loss: 0.3140
168/391 ━━━━━━━━━━━━━━━━━━━━ 16s 73ms/step - accuracy: 0.8696 - loss: 0.3140
169/391 ━━━━━━━━━━━━━━━━━━━━ 16s 73ms/step - accuracy: 0.8696 - loss: 0.3139
170/391 ━━━━━━━━━━━━━━━━━━━━ 16s 73ms/step - accuracy: 0.8696 - loss: 0.3139
171/391 ━━━━━━━━━━━━━━━━━━━━ 16s 73ms/step - accuracy: 0.8696 - loss: 0.3139
172/391 ━━━━━━━━━━━━━━━━━━━━ 16s 73ms/step - accuracy: 0.8696 - loss: 0.3139
173/391 ━━━━━━━━━━━━━━━━━━━━ 16s 73ms/step - accuracy: 0.8696 - loss: 0.3138
174/391 ━━━━━━━━━━━━━━━━━━━━ 15s 73ms/step - accuracy: 0.8696 - loss: 0.3138
175/391 ━━━━━━━━━━━━━━━━━━━━ 15s 73ms/step - accuracy: 0.8696 - loss: 0.3138
176/391 ━━━━━━━━━━━━━━━━━━━━ 15s 73ms/step - accuracy: 0.8696 - loss: 0.3138
177/391 ━━━━━━━━━━━━━━━━━━━━ 15s 74ms/step - accuracy: 0.8696 - loss: 0.3137
178/391 ━━━━━━━━━━━━━━━━━━━━ 15s 74ms/step - accuracy: 0.8696 - loss: 0.3137
179/391 ━━━━━━━━━━━━━━━━━━━━ 15s 74ms/step - accuracy: 0.8696 - loss: 0.3137
180/391 ━━━━━━━━━━━━━━━━━━━━ 15s 74ms/step - accuracy: 0.8696 - loss: 0.3137
181/391 ━━━━━━━━━━━━━━━━━━━━ 15s 74ms/step - accuracy: 0.8696 - loss: 0.3137
182/391 ━━━━━━━━━━━━━━━━━━━━ 15s 74ms/step - accuracy: 0.8696 - loss: 0.3137
183/391 ━━━━━━━━━━━━━━━━━━━━ 15s 74ms/step - accuracy: 0.8696 - loss: 0.3137
184/391 ━━━━━━━━━━━━━━━━━━━━ 15s 74ms/step - accuracy: 0.8696 - loss: 0.3136
185/391 ━━━━━━━━━━━━━━━━━━━━ 15s 74ms/step - accuracy: 0.8696 - loss: 0.3136
186/391 ━━━━━━━━━━━━━━━━━━━━ 15s 74ms/step - accuracy: 0.8696 - loss: 0.3136
187/391 ━━━━━━━━━━━━━━━━━━━━ 15s 74ms/step - accuracy: 0.8696 - loss: 0.3136
188/391 ━━━━━━━━━━━━━━━━━━━━ 14s 74ms/step - accuracy: 0.8696 - loss: 0.3136
189/391 ━━━━━━━━━━━━━━━━━━━━ 14s 74ms/step - accuracy: 0.8696 - loss: 0.3136
190/391 ━━━━━━━━━━━━━━━━━━━━ 14s 74ms/step - accuracy: 0.8696 - loss: 0.3135
191/391 ━━━━━━━━━━━━━━━━━━━━ 14s 73ms/step - accuracy: 0.8696 - loss: 0.3135
192/391 ━━━━━━━━━━━━━━━━━━━━ 14s 74ms/step - accuracy: 0.8696 - loss: 0.3135
193/391 ━━━━━━━━━━━━━━━━━━━━ 14s 74ms/step - accuracy: 0.8696 - loss: 0.3135
194/391 ━━━━━━━━━━━━━━━━━━━━ 14s 73ms/step - accuracy: 0.8696 - loss: 0.3135
195/391 ━━━━━━━━━━━━━━━━━━━━ 14s 73ms/step - accuracy: 0.8695 - loss: 0.3135
196/391 ━━━━━━━━━━━━━━━━━━━━ 14s 73ms/step - accuracy: 0.8695 - loss: 0.3134
197/391 ━━━━━━━━━━━━━━━━━━━━ 14s 73ms/step - accuracy: 0.8695 - loss: 0.3134
198/391 ━━━━━━━━━━━━━━━━━━━━ 14s 73ms/step - accuracy: 0.8695 - loss: 0.3134
199/391 ━━━━━━━━━━━━━━━━━━━━ 14s 73ms/step - accuracy: 0.8695 - loss: 0.3134
200/391 ━━━━━━━━━━━━━━━━━━━━ 14s 73ms/step - accuracy: 0.8695 - loss: 0.3134
201/391 ━━━━━━━━━━━━━━━━━━━━ 13s 73ms/step - accuracy: 0.8695 - loss: 0.3134
202/391 ━━━━━━━━━━━━━━━━━━━━ 13s 73ms/step - accuracy: 0.8695 - loss: 0.3133
203/391 ━━━━━━━━━━━━━━━━━━━━ 13s 74ms/step - accuracy: 0.8695 - loss: 0.3133
204/391 ━━━━━━━━━━━━━━━━━━━━ 13s 74ms/step - accuracy: 0.8695 - loss: 0.3133
205/391 ━━━━━━━━━━━━━━━━━━━━ 13s 74ms/step - accuracy: 0.8695 - loss: 0.3133
206/391 ━━━━━━━━━━━━━━━━━━━━ 13s 74ms/step - accuracy: 0.8695 - loss: 0.3133
207/391 ━━━━━━━━━━━━━━━━━━━━ 13s 74ms/step - accuracy: 0.8695 - loss: 0.3133
208/391 ━━━━━━━━━━━━━━━━━━━━ 13s 74ms/step - accuracy: 0.8695 - loss: 0.3133
209/391 ━━━━━━━━━━━━━━━━━━━━ 13s 73ms/step - accuracy: 0.8695 - loss: 0.3133
210/391 ━━━━━━━━━━━━━━━━━━━━ 13s 73ms/step - accuracy: 0.8695 - loss: 0.3133
211/391 ━━━━━━━━━━━━━━━━━━━━ 13s 73ms/step - accuracy: 0.8695 - loss: 0.3133
212/391 ━━━━━━━━━━━━━━━━━━━━ 13s 73ms/step - accuracy: 0.8695 - loss: 0.3133
213/391 ━━━━━━━━━━━━━━━━━━━━ 13s 73ms/step - accuracy: 0.8695 - loss: 0.3133
214/391 ━━━━━━━━━━━━━━━━━━━━ 12s 73ms/step - accuracy: 0.8695 - loss: 0.3133
215/391 ━━━━━━━━━━━━━━━━━━━━ 12s 73ms/step - accuracy: 0.8694 - loss: 0.3133
216/391 ━━━━━━━━━━━━━━━━━━━━ 12s 73ms/step - accuracy: 0.8694 - loss: 0.3133
217/391 ━━━━━━━━━━━━━━━━━━━━ 12s 73ms/step - accuracy: 0.8694 - loss: 0.3132
218/391 ━━━━━━━━━━━━━━━━━━━━ 12s 73ms/step - accuracy: 0.8694 - loss: 0.3132
219/391 ━━━━━━━━━━━━━━━━━━━━ 12s 73ms/step - accuracy: 0.8694 - loss: 0.3132
220/391 ━━━━━━━━━━━━━━━━━━━━ 12s 73ms/step - accuracy: 0.8694 - loss: 0.3132
221/391 ━━━━━━━━━━━━━━━━━━━━ 12s 73ms/step - accuracy: 0.8694 - loss: 0.3132
222/391 ━━━━━━━━━━━━━━━━━━━━ 12s 74ms/step - accuracy: 0.8694 - loss: 0.3132
223/391 ━━━━━━━━━━━━━━━━━━━━ 12s 74ms/step - accuracy: 0.8694 - loss: 0.3132
224/391 ━━━━━━━━━━━━━━━━━━━━ 12s 74ms/step - accuracy: 0.8694 - loss: 0.3132
225/391 ━━━━━━━━━━━━━━━━━━━━ 12s 74ms/step - accuracy: 0.8694 - loss: 0.3132
226/391 ━━━━━━━━━━━━━━━━━━━━ 12s 74ms/step - accuracy: 0.8694 - loss: 0.3132
227/391 ━━━━━━━━━━━━━━━━━━━━ 12s 74ms/step - accuracy: 0.8694 - loss: 0.3132
228/391 ━━━━━━━━━━━━━━━━━━━━ 12s 74ms/step - accuracy: 0.8694 - loss: 0.3132
229/391 ━━━━━━━━━━━━━━━━━━━━ 11s 74ms/step - accuracy: 0.8694 - loss: 0.3132
230/391 ━━━━━━━━━━━━━━━━━━━━ 11s 74ms/step - accuracy: 0.8693 - loss: 0.3132
231/391 ━━━━━━━━━━━━━━━━━━━━ 11s 74ms/step - accuracy: 0.8693 - loss: 0.3132
232/391 ━━━━━━━━━━━━━━━━━━━━ 11s 74ms/step - accuracy: 0.8693 - loss: 0.3132
233/391 ━━━━━━━━━━━━━━━━━━━━ 11s 74ms/step - accuracy: 0.8693 - loss: 0.3132
234/391 ━━━━━━━━━━━━━━━━━━━━ 11s 74ms/step - accuracy: 0.8693 - loss: 0.3132
235/391 ━━━━━━━━━━━━━━━━━━━━ 11s 74ms/step - accuracy: 0.8693 - loss: 0.3132
236/391 ━━━━━━━━━━━━━━━━━━━━ 11s 74ms/step - accuracy: 0.8693 - loss: 0.3132
237/391 ━━━━━━━━━━━━━━━━━━━━ 11s 74ms/step - accuracy: 0.8693 - loss: 0.3132
238/391 ━━━━━━━━━━━━━━━━━━━━ 11s 74ms/step - accuracy: 0.8693 - loss: 0.3132
239/391 ━━━━━━━━━━━━━━━━━━━━ 11s 74ms/step - accuracy: 0.8693 - loss: 0.3132
240/391 ━━━━━━━━━━━━━━━━━━━━ 11s 74ms/step - accuracy: 0.8693 - loss: 0.3132
241/391 ━━━━━━━━━━━━━━━━━━━━ 11s 74ms/step - accuracy: 0.8693 - loss: 0.3132
242/391 ━━━━━━━━━━━━━━━━━━━━ 11s 74ms/step - accuracy: 0.8693 - loss: 0.3132
243/391 ━━━━━━━━━━━━━━━━━━━━ 10s 74ms/step - accuracy: 0.8693 - loss: 0.3132
244/391 ━━━━━━━━━━━━━━━━━━━━ 10s 74ms/step - accuracy: 0.8693 - loss: 0.3132
245/391 ━━━━━━━━━━━━━━━━━━━━ 10s 74ms/step - accuracy: 0.8693 - loss: 0.3132
246/391 ━━━━━━━━━━━━━━━━━━━━ 10s 74ms/step - accuracy: 0.8693 - loss: 0.3132
247/391 ━━━━━━━━━━━━━━━━━━━━ 10s 75ms/step - accuracy: 0.8693 - loss: 0.3132
248/391 ━━━━━━━━━━━━━━━━━━━━ 10s 75ms/step - accuracy: 0.8693 - loss: 0.3132
249/391 ━━━━━━━━━━━━━━━━━━━━ 10s 75ms/step - accuracy: 0.8693 - loss: 0.3132
250/391 ━━━━━━━━━━━━━━━━━━━━ 10s 75ms/step - accuracy: 0.8693 - loss: 0.3132
251/391 ━━━━━━━━━━━━━━━━━━━━ 10s 75ms/step - accuracy: 0.8692 - loss: 0.3132
252/391 ━━━━━━━━━━━━━━━━━━━━ 10s 75ms/step - accuracy: 0.8692 - loss: 0.3132
253/391 ━━━━━━━━━━━━━━━━━━━━ 10s 75ms/step - accuracy: 0.8692 - loss: 0.3132
254/391 ━━━━━━━━━━━━━━━━━━━━ 10s 75ms/step - accuracy: 0.8692 - loss: 0.3132
255/391 ━━━━━━━━━━━━━━━━━━━━ 10s 75ms/step - accuracy: 0.8692 - loss: 0.3132
256/391 ━━━━━━━━━━━━━━━━━━━━ 10s 74ms/step - accuracy: 0.8692 - loss: 0.3132
257/391 ━━━━━━━━━━━━━━━━━━━━ 9s 74ms/step - accuracy: 0.8692 - loss: 0.3132 
258/391 ━━━━━━━━━━━━━━━━━━━━ 9s 74ms/step - accuracy: 0.8692 - loss: 0.3132
259/391 ━━━━━━━━━━━━━━━━━━━━ 9s 74ms/step - accuracy: 0.8692 - loss: 0.3132
260/391 ━━━━━━━━━━━━━━━━━━━━ 9s 74ms/step - accuracy: 0.8692 - loss: 0.3132
261/391 ━━━━━━━━━━━━━━━━━━━━ 9s 74ms/step - accuracy: 0.8692 - loss: 0.3132
262/391 ━━━━━━━━━━━━━━━━━━━━ 9s 74ms/step - accuracy: 0.8692 - loss: 0.3132
263/391 ━━━━━━━━━━━━━━━━━━━━ 9s 74ms/step - accuracy: 0.8692 - loss: 0.3132
264/391 ━━━━━━━━━━━━━━━━━━━━ 9s 74ms/step - accuracy: 0.8692 - loss: 0.3132
265/391 ━━━━━━━━━━━━━━━━━━━━ 9s 74ms/step - accuracy: 0.8692 - loss: 0.3132
266/391 ━━━━━━━━━━━━━━━━━━━━ 9s 74ms/step - accuracy: 0.8692 - loss: 0.3132
267/391 ━━━━━━━━━━━━━━━━━━━━ 9s 74ms/step - accuracy: 0.8692 - loss: 0.3132
268/391 ━━━━━━━━━━━━━━━━━━━━ 9s 74ms/step - accuracy: 0.8692 - loss: 0.3132
269/391 ━━━━━━━━━━━━━━━━━━━━ 9s 74ms/step - accuracy: 0.8692 - loss: 0.3132
270/391 ━━━━━━━━━━━━━━━━━━━━ 8s 74ms/step - accuracy: 0.8692 - loss: 0.3132
271/391 ━━━━━━━━━━━━━━━━━━━━ 8s 74ms/step - accuracy: 0.8692 - loss: 0.3132
272/391 ━━━━━━━━━━━━━━━━━━━━ 8s 74ms/step - accuracy: 0.8692 - loss: 0.3132
273/391 ━━━━━━━━━━━━━━━━━━━━ 8s 74ms/step - accuracy: 0.8692 - loss: 0.3132
274/391 ━━━━━━━━━━━━━━━━━━━━ 8s 74ms/step - accuracy: 0.8691 - loss: 0.3132
275/391 ━━━━━━━━━━━━━━━━━━━━ 8s 74ms/step - accuracy: 0.8691 - loss: 0.3132
276/391 ━━━━━━━━━━━━━━━━━━━━ 8s 74ms/step - accuracy: 0.8691 - loss: 0.3132
277/391 ━━━━━━━━━━━━━━━━━━━━ 8s 74ms/step - accuracy: 0.8691 - loss: 0.3132
278/391 ━━━━━━━━━━━━━━━━━━━━ 8s 74ms/step - accuracy: 0.8691 - loss: 0.3132
279/391 ━━━━━━━━━━━━━━━━━━━━ 8s 74ms/step - accuracy: 0.8691 - loss: 0.3132
280/391 ━━━━━━━━━━━━━━━━━━━━ 8s 74ms/step - accuracy: 0.8691 - loss: 0.3132
281/391 ━━━━━━━━━━━━━━━━━━━━ 8s 74ms/step - accuracy: 0.8691 - loss: 0.3132
282/391 ━━━━━━━━━━━━━━━━━━━━ 8s 74ms/step - accuracy: 0.8691 - loss: 0.3132
283/391 ━━━━━━━━━━━━━━━━━━━━ 7s 74ms/step - accuracy: 0.8691 - loss: 0.3132
284/391 ━━━━━━━━━━━━━━━━━━━━ 7s 74ms/step - accuracy: 0.8691 - loss: 0.3132
285/391 ━━━━━━━━━━━━━━━━━━━━ 7s 74ms/step - accuracy: 0.8691 - loss: 0.3132
286/391 ━━━━━━━━━━━━━━━━━━━━ 7s 74ms/step - accuracy: 0.8691 - loss: 0.3132
287/391 ━━━━━━━━━━━━━━━━━━━━ 7s 74ms/step - accuracy: 0.8691 - loss: 0.3132
288/391 ━━━━━━━━━━━━━━━━━━━━ 7s 74ms/step - accuracy: 0.8691 - loss: 0.3132
289/391 ━━━━━━━━━━━━━━━━━━━━ 7s 74ms/step - accuracy: 0.8691 - loss: 0.3132
290/391 ━━━━━━━━━━━━━━━━━━━━ 7s 74ms/step - accuracy: 0.8691 - loss: 0.3132
291/391 ━━━━━━━━━━━━━━━━━━━━ 7s 74ms/step - accuracy: 0.8690 - loss: 0.3132
292/391 ━━━━━━━━━━━━━━━━━━━━ 7s 74ms/step - accuracy: 0.8690 - loss: 0.3132
293/391 ━━━━━━━━━━━━━━━━━━━━ 7s 74ms/step - accuracy: 0.8690 - loss: 0.3132
294/391 ━━━━━━━━━━━━━━━━━━━━ 7s 74ms/step - accuracy: 0.8690 - loss: 0.3132
295/391 ━━━━━━━━━━━━━━━━━━━━ 7s 74ms/step - accuracy: 0.8690 - loss: 0.3133
296/391 ━━━━━━━━━━━━━━━━━━━━ 7s 74ms/step - accuracy: 0.8690 - loss: 0.3133
297/391 ━━━━━━━━━━━━━━━━━━━━ 6s 74ms/step - accuracy: 0.8690 - loss: 0.3133
298/391 ━━━━━━━━━━━━━━━━━━━━ 6s 74ms/step - accuracy: 0.8690 - loss: 0.3133
299/391 ━━━━━━━━━━━━━━━━━━━━ 6s 74ms/step - accuracy: 0.8690 - loss: 0.3133
300/391 ━━━━━━━━━━━━━━━━━━━━ 6s 74ms/step - accuracy: 0.8690 - loss: 0.3133
301/391 ━━━━━━━━━━━━━━━━━━━━ 6s 73ms/step - accuracy: 0.8690 - loss: 0.3133
302/391 ━━━━━━━━━━━━━━━━━━━━ 6s 73ms/step - accuracy: 0.8689 - loss: 0.3133
303/391 ━━━━━━━━━━━━━━━━━━━━ 6s 74ms/step - accuracy: 0.8689 - loss: 0.3133
304/391 ━━━━━━━━━━━━━━━━━━━━ 6s 74ms/step - accuracy: 0.8689 - loss: 0.3133
305/391 ━━━━━━━━━━━━━━━━━━━━ 6s 73ms/step - accuracy: 0.8689 - loss: 0.3133
306/391 ━━━━━━━━━━━━━━━━━━━━ 6s 74ms/step - accuracy: 0.8689 - loss: 0.3134
307/391 ━━━━━━━━━━━━━━━━━━━━ 6s 74ms/step - accuracy: 0.8689 - loss: 0.3134
308/391 ━━━━━━━━━━━━━━━━━━━━ 6s 74ms/step - accuracy: 0.8689 - loss: 0.3134
309/391 ━━━━━━━━━━━━━━━━━━━━ 6s 74ms/step - accuracy: 0.8689 - loss: 0.3134
310/391 ━━━━━━━━━━━━━━━━━━━━ 5s 74ms/step - accuracy: 0.8689 - loss: 0.3134
311/391 ━━━━━━━━━━━━━━━━━━━━ 5s 74ms/step - accuracy: 0.8689 - loss: 0.3134
312/391 ━━━━━━━━━━━━━━━━━━━━ 5s 73ms/step - accuracy: 0.8688 - loss: 0.3134
313/391 ━━━━━━━━━━━━━━━━━━━━ 5s 73ms/step - accuracy: 0.8688 - loss: 0.3134
314/391 ━━━━━━━━━━━━━━━━━━━━ 5s 73ms/step - accuracy: 0.8688 - loss: 0.3134
315/391 ━━━━━━━━━━━━━━━━━━━━ 5s 73ms/step - accuracy: 0.8688 - loss: 0.3134
316/391 ━━━━━━━━━━━━━━━━━━━━ 5s 73ms/step - accuracy: 0.8688 - loss: 0.3134
317/391 ━━━━━━━━━━━━━━━━━━━━ 5s 73ms/step - accuracy: 0.8688 - loss: 0.3134
318/391 ━━━━━━━━━━━━━━━━━━━━ 5s 73ms/step - accuracy: 0.8688 - loss: 0.3135
319/391 ━━━━━━━━━━━━━━━━━━━━ 5s 73ms/step - accuracy: 0.8688 - loss: 0.3135
320/391 ━━━━━━━━━━━━━━━━━━━━ 5s 73ms/step - accuracy: 0.8688 - loss: 0.3135
321/391 ━━━━━━━━━━━━━━━━━━━━ 5s 73ms/step - accuracy: 0.8688 - loss: 0.3135
322/391 ━━━━━━━━━━━━━━━━━━━━ 5s 73ms/step - accuracy: 0.8688 - loss: 0.3135
323/391 ━━━━━━━━━━━━━━━━━━━━ 4s 73ms/step - accuracy: 0.8687 - loss: 0.3135
324/391 ━━━━━━━━━━━━━━━━━━━━ 4s 73ms/step - accuracy: 0.8687 - loss: 0.3135
325/391 ━━━━━━━━━━━━━━━━━━━━ 4s 73ms/step - accuracy: 0.8687 - loss: 0.3135
326/391 ━━━━━━━━━━━━━━━━━━━━ 4s 73ms/step - accuracy: 0.8687 - loss: 0.3135
327/391 ━━━━━━━━━━━━━━━━━━━━ 4s 73ms/step - accuracy: 0.8687 - loss: 0.3135
328/391 ━━━━━━━━━━━━━━━━━━━━ 4s 73ms/step - accuracy: 0.8687 - loss: 0.3135
329/391 ━━━━━━━━━━━━━━━━━━━━ 4s 73ms/step - accuracy: 0.8687 - loss: 0.3135
330/391 ━━━━━━━━━━━━━━━━━━━━ 4s 73ms/step - accuracy: 0.8687 - loss: 0.3136
331/391 ━━━━━━━━━━━━━━━━━━━━ 4s 73ms/step - accuracy: 0.8687 - loss: 0.3136
332/391 ━━━━━━━━━━━━━━━━━━━━ 4s 73ms/step - accuracy: 0.8687 - loss: 0.3136
333/391 ━━━━━━━━━━━━━━━━━━━━ 4s 73ms/step - accuracy: 0.8687 - loss: 0.3136
334/391 ━━━━━━━━━━━━━━━━━━━━ 4s 73ms/step - accuracy: 0.8687 - loss: 0.3136
335/391 ━━━━━━━━━━━━━━━━━━━━ 4s 73ms/step - accuracy: 0.8687 - loss: 0.3136
336/391 ━━━━━━━━━━━━━━━━━━━━ 3s 73ms/step - accuracy: 0.8686 - loss: 0.3136
337/391 ━━━━━━━━━━━━━━━━━━━━ 3s 73ms/step - accuracy: 0.8686 - loss: 0.3136
338/391 ━━━━━━━━━━━━━━━━━━━━ 3s 73ms/step - accuracy: 0.8686 - loss: 0.3136
339/391 ━━━━━━━━━━━━━━━━━━━━ 3s 73ms/step - accuracy: 0.8686 - loss: 0.3136
340/391 ━━━━━━━━━━━━━━━━━━━━ 3s 72ms/step - accuracy: 0.8686 - loss: 0.3136
341/391 ━━━━━━━━━━━━━━━━━━━━ 3s 72ms/step - accuracy: 0.8686 - loss: 0.3137
342/391 ━━━━━━━━━━━━━━━━━━━━ 3s 72ms/step - accuracy: 0.8686 - loss: 0.3137
343/391 ━━━━━━━━━━━━━━━━━━━━ 3s 72ms/step - accuracy: 0.8686 - loss: 0.3137
344/391 ━━━━━━━━━━━━━━━━━━━━ 3s 73ms/step - accuracy: 0.8686 - loss: 0.3137
345/391 ━━━━━━━━━━━━━━━━━━━━ 3s 73ms/step - accuracy: 0.8686 - loss: 0.3137
346/391 ━━━━━━━━━━━━━━━━━━━━ 3s 73ms/step - accuracy: 0.8686 - loss: 0.3137
347/391 ━━━━━━━━━━━━━━━━━━━━ 3s 72ms/step - accuracy: 0.8686 - loss: 0.3137
348/391 ━━━━━━━━━━━━━━━━━━━━ 3s 73ms/step - accuracy: 0.8686 - loss: 0.3137
349/391 ━━━━━━━━━━━━━━━━━━━━ 3s 73ms/step - accuracy: 0.8686 - loss: 0.3137
350/391 ━━━━━━━━━━━━━━━━━━━━ 2s 72ms/step - accuracy: 0.8685 - loss: 0.3137
351/391 ━━━━━━━━━━━━━━━━━━━━ 2s 72ms/step - accuracy: 0.8685 - loss: 0.3137
352/391 ━━━━━━━━━━━━━━━━━━━━ 2s 72ms/step - accuracy: 0.8685 - loss: 0.3137
353/391 ━━━━━━━━━━━━━━━━━━━━ 2s 72ms/step - accuracy: 0.8685 - loss: 0.3138
354/391 ━━━━━━━━━━━━━━━━━━━━ 2s 72ms/step - accuracy: 0.8685 - loss: 0.3138
355/391 ━━━━━━━━━━━━━━━━━━━━ 2s 72ms/step - accuracy: 0.8685 - loss: 0.3138
356/391 ━━━━━━━━━━━━━━━━━━━━ 2s 72ms/step - accuracy: 0.8685 - loss: 0.3138
357/391 ━━━━━━━━━━━━━━━━━━━━ 2s 72ms/step - accuracy: 0.8685 - loss: 0.3138
358/391 ━━━━━━━━━━━━━━━━━━━━ 2s 72ms/step - accuracy: 0.8685 - loss: 0.3138
359/391 ━━━━━━━━━━━━━━━━━━━━ 2s 72ms/step - accuracy: 0.8685 - loss: 0.3138
360/391 ━━━━━━━━━━━━━━━━━━━━ 2s 72ms/step - accuracy: 0.8685 - loss: 0.3138
361/391 ━━━━━━━━━━━━━━━━━━━━ 2s 72ms/step - accuracy: 0.8685 - loss: 0.3138
362/391 ━━━━━━━━━━━━━━━━━━━━ 2s 72ms/step - accuracy: 0.8685 - loss: 0.3138
363/391 ━━━━━━━━━━━━━━━━━━━━ 2s 72ms/step - accuracy: 0.8685 - loss: 0.3138
364/391 ━━━━━━━━━━━━━━━━━━━━ 1s 72ms/step - accuracy: 0.8685 - loss: 0.3139
365/391 ━━━━━━━━━━━━━━━━━━━━ 1s 72ms/step - accuracy: 0.8684 - loss: 0.3139
366/391 ━━━━━━━━━━━━━━━━━━━━ 1s 72ms/step - accuracy: 0.8684 - loss: 0.3139
367/391 ━━━━━━━━━━━━━━━━━━━━ 1s 72ms/step - accuracy: 0.8684 - loss: 0.3139
368/391 ━━━━━━━━━━━━━━━━━━━━ 1s 72ms/step - accuracy: 0.8684 - loss: 0.3139
369/391 ━━━━━━━━━━━━━━━━━━━━ 1s 72ms/step - accuracy: 0.8684 - loss: 0.3139
370/391 ━━━━━━━━━━━━━━━━━━━━ 1s 72ms/step - accuracy: 0.8684 - loss: 0.3139
371/391 ━━━━━━━━━━━━━━━━━━━━ 1s 72ms/step - accuracy: 0.8684 - loss: 0.3139
372/391 ━━━━━━━━━━━━━━━━━━━━ 1s 72ms/step - accuracy: 0.8684 - loss: 0.3139
373/391 ━━━━━━━━━━━━━━━━━━━━ 1s 72ms/step - accuracy: 0.8684 - loss: 0.3139
374/391 ━━━━━━━━━━━━━━━━━━━━ 1s 72ms/step - accuracy: 0.8684 - loss: 0.3139
375/391 ━━━━━━━━━━━━━━━━━━━━ 1s 72ms/step - accuracy: 0.8684 - loss: 0.3139
376/391 ━━━━━━━━━━━━━━━━━━━━ 1s 72ms/step - accuracy: 0.8684 - loss: 0.3140
377/391 ━━━━━━━━━━━━━━━━━━━━ 1s 72ms/step - accuracy: 0.8684 - loss: 0.3140
378/391 ━━━━━━━━━━━━━━━━━━━━ 0s 72ms/step - accuracy: 0.8684 - loss: 0.3140
379/391 ━━━━━━━━━━━━━━━━━━━━ 0s 72ms/step - accuracy: 0.8684 - loss: 0.3140
380/391 ━━━━━━━━━━━━━━━━━━━━ 0s 72ms/step - accuracy: 0.8683 - loss: 0.3140
381/391 ━━━━━━━━━━━━━━━━━━━━ 0s 72ms/step - accuracy: 0.8683 - loss: 0.3140
382/391 ━━━━━━━━━━━━━━━━━━━━ 0s 72ms/step - accuracy: 0.8683 - loss: 0.3140
383/391 ━━━━━━━━━━━━━━━━━━━━ 0s 72ms/step - accuracy: 0.8683 - loss: 0.3140
384/391 ━━━━━━━━━━━━━━━━━━━━ 0s 72ms/step - accuracy: 0.8683 - loss: 0.3140
385/391 ━━━━━━━━━━━━━━━━━━━━ 0s 72ms/step - accuracy: 0.8683 - loss: 0.3140
386/391 ━━━━━━━━━━━━━━━━━━━━ 0s 72ms/step - accuracy: 0.8683 - loss: 0.3140
387/391 ━━━━━━━━━━━━━━━━━━━━ 0s 72ms/step - accuracy: 0.8683 - loss: 0.3141
388/391 ━━━━━━━━━━━━━━━━━━━━ 0s 72ms/step - accuracy: 0.8683 - loss: 0.3141
389/391 ━━━━━━━━━━━━━━━━━━━━ 0s 72ms/step - accuracy: 0.8683 - loss: 0.3141
390/391 ━━━━━━━━━━━━━━━━━━━━ 0s 72ms/step - accuracy: 0.8683 - loss: 0.3141
391/391 ━━━━━━━━━━━━━━━━━━━━ 0s 72ms/step - accuracy: 0.8683 - loss: 0.3141
391/391 ━━━━━━━━━━━━━━━━━━━━ 42s 108ms/step - accuracy: 0.8662 - loss: 0.3167 - val_accuracy: 0.8558 - val_loss: 0.3424
Epoch 5/5
  1/391 ━━━━━━━━━━━━━━━━━━━━ 1:38 254ms/step - accuracy: 0.9219 - loss: 0.2321
  2/391 ━━━━━━━━━━━━━━━━━━━━ 26s 68ms/step - accuracy: 0.9219 - loss: 0.2218  
  3/391 ━━━━━━━━━━━━━━━━━━━━ 30s 79ms/step - accuracy: 0.9219 - loss: 0.2253
  4/391 ━━━━━━━━━━━━━━━━━━━━ 28s 75ms/step - accuracy: 0.9180 - loss: 0.2280
  5/391 ━━━━━━━━━━━━━━━━━━━━ 29s 77ms/step - accuracy: 0.9156 - loss: 0.2337
  6/391 ━━━━━━━━━━━━━━━━━━━━ 30s 79ms/step - accuracy: 0.9141 - loss: 0.2354
  7/391 ━━━━━━━━━━━━━━━━━━━━ 30s 81ms/step - accuracy: 0.9129 - loss: 0.2366
  8/391 ━━━━━━━━━━━━━━━━━━━━ 31s 81ms/step - accuracy: 0.9119 - loss: 0.2369
  9/391 ━━━━━━━━━━━━━━━━━━━━ 30s 79ms/step - accuracy: 0.9110 - loss: 0.2381
 10/391 ━━━━━━━━━━━━━━━━━━━━ 29s 78ms/step - accuracy: 0.9092 - loss: 0.2401
 11/391 ━━━━━━━━━━━━━━━━━━━━ 30s 79ms/step - accuracy: 0.9079 - loss: 0.2414
 12/391 ━━━━━━━━━━━━━━━━━━━━ 30s 80ms/step - accuracy: 0.9070 - loss: 0.2426
 13/391 ━━━━━━━━━━━━━━━━━━━━ 30s 80ms/step - accuracy: 0.9058 - loss: 0.2437
 14/391 ━━━━━━━━━━━━━━━━━━━━ 30s 81ms/step - accuracy: 0.9046 - loss: 0.2448
 15/391 ━━━━━━━━━━━━━━━━━━━━ 30s 81ms/step - accuracy: 0.9037 - loss: 0.2457
 16/391 ━━━━━━━━━━━━━━━━━━━━ 30s 82ms/step - accuracy: 0.9029 - loss: 0.2467
 17/391 ━━━━━━━━━━━━━━━━━━━━ 30s 81ms/step - accuracy: 0.9023 - loss: 0.2478
 18/391 ━━━━━━━━━━━━━━━━━━━━ 29s 80ms/step - accuracy: 0.9016 - loss: 0.2492
 19/391 ━━━━━━━━━━━━━━━━━━━━ 29s 79ms/step - accuracy: 0.9008 - loss: 0.2506
 20/391 ━━━━━━━━━━━━━━━━━━━━ 28s 78ms/step - accuracy: 0.9001 - loss: 0.2519
 21/391 ━━━━━━━━━━━━━━━━━━━━ 28s 77ms/step - accuracy: 0.8995 - loss: 0.2532
 22/391 ━━━━━━━━━━━━━━━━━━━━ 28s 76ms/step - accuracy: 0.8991 - loss: 0.2543
 23/391 ━━━━━━━━━━━━━━━━━━━━ 28s 76ms/step - accuracy: 0.8987 - loss: 0.2552
 24/391 ━━━━━━━━━━━━━━━━━━━━ 28s 77ms/step - accuracy: 0.8984 - loss: 0.2560
 25/391 ━━━━━━━━━━━━━━━━━━━━ 28s 77ms/step - accuracy: 0.8982 - loss: 0.2566
 26/391 ━━━━━━━━━━━━━━━━━━━━ 27s 76ms/step - accuracy: 0.8979 - loss: 0.2573
 27/391 ━━━━━━━━━━━━━━━━━━━━ 27s 77ms/step - accuracy: 0.8977 - loss: 0.2579
 28/391 ━━━━━━━━━━━━━━━━━━━━ 27s 76ms/step - accuracy: 0.8975 - loss: 0.2584
 29/391 ━━━━━━━━━━━━━━━━━━━━ 27s 77ms/step - accuracy: 0.8974 - loss: 0.2587
 30/391 ━━━━━━━━━━━━━━━━━━━━ 27s 77ms/step - accuracy: 0.8972 - loss: 0.2591
 31/391 ━━━━━━━━━━━━━━━━━━━━ 27s 77ms/step - accuracy: 0.8971 - loss: 0.2594
 32/391 ━━━━━━━━━━━━━━━━━━━━ 27s 78ms/step - accuracy: 0.8970 - loss: 0.2595
 33/391 ━━━━━━━━━━━━━━━━━━━━ 27s 77ms/step - accuracy: 0.8970 - loss: 0.2596
 34/391 ━━━━━━━━━━━━━━━━━━━━ 27s 78ms/step - accuracy: 0.8970 - loss: 0.2596
 35/391 ━━━━━━━━━━━━━━━━━━━━ 27s 77ms/step - accuracy: 0.8970 - loss: 0.2596
 36/391 ━━━━━━━━━━━━━━━━━━━━ 27s 77ms/step - accuracy: 0.8970 - loss: 0.2595
 37/391 ━━━━━━━━━━━━━━━━━━━━ 27s 76ms/step - accuracy: 0.8970 - loss: 0.2595
 38/391 ━━━━━━━━━━━━━━━━━━━━ 26s 76ms/step - accuracy: 0.8970 - loss: 0.2596
 39/391 ━━━━━━━━━━━━━━━━━━━━ 26s 75ms/step - accuracy: 0.8970 - loss: 0.2596
 40/391 ━━━━━━━━━━━━━━━━━━━━ 26s 76ms/step - accuracy: 0.8970 - loss: 0.2596
 41/391 ━━━━━━━━━━━━━━━━━━━━ 26s 75ms/step - accuracy: 0.8969 - loss: 0.2596
 42/391 ━━━━━━━━━━━━━━━━━━━━ 26s 76ms/step - accuracy: 0.8969 - loss: 0.2596
 43/391 ━━━━━━━━━━━━━━━━━━━━ 26s 75ms/step - accuracy: 0.8969 - loss: 0.2596
 44/391 ━━━━━━━━━━━━━━━━━━━━ 26s 75ms/step - accuracy: 0.8970 - loss: 0.2595
 45/391 ━━━━━━━━━━━━━━━━━━━━ 26s 75ms/step - accuracy: 0.8970 - loss: 0.2594
 46/391 ━━━━━━━━━━━━━━━━━━━━ 26s 76ms/step - accuracy: 0.8971 - loss: 0.2593
 47/391 ━━━━━━━━━━━━━━━━━━━━ 25s 75ms/step - accuracy: 0.8971 - loss: 0.2591
 48/391 ━━━━━━━━━━━━━━━━━━━━ 25s 76ms/step - accuracy: 0.8972 - loss: 0.2589
 49/391 ━━━━━━━━━━━━━━━━━━━━ 25s 76ms/step - accuracy: 0.8973 - loss: 0.2588
 50/391 ━━━━━━━━━━━━━━━━━━━━ 25s 76ms/step - accuracy: 0.8973 - loss: 0.2586
 51/391 ━━━━━━━━━━━━━━━━━━━━ 25s 76ms/step - accuracy: 0.8973 - loss: 0.2585
 52/391 ━━━━━━━━━━━━━━━━━━━━ 25s 76ms/step - accuracy: 0.8973 - loss: 0.2585
 53/391 ━━━━━━━━━━━━━━━━━━━━ 25s 76ms/step - accuracy: 0.8973 - loss: 0.2584
 54/391 ━━━━━━━━━━━━━━━━━━━━ 25s 76ms/step - accuracy: 0.8973 - loss: 0.2584
 55/391 ━━━━━━━━━━━━━━━━━━━━ 25s 77ms/step - accuracy: 0.8972 - loss: 0.2585
 56/391 ━━━━━━━━━━━━━━━━━━━━ 25s 77ms/step - accuracy: 0.8972 - loss: 0.2585
 57/391 ━━━━━━━━━━━━━━━━━━━━ 25s 77ms/step - accuracy: 0.8972 - loss: 0.2585
 58/391 ━━━━━━━━━━━━━━━━━━━━ 25s 77ms/step - accuracy: 0.8972 - loss: 0.2585
 59/391 ━━━━━━━━━━━━━━━━━━━━ 25s 77ms/step - accuracy: 0.8971 - loss: 0.2584
 60/391 ━━━━━━━━━━━━━━━━━━━━ 25s 77ms/step - accuracy: 0.8971 - loss: 0.2584
 61/391 ━━━━━━━━━━━━━━━━━━━━ 25s 77ms/step - accuracy: 0.8971 - loss: 0.2583
 62/391 ━━━━━━━━━━━━━━━━━━━━ 25s 77ms/step - accuracy: 0.8971 - loss: 0.2583
 63/391 ━━━━━━━━━━━━━━━━━━━━ 25s 76ms/step - accuracy: 0.8971 - loss: 0.2582
 64/391 ━━━━━━━━━━━━━━━━━━━━ 24s 76ms/step - accuracy: 0.8971 - loss: 0.2582
 65/391 ━━━━━━━━━━━━━━━━━━━━ 24s 77ms/step - accuracy: 0.8971 - loss: 0.2581
 66/391 ━━━━━━━━━━━━━━━━━━━━ 24s 76ms/step - accuracy: 0.8971 - loss: 0.2581
 67/391 ━━━━━━━━━━━━━━━━━━━━ 24s 76ms/step - accuracy: 0.8971 - loss: 0.2581
 68/391 ━━━━━━━━━━━━━━━━━━━━ 24s 76ms/step - accuracy: 0.8971 - loss: 0.2581
 69/391 ━━━━━━━━━━━━━━━━━━━━ 24s 76ms/step - accuracy: 0.8970 - loss: 0.2581
 70/391 ━━━━━━━━━━━━━━━━━━━━ 24s 76ms/step - accuracy: 0.8970 - loss: 0.2581
 71/391 ━━━━━━━━━━━━━━━━━━━━ 24s 75ms/step - accuracy: 0.8970 - loss: 0.2581
 72/391 ━━━━━━━━━━━━━━━━━━━━ 23s 75ms/step - accuracy: 0.8969 - loss: 0.2581
 73/391 ━━━━━━━━━━━━━━━━━━━━ 23s 75ms/step - accuracy: 0.8969 - loss: 0.2581
 74/391 ━━━━━━━━━━━━━━━━━━━━ 23s 75ms/step - accuracy: 0.8969 - loss: 0.2582
 75/391 ━━━━━━━━━━━━━━━━━━━━ 23s 75ms/step - accuracy: 0.8968 - loss: 0.2581
 76/391 ━━━━━━━━━━━━━━━━━━━━ 23s 75ms/step - accuracy: 0.8968 - loss: 0.2582
 77/391 ━━━━━━━━━━━━━━━━━━━━ 23s 75ms/step - accuracy: 0.8967 - loss: 0.2582
 78/391 ━━━━━━━━━━━━━━━━━━━━ 23s 75ms/step - accuracy: 0.8967 - loss: 0.2582
 79/391 ━━━━━━━━━━━━━━━━━━━━ 23s 75ms/step - accuracy: 0.8966 - loss: 0.2582
 80/391 ━━━━━━━━━━━━━━━━━━━━ 23s 75ms/step - accuracy: 0.8966 - loss: 0.2582
 81/391 ━━━━━━━━━━━━━━━━━━━━ 23s 75ms/step - accuracy: 0.8966 - loss: 0.2583
 82/391 ━━━━━━━━━━━━━━━━━━━━ 23s 74ms/step - accuracy: 0.8965 - loss: 0.2583
 83/391 ━━━━━━━━━━━━━━━━━━━━ 22s 75ms/step - accuracy: 0.8965 - loss: 0.2583
 84/391 ━━━━━━━━━━━━━━━━━━━━ 22s 74ms/step - accuracy: 0.8965 - loss: 0.2583
 85/391 ━━━━━━━━━━━━━━━━━━━━ 22s 74ms/step - accuracy: 0.8965 - loss: 0.2583
 86/391 ━━━━━━━━━━━━━━━━━━━━ 22s 74ms/step - accuracy: 0.8964 - loss: 0.2584
 87/391 ━━━━━━━━━━━━━━━━━━━━ 22s 74ms/step - accuracy: 0.8964 - loss: 0.2584
 88/391 ━━━━━━━━━━━━━━━━━━━━ 22s 74ms/step - accuracy: 0.8964 - loss: 0.2584
 89/391 ━━━━━━━━━━━━━━━━━━━━ 22s 75ms/step - accuracy: 0.8963 - loss: 0.2584
 90/391 ━━━━━━━━━━━━━━━━━━━━ 22s 75ms/step - accuracy: 0.8963 - loss: 0.2585
 91/391 ━━━━━━━━━━━━━━━━━━━━ 22s 74ms/step - accuracy: 0.8962 - loss: 0.2586
 92/391 ━━━━━━━━━━━━━━━━━━━━ 22s 74ms/step - accuracy: 0.8962 - loss: 0.2586
 93/391 ━━━━━━━━━━━━━━━━━━━━ 22s 74ms/step - accuracy: 0.8961 - loss: 0.2587
 94/391 ━━━━━━━━━━━━━━━━━━━━ 22s 74ms/step - accuracy: 0.8961 - loss: 0.2587
 95/391 ━━━━━━━━━━━━━━━━━━━━ 21s 74ms/step - accuracy: 0.8960 - loss: 0.2588
 96/391 ━━━━━━━━━━━━━━━━━━━━ 21s 74ms/step - accuracy: 0.8960 - loss: 0.2589
 97/391 ━━━━━━━━━━━━━━━━━━━━ 21s 75ms/step - accuracy: 0.8959 - loss: 0.2589
 98/391 ━━━━━━━━━━━━━━━━━━━━ 21s 75ms/step - accuracy: 0.8959 - loss: 0.2590
 99/391 ━━━━━━━━━━━━━━━━━━━━ 21s 75ms/step - accuracy: 0.8958 - loss: 0.2591
100/391 ━━━━━━━━━━━━━━━━━━━━ 21s 75ms/step - accuracy: 0.8958 - loss: 0.2591
101/391 ━━━━━━━━━━━━━━━━━━━━ 21s 75ms/step - accuracy: 0.8957 - loss: 0.2592
102/391 ━━━━━━━━━━━━━━━━━━━━ 21s 75ms/step - accuracy: 0.8957 - loss: 0.2593
103/391 ━━━━━━━━━━━━━━━━━━━━ 21s 75ms/step - accuracy: 0.8956 - loss: 0.2593
104/391 ━━━━━━━━━━━━━━━━━━━━ 21s 75ms/step - accuracy: 0.8956 - loss: 0.2594
105/391 ━━━━━━━━━━━━━━━━━━━━ 21s 75ms/step - accuracy: 0.8955 - loss: 0.2595
106/391 ━━━━━━━━━━━━━━━━━━━━ 21s 75ms/step - accuracy: 0.8955 - loss: 0.2596
107/391 ━━━━━━━━━━━━━━━━━━━━ 21s 74ms/step - accuracy: 0.8954 - loss: 0.2597
108/391 ━━━━━━━━━━━━━━━━━━━━ 21s 74ms/step - accuracy: 0.8954 - loss: 0.2597
109/391 ━━━━━━━━━━━━━━━━━━━━ 20s 74ms/step - accuracy: 0.8953 - loss: 0.2598
110/391 ━━━━━━━━━━━━━━━━━━━━ 20s 74ms/step - accuracy: 0.8953 - loss: 0.2598
111/391 ━━━━━━━━━━━━━━━━━━━━ 20s 75ms/step - accuracy: 0.8952 - loss: 0.2599
112/391 ━━━━━━━━━━━━━━━━━━━━ 20s 75ms/step - accuracy: 0.8952 - loss: 0.2600
113/391 ━━━━━━━━━━━━━━━━━━━━ 20s 75ms/step - accuracy: 0.8952 - loss: 0.2600
114/391 ━━━━━━━━━━━━━━━━━━━━ 20s 75ms/step - accuracy: 0.8951 - loss: 0.2601
115/391 ━━━━━━━━━━━━━━━━━━━━ 20s 75ms/step - accuracy: 0.8951 - loss: 0.2601
116/391 ━━━━━━━━━━━━━━━━━━━━ 20s 75ms/step - accuracy: 0.8951 - loss: 0.2601
117/391 ━━━━━━━━━━━━━━━━━━━━ 20s 74ms/step - accuracy: 0.8950 - loss: 0.2602
118/391 ━━━━━━━━━━━━━━━━━━━━ 20s 74ms/step - accuracy: 0.8950 - loss: 0.2602
119/391 ━━━━━━━━━━━━━━━━━━━━ 20s 74ms/step - accuracy: 0.8950 - loss: 0.2603
120/391 ━━━━━━━━━━━━━━━━━━━━ 20s 74ms/step - accuracy: 0.8949 - loss: 0.2603
121/391 ━━━━━━━━━━━━━━━━━━━━ 20s 75ms/step - accuracy: 0.8949 - loss: 0.2604
122/391 ━━━━━━━━━━━━━━━━━━━━ 20s 75ms/step - accuracy: 0.8949 - loss: 0.2604
123/391 ━━━━━━━━━━━━━━━━━━━━ 20s 75ms/step - accuracy: 0.8948 - loss: 0.2605
124/391 ━━━━━━━━━━━━━━━━━━━━ 19s 75ms/step - accuracy: 0.8948 - loss: 0.2605
125/391 ━━━━━━━━━━━━━━━━━━━━ 19s 75ms/step - accuracy: 0.8948 - loss: 0.2605
126/391 ━━━━━━━━━━━━━━━━━━━━ 19s 74ms/step - accuracy: 0.8947 - loss: 0.2606
127/391 ━━━━━━━━━━━━━━━━━━━━ 19s 74ms/step - accuracy: 0.8947 - loss: 0.2606
128/391 ━━━━━━━━━━━━━━━━━━━━ 19s 74ms/step - accuracy: 0.8947 - loss: 0.2607
129/391 ━━━━━━━━━━━━━━━━━━━━ 19s 74ms/step - accuracy: 0.8946 - loss: 0.2607
130/391 ━━━━━━━━━━━━━━━━━━━━ 19s 74ms/step - accuracy: 0.8946 - loss: 0.2608
131/391 ━━━━━━━━━━━━━━━━━━━━ 19s 74ms/step - accuracy: 0.8946 - loss: 0.2608
132/391 ━━━━━━━━━━━━━━━━━━━━ 19s 74ms/step - accuracy: 0.8946 - loss: 0.2608
133/391 ━━━━━━━━━━━━━━━━━━━━ 19s 74ms/step - accuracy: 0.8945 - loss: 0.2609
134/391 ━━━━━━━━━━━━━━━━━━━━ 18s 74ms/step - accuracy: 0.8945 - loss: 0.2609
135/391 ━━━━━━━━━━━━━━━━━━━━ 18s 74ms/step - accuracy: 0.8945 - loss: 0.2609
136/391 ━━━━━━━━━━━━━━━━━━━━ 18s 74ms/step - accuracy: 0.8945 - loss: 0.2609
137/391 ━━━━━━━━━━━━━━━━━━━━ 18s 74ms/step - accuracy: 0.8944 - loss: 0.2610
138/391 ━━━━━━━━━━━━━━━━━━━━ 18s 74ms/step - accuracy: 0.8944 - loss: 0.2610
139/391 ━━━━━━━━━━━━━━━━━━━━ 18s 74ms/step - accuracy: 0.8944 - loss: 0.2610
140/391 ━━━━━━━━━━━━━━━━━━━━ 18s 74ms/step - accuracy: 0.8944 - loss: 0.2610
141/391 ━━━━━━━━━━━━━━━━━━━━ 18s 74ms/step - accuracy: 0.8944 - loss: 0.2610
142/391 ━━━━━━━━━━━━━━━━━━━━ 18s 74ms/step - accuracy: 0.8943 - loss: 0.2610
143/391 ━━━━━━━━━━━━━━━━━━━━ 18s 74ms/step - accuracy: 0.8943 - loss: 0.2611
144/391 ━━━━━━━━━━━━━━━━━━━━ 18s 74ms/step - accuracy: 0.8943 - loss: 0.2611
145/391 ━━━━━━━━━━━━━━━━━━━━ 18s 73ms/step - accuracy: 0.8943 - loss: 0.2611
146/391 ━━━━━━━━━━━━━━━━━━━━ 17s 73ms/step - accuracy: 0.8943 - loss: 0.2611
147/391 ━━━━━━━━━━━━━━━━━━━━ 17s 73ms/step - accuracy: 0.8942 - loss: 0.2611
148/391 ━━━━━━━━━━━━━━━━━━━━ 17s 73ms/step - accuracy: 0.8942 - loss: 0.2612
149/391 ━━━━━━━━━━━━━━━━━━━━ 17s 73ms/step - accuracy: 0.8942 - loss: 0.2612
150/391 ━━━━━━━━━━━━━━━━━━━━ 17s 73ms/step - accuracy: 0.8942 - loss: 0.2612
151/391 ━━━━━━━━━━━━━━━━━━━━ 17s 73ms/step - accuracy: 0.8942 - loss: 0.2612
152/391 ━━━━━━━━━━━━━━━━━━━━ 17s 73ms/step - accuracy: 0.8941 - loss: 0.2612
153/391 ━━━━━━━━━━━━━━━━━━━━ 17s 73ms/step - accuracy: 0.8941 - loss: 0.2613
154/391 ━━━━━━━━━━━━━━━━━━━━ 17s 73ms/step - accuracy: 0.8941 - loss: 0.2613
155/391 ━━━━━━━━━━━━━━━━━━━━ 17s 73ms/step - accuracy: 0.8941 - loss: 0.2613
156/391 ━━━━━━━━━━━━━━━━━━━━ 17s 72ms/step - accuracy: 0.8940 - loss: 0.2613
157/391 ━━━━━━━━━━━━━━━━━━━━ 16s 72ms/step - accuracy: 0.8940 - loss: 0.2613
158/391 ━━━━━━━━━━━━━━━━━━━━ 16s 72ms/step - accuracy: 0.8940 - loss: 0.2613
159/391 ━━━━━━━━━━━━━━━━━━━━ 16s 72ms/step - accuracy: 0.8940 - loss: 0.2614
160/391 ━━━━━━━━━━━━━━━━━━━━ 16s 72ms/step - accuracy: 0.8940 - loss: 0.2614
161/391 ━━━━━━━━━━━━━━━━━━━━ 16s 72ms/step - accuracy: 0.8939 - loss: 0.2614
162/391 ━━━━━━━━━━━━━━━━━━━━ 16s 72ms/step - accuracy: 0.8939 - loss: 0.2614
163/391 ━━━━━━━━━━━━━━━━━━━━ 16s 72ms/step - accuracy: 0.8939 - loss: 0.2615
164/391 ━━━━━━━━━━━━━━━━━━━━ 16s 72ms/step - accuracy: 0.8939 - loss: 0.2615
165/391 ━━━━━━━━━━━━━━━━━━━━ 16s 72ms/step - accuracy: 0.8938 - loss: 0.2615
166/391 ━━━━━━━━━━━━━━━━━━━━ 16s 72ms/step - accuracy: 0.8938 - loss: 0.2615
167/391 ━━━━━━━━━━━━━━━━━━━━ 16s 72ms/step - accuracy: 0.8938 - loss: 0.2616
168/391 ━━━━━━━━━━━━━━━━━━━━ 16s 72ms/step - accuracy: 0.8938 - loss: 0.2616
169/391 ━━━━━━━━━━━━━━━━━━━━ 16s 72ms/step - accuracy: 0.8937 - loss: 0.2616
170/391 ━━━━━━━━━━━━━━━━━━━━ 15s 72ms/step - accuracy: 0.8937 - loss: 0.2616
171/391 ━━━━━━━━━━━━━━━━━━━━ 15s 72ms/step - accuracy: 0.8937 - loss: 0.2617
172/391 ━━━━━━━━━━━━━━━━━━━━ 15s 72ms/step - accuracy: 0.8937 - loss: 0.2617
173/391 ━━━━━━━━━━━━━━━━━━━━ 15s 72ms/step - accuracy: 0.8937 - loss: 0.2617
174/391 ━━━━━━━━━━━━━━━━━━━━ 15s 72ms/step - accuracy: 0.8936 - loss: 0.2617
175/391 ━━━━━━━━━━━━━━━━━━━━ 15s 72ms/step - accuracy: 0.8936 - loss: 0.2618
176/391 ━━━━━━━━━━━━━━━━━━━━ 15s 72ms/step - accuracy: 0.8936 - loss: 0.2618
177/391 ━━━━━━━━━━━━━━━━━━━━ 15s 72ms/step - accuracy: 0.8936 - loss: 0.2618
178/391 ━━━━━━━━━━━━━━━━━━━━ 15s 72ms/step - accuracy: 0.8935 - loss: 0.2618
179/391 ━━━━━━━━━━━━━━━━━━━━ 15s 72ms/step - accuracy: 0.8935 - loss: 0.2619
180/391 ━━━━━━━━━━━━━━━━━━━━ 15s 72ms/step - accuracy: 0.8935 - loss: 0.2619
181/391 ━━━━━━━━━━━━━━━━━━━━ 15s 72ms/step - accuracy: 0.8935 - loss: 0.2619
182/391 ━━━━━━━━━━━━━━━━━━━━ 15s 72ms/step - accuracy: 0.8935 - loss: 0.2620
183/391 ━━━━━━━━━━━━━━━━━━━━ 15s 72ms/step - accuracy: 0.8934 - loss: 0.2620
184/391 ━━━━━━━━━━━━━━━━━━━━ 14s 72ms/step - accuracy: 0.8934 - loss: 0.2620
185/391 ━━━━━━━━━━━━━━━━━━━━ 14s 72ms/step - accuracy: 0.8934 - loss: 0.2620
186/391 ━━━━━━━━━━━━━━━━━━━━ 14s 72ms/step - accuracy: 0.8934 - loss: 0.2621
187/391 ━━━━━━━━━━━━━━━━━━━━ 14s 73ms/step - accuracy: 0.8933 - loss: 0.2621
188/391 ━━━━━━━━━━━━━━━━━━━━ 14s 73ms/step - accuracy: 0.8933 - loss: 0.2621
189/391 ━━━━━━━━━━━━━━━━━━━━ 14s 73ms/step - accuracy: 0.8933 - loss: 0.2622
190/391 ━━━━━━━━━━━━━━━━━━━━ 14s 73ms/step - accuracy: 0.8933 - loss: 0.2622
191/391 ━━━━━━━━━━━━━━━━━━━━ 14s 73ms/step - accuracy: 0.8932 - loss: 0.2622
192/391 ━━━━━━━━━━━━━━━━━━━━ 14s 73ms/step - accuracy: 0.8932 - loss: 0.2623
193/391 ━━━━━━━━━━━━━━━━━━━━ 14s 73ms/step - accuracy: 0.8932 - loss: 0.2623
194/391 ━━━━━━━━━━━━━━━━━━━━ 14s 73ms/step - accuracy: 0.8931 - loss: 0.2623
195/391 ━━━━━━━━━━━━━━━━━━━━ 14s 73ms/step - accuracy: 0.8931 - loss: 0.2624
196/391 ━━━━━━━━━━━━━━━━━━━━ 14s 73ms/step - accuracy: 0.8931 - loss: 0.2624
197/391 ━━━━━━━━━━━━━━━━━━━━ 14s 73ms/step - accuracy: 0.8931 - loss: 0.2625
198/391 ━━━━━━━━━━━━━━━━━━━━ 14s 73ms/step - accuracy: 0.8930 - loss: 0.2625
199/391 ━━━━━━━━━━━━━━━━━━━━ 13s 73ms/step - accuracy: 0.8930 - loss: 0.2625
200/391 ━━━━━━━━━━━━━━━━━━━━ 13s 73ms/step - accuracy: 0.8930 - loss: 0.2626
201/391 ━━━━━━━━━━━━━━━━━━━━ 13s 73ms/step - accuracy: 0.8929 - loss: 0.2626
202/391 ━━━━━━━━━━━━━━━━━━━━ 13s 73ms/step - accuracy: 0.8929 - loss: 0.2627
203/391 ━━━━━━━━━━━━━━━━━━━━ 13s 73ms/step - accuracy: 0.8929 - loss: 0.2627
204/391 ━━━━━━━━━━━━━━━━━━━━ 13s 73ms/step - accuracy: 0.8928 - loss: 0.2627
205/391 ━━━━━━━━━━━━━━━━━━━━ 13s 73ms/step - accuracy: 0.8928 - loss: 0.2628
206/391 ━━━━━━━━━━━━━━━━━━━━ 13s 73ms/step - accuracy: 0.8928 - loss: 0.2628
207/391 ━━━━━━━━━━━━━━━━━━━━ 13s 73ms/step - accuracy: 0.8928 - loss: 0.2629
208/391 ━━━━━━━━━━━━━━━━━━━━ 13s 73ms/step - accuracy: 0.8927 - loss: 0.2629
209/391 ━━━━━━━━━━━━━━━━━━━━ 13s 73ms/step - accuracy: 0.8927 - loss: 0.2629
210/391 ━━━━━━━━━━━━━━━━━━━━ 13s 73ms/step - accuracy: 0.8927 - loss: 0.2630
211/391 ━━━━━━━━━━━━━━━━━━━━ 13s 73ms/step - accuracy: 0.8927 - loss: 0.2630
212/391 ━━━━━━━━━━━━━━━━━━━━ 13s 73ms/step - accuracy: 0.8926 - loss: 0.2630
213/391 ━━━━━━━━━━━━━━━━━━━━ 12s 73ms/step - accuracy: 0.8926 - loss: 0.2631
214/391 ━━━━━━━━━━━━━━━━━━━━ 12s 73ms/step - accuracy: 0.8926 - loss: 0.2631
215/391 ━━━━━━━━━━━━━━━━━━━━ 12s 73ms/step - accuracy: 0.8926 - loss: 0.2631
216/391 ━━━━━━━━━━━━━━━━━━━━ 12s 73ms/step - accuracy: 0.8926 - loss: 0.2632
217/391 ━━━━━━━━━━━━━━━━━━━━ 12s 73ms/step - accuracy: 0.8925 - loss: 0.2632
218/391 ━━━━━━━━━━━━━━━━━━━━ 12s 73ms/step - accuracy: 0.8925 - loss: 0.2632
219/391 ━━━━━━━━━━━━━━━━━━━━ 12s 73ms/step - accuracy: 0.8925 - loss: 0.2633
220/391 ━━━━━━━━━━━━━━━━━━━━ 12s 73ms/step - accuracy: 0.8925 - loss: 0.2633
221/391 ━━━━━━━━━━━━━━━━━━━━ 12s 73ms/step - accuracy: 0.8924 - loss: 0.2633
222/391 ━━━━━━━━━━━━━━━━━━━━ 12s 73ms/step - accuracy: 0.8924 - loss: 0.2634
223/391 ━━━━━━━━━━━━━━━━━━━━ 12s 73ms/step - accuracy: 0.8924 - loss: 0.2634
224/391 ━━━━━━━━━━━━━━━━━━━━ 12s 73ms/step - accuracy: 0.8924 - loss: 0.2634
225/391 ━━━━━━━━━━━━━━━━━━━━ 12s 73ms/step - accuracy: 0.8923 - loss: 0.2635
226/391 ━━━━━━━━━━━━━━━━━━━━ 12s 73ms/step - accuracy: 0.8923 - loss: 0.2635
227/391 ━━━━━━━━━━━━━━━━━━━━ 11s 73ms/step - accuracy: 0.8923 - loss: 0.2635
228/391 ━━━━━━━━━━━━━━━━━━━━ 11s 73ms/step - accuracy: 0.8923 - loss: 0.2636
229/391 ━━━━━━━━━━━━━━━━━━━━ 11s 73ms/step - accuracy: 0.8922 - loss: 0.2636
230/391 ━━━━━━━━━━━━━━━━━━━━ 11s 73ms/step - accuracy: 0.8922 - loss: 0.2636
231/391 ━━━━━━━━━━━━━━━━━━━━ 11s 73ms/step - accuracy: 0.8922 - loss: 0.2637
232/391 ━━━━━━━━━━━━━━━━━━━━ 11s 73ms/step - accuracy: 0.8922 - loss: 0.2637
233/391 ━━━━━━━━━━━━━━━━━━━━ 11s 73ms/step - accuracy: 0.8922 - loss: 0.2637
234/391 ━━━━━━━━━━━━━━━━━━━━ 11s 73ms/step - accuracy: 0.8921 - loss: 0.2638
235/391 ━━━━━━━━━━━━━━━━━━━━ 11s 73ms/step - accuracy: 0.8921 - loss: 0.2638
236/391 ━━━━━━━━━━━━━━━━━━━━ 11s 73ms/step - accuracy: 0.8921 - loss: 0.2638
237/391 ━━━━━━━━━━━━━━━━━━━━ 11s 73ms/step - accuracy: 0.8921 - loss: 0.2639
238/391 ━━━━━━━━━━━━━━━━━━━━ 11s 73ms/step - accuracy: 0.8920 - loss: 0.2639
239/391 ━━━━━━━━━━━━━━━━━━━━ 11s 73ms/step - accuracy: 0.8920 - loss: 0.2640
240/391 ━━━━━━━━━━━━━━━━━━━━ 10s 73ms/step - accuracy: 0.8920 - loss: 0.2640
241/391 ━━━━━━━━━━━━━━━━━━━━ 10s 73ms/step - accuracy: 0.8920 - loss: 0.2640
242/391 ━━━━━━━━━━━━━━━━━━━━ 10s 73ms/step - accuracy: 0.8919 - loss: 0.2641
243/391 ━━━━━━━━━━━━━━━━━━━━ 10s 73ms/step - accuracy: 0.8919 - loss: 0.2641
244/391 ━━━━━━━━━━━━━━━━━━━━ 10s 73ms/step - accuracy: 0.8919 - loss: 0.2641
245/391 ━━━━━━━━━━━━━━━━━━━━ 10s 73ms/step - accuracy: 0.8919 - loss: 0.2642
246/391 ━━━━━━━━━━━━━━━━━━━━ 10s 73ms/step - accuracy: 0.8919 - loss: 0.2642
247/391 ━━━━━━━━━━━━━━━━━━━━ 10s 73ms/step - accuracy: 0.8918 - loss: 0.2642
248/391 ━━━━━━━━━━━━━━━━━━━━ 10s 73ms/step - accuracy: 0.8918 - loss: 0.2643
249/391 ━━━━━━━━━━━━━━━━━━━━ 10s 73ms/step - accuracy: 0.8918 - loss: 0.2643
250/391 ━━━━━━━━━━━━━━━━━━━━ 10s 73ms/step - accuracy: 0.8918 - loss: 0.2643
251/391 ━━━━━━━━━━━━━━━━━━━━ 10s 73ms/step - accuracy: 0.8918 - loss: 0.2644
252/391 ━━━━━━━━━━━━━━━━━━━━ 10s 73ms/step - accuracy: 0.8918 - loss: 0.2644
253/391 ━━━━━━━━━━━━━━━━━━━━ 10s 73ms/step - accuracy: 0.8917 - loss: 0.2644
254/391 ━━━━━━━━━━━━━━━━━━━━ 9s 73ms/step - accuracy: 0.8917 - loss: 0.2645 
255/391 ━━━━━━━━━━━━━━━━━━━━ 9s 73ms/step - accuracy: 0.8917 - loss: 0.2645
256/391 ━━━━━━━━━━━━━━━━━━━━ 9s 73ms/step - accuracy: 0.8917 - loss: 0.2645
257/391 ━━━━━━━━━━━━━━━━━━━━ 9s 73ms/step - accuracy: 0.8917 - loss: 0.2646
258/391 ━━━━━━━━━━━━━━━━━━━━ 9s 73ms/step - accuracy: 0.8916 - loss: 0.2646
259/391 ━━━━━━━━━━━━━━━━━━━━ 9s 73ms/step - accuracy: 0.8916 - loss: 0.2646
260/391 ━━━━━━━━━━━━━━━━━━━━ 9s 73ms/step - accuracy: 0.8916 - loss: 0.2647
261/391 ━━━━━━━━━━━━━━━━━━━━ 9s 73ms/step - accuracy: 0.8916 - loss: 0.2647
262/391 ━━━━━━━━━━━━━━━━━━━━ 9s 73ms/step - accuracy: 0.8916 - loss: 0.2648
263/391 ━━━━━━━━━━━━━━━━━━━━ 9s 73ms/step - accuracy: 0.8915 - loss: 0.2648
264/391 ━━━━━━━━━━━━━━━━━━━━ 9s 73ms/step - accuracy: 0.8915 - loss: 0.2648
265/391 ━━━━━━━━━━━━━━━━━━━━ 9s 73ms/step - accuracy: 0.8915 - loss: 0.2649
266/391 ━━━━━━━━━━━━━━━━━━━━ 9s 73ms/step - accuracy: 0.8915 - loss: 0.2649
267/391 ━━━━━━━━━━━━━━━━━━━━ 9s 73ms/step - accuracy: 0.8915 - loss: 0.2649
268/391 ━━━━━━━━━━━━━━━━━━━━ 8s 73ms/step - accuracy: 0.8915 - loss: 0.2650
269/391 ━━━━━━━━━━━━━━━━━━━━ 8s 73ms/step - accuracy: 0.8914 - loss: 0.2650
270/391 ━━━━━━━━━━━━━━━━━━━━ 8s 73ms/step - accuracy: 0.8914 - loss: 0.2650
271/391 ━━━━━━━━━━━━━━━━━━━━ 8s 73ms/step - accuracy: 0.8914 - loss: 0.2651
272/391 ━━━━━━━━━━━━━━━━━━━━ 8s 73ms/step - accuracy: 0.8914 - loss: 0.2651
273/391 ━━━━━━━━━━━━━━━━━━━━ 8s 73ms/step - accuracy: 0.8914 - loss: 0.2651
274/391 ━━━━━━━━━━━━━━━━━━━━ 8s 73ms/step - accuracy: 0.8914 - loss: 0.2652
275/391 ━━━━━━━━━━━━━━━━━━━━ 8s 73ms/step - accuracy: 0.8913 - loss: 0.2652
276/391 ━━━━━━━━━━━━━━━━━━━━ 8s 73ms/step - accuracy: 0.8913 - loss: 0.2652
277/391 ━━━━━━━━━━━━━━━━━━━━ 8s 73ms/step - accuracy: 0.8913 - loss: 0.2653
278/391 ━━━━━━━━━━━━━━━━━━━━ 8s 73ms/step - accuracy: 0.8913 - loss: 0.2653
279/391 ━━━━━━━━━━━━━━━━━━━━ 8s 73ms/step - accuracy: 0.8913 - loss: 0.2653
280/391 ━━━━━━━━━━━━━━━━━━━━ 8s 73ms/step - accuracy: 0.8913 - loss: 0.2654
281/391 ━━━━━━━━━━━━━━━━━━━━ 8s 73ms/step - accuracy: 0.8913 - loss: 0.2654
282/391 ━━━━━━━━━━━━━━━━━━━━ 7s 73ms/step - accuracy: 0.8912 - loss: 0.2654
283/391 ━━━━━━━━━━━━━━━━━━━━ 7s 73ms/step - accuracy: 0.8912 - loss: 0.2655
284/391 ━━━━━━━━━━━━━━━━━━━━ 7s 73ms/step - accuracy: 0.8912 - loss: 0.2655
285/391 ━━━━━━━━━━━━━━━━━━━━ 7s 73ms/step - accuracy: 0.8912 - loss: 0.2655
286/391 ━━━━━━━━━━━━━━━━━━━━ 7s 73ms/step - accuracy: 0.8912 - loss: 0.2655
287/391 ━━━━━━━━━━━━━━━━━━━━ 7s 73ms/step - accuracy: 0.8912 - loss: 0.2656
288/391 ━━━━━━━━━━━━━━━━━━━━ 7s 72ms/step - accuracy: 0.8911 - loss: 0.2656
289/391 ━━━━━━━━━━━━━━━━━━━━ 7s 73ms/step - accuracy: 0.8911 - loss: 0.2656
290/391 ━━━━━━━━━━━━━━━━━━━━ 7s 72ms/step - accuracy: 0.8911 - loss: 0.2657
291/391 ━━━━━━━━━━━━━━━━━━━━ 7s 72ms/step - accuracy: 0.8911 - loss: 0.2657
292/391 ━━━━━━━━━━━━━━━━━━━━ 7s 72ms/step - accuracy: 0.8911 - loss: 0.2657
293/391 ━━━━━━━━━━━━━━━━━━━━ 7s 72ms/step - accuracy: 0.8911 - loss: 0.2657
294/391 ━━━━━━━━━━━━━━━━━━━━ 7s 72ms/step - accuracy: 0.8911 - loss: 0.2658
295/391 ━━━━━━━━━━━━━━━━━━━━ 6s 72ms/step - accuracy: 0.8910 - loss: 0.2658
296/391 ━━━━━━━━━━━━━━━━━━━━ 6s 72ms/step - accuracy: 0.8910 - loss: 0.2658
297/391 ━━━━━━━━━━━━━━━━━━━━ 6s 72ms/step - accuracy: 0.8910 - loss: 0.2659
298/391 ━━━━━━━━━━━━━━━━━━━━ 6s 73ms/step - accuracy: 0.8910 - loss: 0.2659
299/391 ━━━━━━━━━━━━━━━━━━━━ 6s 72ms/step - accuracy: 0.8910 - loss: 0.2659
300/391 ━━━━━━━━━━━━━━━━━━━━ 6s 72ms/step - accuracy: 0.8909 - loss: 0.2660
301/391 ━━━━━━━━━━━━━━━━━━━━ 6s 72ms/step - accuracy: 0.8909 - loss: 0.2660
302/391 ━━━━━━━━━━━━━━━━━━━━ 6s 72ms/step - accuracy: 0.8909 - loss: 0.2660
303/391 ━━━━━━━━━━━━━━━━━━━━ 6s 72ms/step - accuracy: 0.8909 - loss: 0.2661
304/391 ━━━━━━━━━━━━━━━━━━━━ 6s 72ms/step - accuracy: 0.8909 - loss: 0.2661
305/391 ━━━━━━━━━━━━━━━━━━━━ 6s 72ms/step - accuracy: 0.8909 - loss: 0.2661
306/391 ━━━━━━━━━━━━━━━━━━━━ 6s 72ms/step - accuracy: 0.8908 - loss: 0.2661
307/391 ━━━━━━━━━━━━━━━━━━━━ 6s 72ms/step - accuracy: 0.8908 - loss: 0.2662
308/391 ━━━━━━━━━━━━━━━━━━━━ 5s 72ms/step - accuracy: 0.8908 - loss: 0.2662
309/391 ━━━━━━━━━━━━━━━━━━━━ 5s 72ms/step - accuracy: 0.8908 - loss: 0.2662
310/391 ━━━━━━━━━━━━━━━━━━━━ 5s 72ms/step - accuracy: 0.8908 - loss: 0.2663
311/391 ━━━━━━━━━━━━━━━━━━━━ 5s 72ms/step - accuracy: 0.8908 - loss: 0.2663
312/391 ━━━━━━━━━━━━━━━━━━━━ 5s 72ms/step - accuracy: 0.8907 - loss: 0.2663
313/391 ━━━━━━━━━━━━━━━━━━━━ 5s 72ms/step - accuracy: 0.8907 - loss: 0.2663
314/391 ━━━━━━━━━━━━━━━━━━━━ 5s 72ms/step - accuracy: 0.8907 - loss: 0.2664
315/391 ━━━━━━━━━━━━━━━━━━━━ 5s 72ms/step - accuracy: 0.8907 - loss: 0.2664
316/391 ━━━━━━━━━━━━━━━━━━━━ 5s 72ms/step - accuracy: 0.8907 - loss: 0.2664
317/391 ━━━━━━━━━━━━━━━━━━━━ 5s 72ms/step - accuracy: 0.8907 - loss: 0.2665
318/391 ━━━━━━━━━━━━━━━━━━━━ 5s 72ms/step - accuracy: 0.8906 - loss: 0.2665
319/391 ━━━━━━━━━━━━━━━━━━━━ 5s 72ms/step - accuracy: 0.8906 - loss: 0.2665
320/391 ━━━━━━━━━━━━━━━━━━━━ 5s 72ms/step - accuracy: 0.8906 - loss: 0.2665
321/391 ━━━━━━━━━━━━━━━━━━━━ 5s 72ms/step - accuracy: 0.8906 - loss: 0.2666
322/391 ━━━━━━━━━━━━━━━━━━━━ 4s 72ms/step - accuracy: 0.8906 - loss: 0.2666
323/391 ━━━━━━━━━━━━━━━━━━━━ 4s 72ms/step - accuracy: 0.8906 - loss: 0.2666
324/391 ━━━━━━━━━━━━━━━━━━━━ 4s 72ms/step - accuracy: 0.8906 - loss: 0.2666
325/391 ━━━━━━━━━━━━━━━━━━━━ 4s 72ms/step - accuracy: 0.8905 - loss: 0.2667
326/391 ━━━━━━━━━━━━━━━━━━━━ 4s 72ms/step - accuracy: 0.8905 - loss: 0.2667
327/391 ━━━━━━━━━━━━━━━━━━━━ 4s 72ms/step - accuracy: 0.8905 - loss: 0.2667
328/391 ━━━━━━━━━━━━━━━━━━━━ 4s 72ms/step - accuracy: 0.8905 - loss: 0.2668
329/391 ━━━━━━━━━━━━━━━━━━━━ 4s 72ms/step - accuracy: 0.8905 - loss: 0.2668
330/391 ━━━━━━━━━━━━━━━━━━━━ 4s 72ms/step - accuracy: 0.8905 - loss: 0.2668
331/391 ━━━━━━━━━━━━━━━━━━━━ 4s 72ms/step - accuracy: 0.8904 - loss: 0.2669
332/391 ━━━━━━━━━━━━━━━━━━━━ 4s 72ms/step - accuracy: 0.8904 - loss: 0.2669
333/391 ━━━━━━━━━━━━━━━━━━━━ 4s 72ms/step - accuracy: 0.8904 - loss: 0.2669
334/391 ━━━━━━━━━━━━━━━━━━━━ 4s 72ms/step - accuracy: 0.8904 - loss: 0.2669
335/391 ━━━━━━━━━━━━━━━━━━━━ 4s 72ms/step - accuracy: 0.8904 - loss: 0.2670
336/391 ━━━━━━━━━━━━━━━━━━━━ 3s 72ms/step - accuracy: 0.8903 - loss: 0.2670
337/391 ━━━━━━━━━━━━━━━━━━━━ 3s 72ms/step - accuracy: 0.8903 - loss: 0.2670
338/391 ━━━━━━━━━━━━━━━━━━━━ 3s 72ms/step - accuracy: 0.8903 - loss: 0.2671
339/391 ━━━━━━━━━━━━━━━━━━━━ 3s 72ms/step - accuracy: 0.8903 - loss: 0.2671
340/391 ━━━━━━━━━━━━━━━━━━━━ 3s 72ms/step - accuracy: 0.8903 - loss: 0.2671
341/391 ━━━━━━━━━━━━━━━━━━━━ 3s 72ms/step - accuracy: 0.8903 - loss: 0.2672
342/391 ━━━━━━━━━━━━━━━━━━━━ 3s 72ms/step - accuracy: 0.8902 - loss: 0.2672
343/391 ━━━━━━━━━━━━━━━━━━━━ 3s 72ms/step - accuracy: 0.8902 - loss: 0.2672
344/391 ━━━━━━━━━━━━━━━━━━━━ 3s 72ms/step - accuracy: 0.8902 - loss: 0.2673
345/391 ━━━━━━━━━━━━━━━━━━━━ 3s 72ms/step - accuracy: 0.8902 - loss: 0.2673
346/391 ━━━━━━━━━━━━━━━━━━━━ 3s 72ms/step - accuracy: 0.8902 - loss: 0.2673
347/391 ━━━━━━━━━━━━━━━━━━━━ 3s 72ms/step - accuracy: 0.8902 - loss: 0.2674
348/391 ━━━━━━━━━━━━━━━━━━━━ 3s 72ms/step - accuracy: 0.8901 - loss: 0.2674
349/391 ━━━━━━━━━━━━━━━━━━━━ 3s 72ms/step - accuracy: 0.8901 - loss: 0.2674
350/391 ━━━━━━━━━━━━━━━━━━━━ 2s 72ms/step - accuracy: 0.8901 - loss: 0.2674
351/391 ━━━━━━━━━━━━━━━━━━━━ 2s 72ms/step - accuracy: 0.8901 - loss: 0.2675
352/391 ━━━━━━━━━━━━━━━━━━━━ 2s 72ms/step - accuracy: 0.8901 - loss: 0.2675
353/391 ━━━━━━━━━━━━━━━━━━━━ 2s 72ms/step - accuracy: 0.8901 - loss: 0.2675
354/391 ━━━━━━━━━━━━━━━━━━━━ 2s 72ms/step - accuracy: 0.8900 - loss: 0.2676
355/391 ━━━━━━━━━━━━━━━━━━━━ 2s 71ms/step - accuracy: 0.8900 - loss: 0.2676
356/391 ━━━━━━━━━━━━━━━━━━━━ 2s 71ms/step - accuracy: 0.8900 - loss: 0.2676
357/391 ━━━━━━━━━━━━━━━━━━━━ 2s 71ms/step - accuracy: 0.8900 - loss: 0.2677
358/391 ━━━━━━━━━━━━━━━━━━━━ 2s 71ms/step - accuracy: 0.8900 - loss: 0.2677
359/391 ━━━━━━━━━━━━━━━━━━━━ 2s 71ms/step - accuracy: 0.8900 - loss: 0.2677
360/391 ━━━━━━━━━━━━━━━━━━━━ 2s 71ms/step - accuracy: 0.8899 - loss: 0.2678
361/391 ━━━━━━━━━━━━━━━━━━━━ 2s 71ms/step - accuracy: 0.8899 - loss: 0.2678
362/391 ━━━━━━━━━━━━━━━━━━━━ 2s 71ms/step - accuracy: 0.8899 - loss: 0.2678
363/391 ━━━━━━━━━━━━━━━━━━━━ 1s 71ms/step - accuracy: 0.8899 - loss: 0.2678
364/391 ━━━━━━━━━━━━━━━━━━━━ 1s 71ms/step - accuracy: 0.8899 - loss: 0.2679
365/391 ━━━━━━━━━━━━━━━━━━━━ 1s 71ms/step - accuracy: 0.8899 - loss: 0.2679
366/391 ━━━━━━━━━━━━━━━━━━━━ 1s 71ms/step - accuracy: 0.8898 - loss: 0.2679
367/391 ━━━━━━━━━━━━━━━━━━━━ 1s 71ms/step - accuracy: 0.8898 - loss: 0.2680
368/391 ━━━━━━━━━━━━━━━━━━━━ 1s 71ms/step - accuracy: 0.8898 - loss: 0.2680
369/391 ━━━━━━━━━━━━━━━━━━━━ 1s 71ms/step - accuracy: 0.8898 - loss: 0.2680
370/391 ━━━━━━━━━━━━━━━━━━━━ 1s 71ms/step - accuracy: 0.8898 - loss: 0.2680
371/391 ━━━━━━━━━━━━━━━━━━━━ 1s 71ms/step - accuracy: 0.8898 - loss: 0.2681
372/391 ━━━━━━━━━━━━━━━━━━━━ 1s 71ms/step - accuracy: 0.8898 - loss: 0.2681
373/391 ━━━━━━━━━━━━━━━━━━━━ 1s 71ms/step - accuracy: 0.8897 - loss: 0.2681
374/391 ━━━━━━━━━━━━━━━━━━━━ 1s 71ms/step - accuracy: 0.8897 - loss: 0.2682
375/391 ━━━━━━━━━━━━━━━━━━━━ 1s 71ms/step - accuracy: 0.8897 - loss: 0.2682
376/391 ━━━━━━━━━━━━━━━━━━━━ 1s 71ms/step - accuracy: 0.8897 - loss: 0.2682
377/391 ━━━━━━━━━━━━━━━━━━━━ 0s 71ms/step - accuracy: 0.8897 - loss: 0.2682
378/391 ━━━━━━━━━━━━━━━━━━━━ 0s 71ms/step - accuracy: 0.8897 - loss: 0.2683
379/391 ━━━━━━━━━━━━━━━━━━━━ 0s 71ms/step - accuracy: 0.8896 - loss: 0.2683
380/391 ━━━━━━━━━━━━━━━━━━━━ 0s 71ms/step - accuracy: 0.8896 - loss: 0.2683
381/391 ━━━━━━━━━━━━━━━━━━━━ 0s 71ms/step - accuracy: 0.8896 - loss: 0.2684
382/391 ━━━━━━━━━━━━━━━━━━━━ 0s 71ms/step - accuracy: 0.8896 - loss: 0.2684
383/391 ━━━━━━━━━━━━━━━━━━━━ 0s 71ms/step - accuracy: 0.8896 - loss: 0.2684
384/391 ━━━━━━━━━━━━━━━━━━━━ 0s 71ms/step - accuracy: 0.8896 - loss: 0.2685
385/391 ━━━━━━━━━━━━━━━━━━━━ 0s 71ms/step - accuracy: 0.8895 - loss: 0.2685
386/391 ━━━━━━━━━━━━━━━━━━━━ 0s 71ms/step - accuracy: 0.8895 - loss: 0.2685
387/391 ━━━━━━━━━━━━━━━━━━━━ 0s 71ms/step - accuracy: 0.8895 - loss: 0.2686
388/391 ━━━━━━━━━━━━━━━━━━━━ 0s 71ms/step - accuracy: 0.8895 - loss: 0.2686
389/391 ━━━━━━━━━━━━━━━━━━━━ 0s 71ms/step - accuracy: 0.8895 - loss: 0.2686
390/391 ━━━━━━━━━━━━━━━━━━━━ 0s 71ms/step - accuracy: 0.8895 - loss: 0.2686
391/391 ━━━━━━━━━━━━━━━━━━━━ 0s 71ms/step - accuracy: 0.8894 - loss: 0.2687
391/391 ━━━━━━━━━━━━━━━━━━━━ 42s 108ms/step - accuracy: 0.8833 - loss: 0.2800 - val_accuracy: 0.8482 - val_loss: 0.3511
<keras.src.callbacks.history.History at 0x768f5f7dc620>
lr, num_epochs = 0.01, 4
optimizer = nnx.Optimizer(net, optax.adam(lr), wrt=nnx.Param)
loss_fn = optax.softmax_cross_entropy_with_integer_labels

@nnx.jit
def train_step(net, optimizer, X, y):
    def compute_loss(model):
        logits = model(X)
        return loss_fn(logits, y).mean(), logits
    (loss, logits), grads = nnx.value_and_grad(
        compute_loss, has_aux=True)(net)
    optimizer.update(net, grads)
    return loss, logits

@nnx.jit
def eval_step(net, X):
    return net(X)

for epoch in range(num_epochs):
    loss_terms, train_correct_terms, num_train = [], [], 0
    for X, y in train_iter:
        l, logits = train_step(net, optimizer, X, y)
        loss_terms.append(l * len(y))
        train_correct_terms.append((logits.argmax(axis=-1) == y).sum())
        num_train += len(y)
    # Evaluate
    correct_terms, total = [], 0
    for X, y in test_iter:
        logits = eval_step(net, X)
        correct_terms.append((logits.argmax(axis=-1) == y).sum())
        total += len(y)
    loss_sum = float(jnp.stack(loss_terms).sum())
    train_correct = int(jnp.stack(train_correct_terms).sum())
    correct = int(jnp.stack(correct_terms).sum())
    print(f'epoch {epoch + 1}, loss {loss_sum / num_train:.3f}, '
          f'train acc {train_correct / num_train:.3f}, '
          f'test acc {correct / total:.3f}')
epoch 1, loss 0.627, train acc 0.632, test acc 0.796
epoch 2, loss 0.418, train acc 0.814, test acc 0.825
epoch 3, loss 0.364, train acc 0.844, test acc 0.847
epoch 4, loss 0.333, train acc 0.857, test acc 0.846
# Adam's per-step update is ~lr * normalized_step, so unlike SGD it
# doesn't need a 1/batch_size rescale to match PyTorch's lr=0.01
# under d2l.train_batch_ch13's trainer.step(1).
lr, num_epochs = 0.01, 5
trainer = gluon.Trainer(net.collect_params(), 'adam', {'learning_rate': lr})
loss = gluon.loss.SoftmaxCrossEntropyLoss()
d2l.train_ch13(net, train_iter, test_iter, loss, trainer, num_epochs, devices)
loss 0.349, train acc 0.845, test acc 0.812
535.7 examples/sec on [gpu(0)]

We define the following function to predict the sentiment of a text sequence using the trained model net.

def predict_sentiment(net, vocab, sequence):
    """Predict the sentiment of a text sequence."""
    sequence = torch.tensor(vocab[sequence.split()], device=d2l.try_gpu())
    label = torch.argmax(net(sequence.reshape(1, -1)), dim=1)
    return 'positive' if label == 1 else 'negative'

def predict_sentiment(net, vocab, sequence):
    """Predict the sentiment of a text sequence."""
    sequence = tf.constant(vocab[sequence.split()], dtype=tf.int32)
    sequence = tf.reshape(sequence, (1, -1))
    label = tf.argmax(net(sequence, training=False), axis=1)
    return 'positive' if int(label[0]) == 1 else 'negative'

def predict_sentiment(net, vocab, sequence):
    """Predict the sentiment of a text sequence."""
    sequence = jnp.array(vocab[sequence.split()])
    label = jnp.argmax(net(sequence.reshape(1, -1)), axis=1)
    return 'positive' if label == 1 else 'negative'

def predict_sentiment(net, vocab, sequence):
    """Predict the sentiment of a text sequence."""
    sequence = np.array(vocab[sequence.split()], ctx=d2l.try_gpu())
    label = np.argmax(net(sequence.reshape(1, -1)), axis=1)
    return 'positive' if label == 1 else 'negative'

Finally, let’s use the trained model to predict the sentiment for two simple sentences.

predict_sentiment(net, vocab, 'this movie is so great')
'positive'
predict_sentiment(net, vocab, 'this movie is so great')
'positive'
predict_sentiment(net, vocab, 'this movie is so great')
'positive'
predict_sentiment(net, vocab, 'this movie is so great')
'positive'
predict_sentiment(net, vocab, 'this movie is so bad')
'negative'
predict_sentiment(net, vocab, 'this movie is so bad')
'negative'
predict_sentiment(net, vocab, 'this movie is so bad')
'negative'
predict_sentiment(net, vocab, 'this movie is so bad')
'positive'

18.2.4 Summary

  • Pretrained word vectors can represent individual tokens in a text sequence.
  • Bidirectional RNNs can represent a text sequence, such as via the concatenation of its hidden states at the initial and final time steps. This single text representation can be transformed into categories using a fully connected layer.

18.2.5 Exercises

  1. Increase the number of epochs. Can you improve the training and testing accuracies? How about tuning other hyperparameters?
  2. Use larger pretrained word vectors, such as 300-dimensional GloVe embeddings. Does it improve classification accuracy?
  3. Can we improve the classification accuracy by using the spaCy tokenization? You need to install spaCy (pip install spacy) and install the English package (python -m spacy download en_core_web_sm). In the code, first, import spaCy (import spacy). Then, load the spaCy English package (spacy_en = spacy.load('en_core_web_sm')). Finally, define the function def tokenizer(text): return [tok.text for tok in spacy_en.tokenizer(text)] and replace the original tokenizer function. Note the different forms of phrase tokens in GloVe and spaCy. For example, the phrase token “new york” takes the form of “new-york” in GloVe and the form of “new york” after the spaCy tokenization.