from d2l import torch as d2l
import json
import multiprocessing
import torch
from torch import nn
import os18.7 Natural Language Inference: Fine-Tuning BERT
In earlier sections of this chapter, we have designed an attention-based architecture (in Section 18.5) for the natural language inference task on the SNLI dataset (as described in Section 18.4). Now we revisit this task by fine-tuning BERT. As discussed in Section 18.6, natural language inference is a sequence-level text pair classification problem, and fine-tuning BERT only requires an additional MLP-based architecture, as illustrated in Figure 18.7.1.
In this section, we will download a pretrained small version of BERT, then fine-tune it for natural language inference on the SNLI dataset.
from d2l import tensorflow as d2l
import tensorflow as tf
import keras
import numpy as np
import json
import multiprocessing
import osfrom d2l import jax as d2l
import jax
from jax import numpy as jnp
from flax import nnx
import optax
import numpy as np
import json
import osfrom d2l import mxnet as d2l
import json
import multiprocessing
from mxnet import gluon, np, npx
from mxnet.gluon import nn
import os
npx.set_np()18.7.1 Loading Pretrained BERT
We have explained how to pretrain BERT on the WikiText-2 dataset in Section 17.10 and Section 17.11 (note that the original BERT model is pretrained on much bigger corpora). As discussed in Section 17.11, the original BERT model has hundreds of millions of parameters. In the following, we provide two versions of pretrained BERT: “bert.base” is about as big as the original BERT base model that requires a lot of computational resources to fine-tune, while “bert.small” is a small version to facilitate demonstration.
d2l.DATA_HUB['bert.base'] = (d2l.DATA_URL + 'bert.base.torch.zip',
'225d66f04cae318b841a13d32af3acc165f253ac')
d2l.DATA_HUB['bert.small'] = (d2l.DATA_URL + 'bert.small.torch.zip',
'c72329e68a732bef0452e4b96a1c341c8910f81f')d2l.DATA_HUB['bert.base'] = (d2l.DATA_URL + 'bert.base.torch.zip',
'225d66f04cae318b841a13d32af3acc165f253ac')
d2l.DATA_HUB['bert.small'] = (d2l.DATA_URL + 'bert.small.torch.zip',
'c72329e68a732bef0452e4b96a1c341c8910f81f')
def _load_torch_state_dict(path):
"""Load a PyTorch state-dict file as {str: numpy.ndarray} without torch.
Works for files saved with ``torch.save(model.state_dict(), path)``
using pickle protocol 2 (the default for PyTorch <= 2.x CPU tensors).
"""
import pickle, struct, io
from collections import OrderedDict
dtype_info = {
'FloatStorage': (np.float32, 4), 'HalfStorage': (np.float16, 2),
'LongStorage': (np.int64, 8), 'IntStorage': (np.int32, 4),
'DoubleStorage': (np.float64, 8),
}
class _StorageRef:
__slots__ = ('dtype_name', 'key', 'location', 'size')
def __init__(self, dtype_name, key, location, size):
self.dtype_name = dtype_name; self.key = key
self.location = location; self.size = size
class _TensorRef:
__slots__ = ('storage', 'offset', 'size', 'stride')
def __init__(self, storage, offset, size, stride):
self.storage = storage; self.offset = offset
self.size = tuple(size); self.stride = tuple(stride)
class _StorageType:
__slots__ = ('name',)
def __init__(self, name): self.name = name
def __call__(self, _): return self
class _Unpickler(pickle.Unpickler):
def find_class(self, module, name):
if module == 'collections' and name == 'OrderedDict':
return OrderedDict
if module == 'torch._utils' and name == '_rebuild_tensor_v2':
return (lambda s, o, sz, st, *a, **k:
_TensorRef(s, o, sz, st))
if module == 'torch' and name in dtype_info:
return _StorageType(name)
return super().find_class(module, name)
def persistent_load(self, saved_id):
if isinstance(saved_id, tuple) and saved_id[0] == 'storage':
st = saved_id[1]
return _StorageRef(
st.name if isinstance(st, _StorageType) else 'FloatStorage',
saved_id[2], saved_id[3], saved_id[4])
raise RuntimeError(f'Unknown persistent id: {saved_id}')
with open(path, 'rb') as f:
content = f.read()
buf = io.BytesIO(content)
for _ in range(3): # skip magic, proto, sysinfo
_Unpickler(buf).load()
data = _Unpickler(buf).load() # OrderedDict of _TensorRef
storage_keys = _Unpickler(buf).load() # list of storage keys
pos = buf.tell()
key_dtype = {}
for tref in data.values():
if isinstance(tref, _TensorRef):
key_dtype[tref.storage.key] = tref.storage.dtype_name
storages = {}
for key in storage_keys:
dname = key_dtype.get(key, 'FloatStorage')
np_dt, esz = dtype_info[dname]
n = struct.unpack('<Q', content[pos:pos+8])[0]; pos += 8
storages[key] = np.frombuffer(content, np_dt, count=n, offset=pos)
pos += n * esz
result = OrderedDict()
for name, tref in data.items():
if isinstance(tref, _TensorRef):
s = storages[tref.storage.key]
ne = 1
for d in tref.size:
ne *= d
result[name] = s[tref.offset:tref.offset+ne].reshape(
tref.size).copy()
return resultd2l.DATA_HUB['bert.base'] = (d2l.DATA_URL + 'bert.base.torch.zip',
'225d66f04cae318b841a13d32af3acc165f253ac')
d2l.DATA_HUB['bert.small'] = (d2l.DATA_URL + 'bert.small.torch.zip',
'c72329e68a732bef0452e4b96a1c341c8910f81f')
def _load_torch_state_dict(path):
"""Load a PyTorch state-dict file as {str: numpy.ndarray} without torch.
Works for files saved with ``torch.save(model.state_dict(), path)``
using pickle protocol 2 (the default for PyTorch <= 2.x CPU tensors).
"""
import pickle, struct, io
from collections import OrderedDict
dtype_info = {
'FloatStorage': (np.float32, 4), 'HalfStorage': (np.float16, 2),
'LongStorage': (np.int64, 8), 'IntStorage': (np.int32, 4),
'DoubleStorage': (np.float64, 8),
}
class _StorageRef:
__slots__ = ('dtype_name', 'key', 'location', 'size')
def __init__(self, dtype_name, key, location, size):
self.dtype_name = dtype_name; self.key = key
self.location = location; self.size = size
class _TensorRef:
__slots__ = ('storage', 'offset', 'size', 'stride')
def __init__(self, storage, offset, size, stride):
self.storage = storage; self.offset = offset
self.size = tuple(size); self.stride = tuple(stride)
class _StorageType:
__slots__ = ('name',)
def __init__(self, name): self.name = name
def __call__(self, _): return self
class _Unpickler(pickle.Unpickler):
def find_class(self, module, name):
if module == 'collections' and name == 'OrderedDict':
return OrderedDict
if module == 'torch._utils' and name == '_rebuild_tensor_v2':
return (lambda s, o, sz, st, *a, **k:
_TensorRef(s, o, sz, st))
if module == 'torch' and name in dtype_info:
return _StorageType(name)
return super().find_class(module, name)
def persistent_load(self, saved_id):
if isinstance(saved_id, tuple) and saved_id[0] == 'storage':
st = saved_id[1]
return _StorageRef(
st.name if isinstance(st, _StorageType) else 'FloatStorage',
saved_id[2], saved_id[3], saved_id[4])
raise RuntimeError(f'Unknown persistent id: {saved_id}')
with open(path, 'rb') as f:
content = f.read()
buf = io.BytesIO(content)
for _ in range(3): # skip magic, proto, sysinfo
_Unpickler(buf).load()
data = _Unpickler(buf).load() # OrderedDict of _TensorRef
storage_keys = _Unpickler(buf).load() # list of storage keys
pos = buf.tell()
key_dtype = {}
for tref in data.values():
if isinstance(tref, _TensorRef):
key_dtype[tref.storage.key] = tref.storage.dtype_name
storages = {}
for key in storage_keys:
dname = key_dtype.get(key, 'FloatStorage')
np_dt, esz = dtype_info[dname]
n = struct.unpack('<Q', content[pos:pos+8])[0]; pos += 8
storages[key] = np.frombuffer(content, np_dt, count=n, offset=pos)
pos += n * esz
result = OrderedDict()
for name, tref in data.items():
if isinstance(tref, _TensorRef):
s = storages[tref.storage.key]
ne = 1
for d in tref.size:
ne *= d
result[name] = s[tref.offset:tref.offset+ne].reshape(
tref.size).copy()
return resultd2l.DATA_HUB['bert.base'] = (d2l.DATA_URL + 'bert.base.zip',
'7b3820b35da691042e5d34c0971ac3edbd80d3f4')
d2l.DATA_HUB['bert.small'] = (d2l.DATA_URL + 'bert.small.zip',
'a4e718a47137ccd1809c9107ab4f5edd317bae2c')Either pretrained BERT model contains a “vocab.json” file that defines the vocabulary set and a “pretrained.params” file of the pretrained parameters. We implement the following load_pretrained_model function to load pretrained BERT parameters.
def load_pretrained_model(pretrained_model, num_hiddens, ffn_num_hiddens,
num_heads, num_blks, dropout, max_len, devices):
data_dir = d2l.download_extract(pretrained_model)
# Define an empty vocabulary to load the predefined vocabulary
vocab = d2l.Vocab()
vocab.idx_to_token = json.load(open(os.path.join(data_dir, 'vocab.json')))
vocab.token_to_idx = {token: idx for idx, token in enumerate(
vocab.idx_to_token)}
bert = d2l.BERTModel(
len(vocab), num_hiddens, ffn_num_hiddens=ffn_num_hiddens,
num_heads=num_heads, num_blks=num_blks, dropout=dropout,
max_len=max_len)
# Load pretrained BERT parameters
bert.load_state_dict(torch.load(os.path.join(data_dir,
'pretrained.params')))
return bert, vocabdef load_pretrained_model(pretrained_model, num_hiddens, ffn_num_hiddens,
num_heads, num_blks, dropout, max_len, devices):
data_dir = d2l.download_extract(pretrained_model)
# Define an empty vocabulary to load the predefined vocabulary
vocab = d2l.Vocab()
vocab.idx_to_token = json.load(open(os.path.join(data_dir, 'vocab.json')))
vocab.token_to_idx = {token: idx for idx, token in enumerate(
vocab.idx_to_token)}
bert = d2l.BERTModel(
len(vocab), num_hiddens, ffn_num_hiddens=ffn_num_hiddens,
num_heads=num_heads, num_blks=num_blks, dropout=dropout,
max_len=max_len)
# Warm up model weights with a dummy forward pass
dummy_tokens = tf.ones((2, max_len), dtype=tf.int32)
dummy_segments = tf.zeros((2, max_len), dtype=tf.int32)
dummy_valid_lens = tf.cast(
tf.fill((2,), max_len), dtype=tf.float32)
bert(dummy_tokens, dummy_segments, dummy_valid_lens, training=False)
# Load pretrained PyTorch parameters as numpy arrays via the shared
# checkpoint reader defined in the previous cell.
pt = _load_torch_state_dict(
os.path.join(data_dir, 'pretrained.params'))
# Assign pretrained weights to the Keras BERTModel
enc = bert.encoder
enc.token_embedding.embeddings.assign(pt['encoder.token_embedding.weight'])
enc.segment_embedding.embeddings.assign(
pt['encoder.segment_embedding.weight'])
enc.pos_embedding.assign(pt['encoder.pos_embedding'])
for i in range(num_blks):
blk = enc.blks[i]
prefix = f'encoder.blks.{i}'
for attr, name in [('W_q', 'W_q'), ('W_k', 'W_k'),
('W_v', 'W_v'), ('W_o', 'W_o')]:
w = getattr(blk.attention, attr)
w.kernel.assign(pt[f'{prefix}.attention.{name}.weight'].T)
w.bias.assign(pt[f'{prefix}.attention.{name}.bias'])
blk.addnorm1.ln.gamma.assign(pt[f'{prefix}.addnorm1.ln.weight'])
blk.addnorm1.ln.beta.assign(pt[f'{prefix}.addnorm1.ln.bias'])
blk.addnorm2.ln.gamma.assign(pt[f'{prefix}.addnorm2.ln.weight'])
blk.addnorm2.ln.beta.assign(pt[f'{prefix}.addnorm2.ln.bias'])
blk.ffn.dense1.kernel.assign(pt[f'{prefix}.ffn.dense1.weight'].T)
blk.ffn.dense1.bias.assign(pt[f'{prefix}.ffn.dense1.bias'])
blk.ffn.dense2.kernel.assign(pt[f'{prefix}.ffn.dense2.weight'].T)
blk.ffn.dense2.bias.assign(pt[f'{prefix}.ffn.dense2.bias'])
bert.hidden.kernel.assign(pt['hidden.0.weight'].T)
bert.hidden.bias.assign(pt['hidden.0.bias'])
return bert, vocabdef load_pretrained_model(pretrained_model, num_hiddens, ffn_num_hiddens,
num_heads, num_blks, dropout, max_len, devices):
data_dir = d2l.download_extract(pretrained_model)
# Define an empty vocabulary to load the predefined vocabulary
vocab = d2l.Vocab()
vocab.idx_to_token = json.load(open(os.path.join(data_dir, 'vocab.json')))
vocab.token_to_idx = {token: idx for idx, token in enumerate(
vocab.idx_to_token)}
bert = d2l.BERTModel(
len(vocab), num_hiddens, ffn_num_hiddens=ffn_num_hiddens,
num_heads=num_heads, num_blks=num_blks, dropout=dropout,
max_len=max_len)
# Load pretrained PyTorch BERT parameters (as NumPy) into the NNX graph.
pt_state_dict = _load_torch_state_dict(
os.path.join(data_dir, 'pretrained.params'))
_load_torch_into_nnx_bert(bert, pt_state_dict)
return bert, vocab
def _load_torch_into_nnx_bert(bert, pt_state_dict):
"""Load a PyTorch BERT state dict into an NNX model."""
p = pt_state_dict
# Encoder: token, segment, position embeddings
enc = bert.encoder
enc.token_embedding.embedding[...] = jnp.array(
p['encoder.token_embedding.weight'])
enc.segment_embedding.embedding[...] = jnp.array(
p['encoder.segment_embedding.weight'])
enc.pos_embedding[...] = jnp.array(p['encoder.pos_embedding'])
# Transformer encoder blocks
for i, blk in enumerate(enc.blks):
prefix = f'encoder.blks.{i}'
# Multi-head attention
attn = blk.attention
for name in ['W_q', 'W_k', 'W_v', 'W_o']:
linear = getattr(attn, name)
linear.kernel[...] = jnp.array(
p[f'{prefix}.attention.{name}.weight'].T)
linear.bias[...] = jnp.array(
p[f'{prefix}.attention.{name}.bias'])
# Addnorm layers (LayerNorm)
for ln_name in ['addnorm1', 'addnorm2']:
ln = getattr(blk, ln_name).ln
ln.scale[...] = jnp.array(p[f'{prefix}.{ln_name}.ln.weight'])
ln.bias[...] = jnp.array(p[f'{prefix}.{ln_name}.ln.bias'])
# FFN
ffn = blk.ffn
ffn.dense1.kernel[...] = jnp.array(
p[f'{prefix}.ffn.dense1.weight'].T)
ffn.dense1.bias[...] = jnp.array(p[f'{prefix}.ffn.dense1.bias'])
ffn.dense2.kernel[...] = jnp.array(
p[f'{prefix}.ffn.dense2.weight'].T)
ffn.dense2.bias[...] = jnp.array(p[f'{prefix}.ffn.dense2.bias'])
# Hidden (tanh) layer
bert.hidden.kernel[...] = jnp.array(p['hidden.0.weight'].T)
bert.hidden.bias[...] = jnp.array(p['hidden.0.bias'])def load_pretrained_model(pretrained_model, num_hiddens, ffn_num_hiddens,
num_heads, num_blks, dropout, max_len, devices):
data_dir = d2l.download_extract(pretrained_model)
# Define an empty vocabulary to load the predefined vocabulary
vocab = d2l.Vocab()
vocab.idx_to_token = json.load(open(os.path.join(data_dir, 'vocab.json')))
vocab.token_to_idx = {token: idx for idx, token in enumerate(
vocab.idx_to_token)}
bert = d2l.BERTModel(len(vocab), num_hiddens, ffn_num_hiddens, num_heads,
num_blks, dropout, max_len)
# Load pretrained BERT parameters
bert.load_parameters(os.path.join(data_dir, 'pretrained.params'),
ctx=devices)
return bert, vocabTo facilitate demonstration on most machines, we will load and fine-tune the small version (“bert.small”) of the pretrained BERT in this section. In the exercise, we will show how to fine-tune the much larger “bert.base” to significantly improve the testing accuracy.
devices = d2l.try_all_gpus()
bert, vocab = load_pretrained_model(
'bert.small', num_hiddens=256, ffn_num_hiddens=512, num_heads=4,
num_blks=2, dropout=0.1, max_len=512, devices=devices)devices = d2l.try_all_gpus()
bert, vocab = load_pretrained_model(
'bert.small', num_hiddens=256, ffn_num_hiddens=512, num_heads=4,
num_blks=2, dropout=0.1, max_len=512, devices=devices)/home/smola/d2l-neu/.venv-tensorflow/lib/python3.12/site-packages/keras/src/layers/layer.py:427: UserWarning: `build()` was called on layer 'bert_model', however the layer does not have a `build()` method implemented and it looks like it has unbuilt state. This will cause the layer to be marked as built, despite not being actually built, which may cause failures down the line. Make sure to implement a proper `build()` method.
warnings.warn(devices = d2l.try_all_gpus()
bert, vocab = load_pretrained_model(
'bert.small', num_hiddens=256, ffn_num_hiddens=512, num_heads=4,
num_blks=2, dropout=0.1, max_len=512, devices=devices)devices = d2l.try_all_gpus()
bert, vocab = load_pretrained_model(
'bert.small', num_hiddens=256, ffn_num_hiddens=512, num_heads=4,
num_blks=2, dropout=0.1, max_len=512, devices=devices)18.7.2 The Dataset for Fine-Tuning BERT
For the downstream task natural language inference on the SNLI dataset, we define a customized dataset class SNLIBERTDataset. In each example, the premise and hypothesis form a pair of text sequence and is packed into one BERT input sequence as depicted in Figure 18.6.2. Recall Section 17.9.4 that segment IDs are used to distinguish the premise and the hypothesis in a BERT input sequence. With the predefined maximum length of a BERT input sequence (max_len), the last token of the longer of the input text pair keeps getting removed until max_len is met. To accelerate generation of the SNLI dataset for fine-tuning BERT, we use 4 worker processes to generate training or testing examples in parallel.
class SNLIBERTDataset(torch.utils.data.Dataset):
def __init__(self, dataset, max_len, vocab=None):
all_premise_hypothesis_tokens = [[
p_tokens, h_tokens] for p_tokens, h_tokens in zip(
*[d2l.tokenize([s.lower() for s in sentences])
for sentences in dataset[:2]])]
self.labels = torch.tensor(dataset[2])
self.vocab = vocab
self.max_len = max_len
(self.all_token_ids, self.all_segments,
self.valid_lens) = self._preprocess(all_premise_hypothesis_tokens)
print('read ' + str(len(self.all_token_ids)) + ' examples')
def _preprocess(self, all_premise_hypothesis_tokens):
with multiprocessing.Pool(4) as pool: # Use 4 worker processes
out = pool.map(self._mp_worker, all_premise_hypothesis_tokens)
all_token_ids = [
token_ids for token_ids, segments, valid_len in out]
all_segments = [segments for token_ids, segments, valid_len in out]
valid_lens = [valid_len for token_ids, segments, valid_len in out]
return (torch.tensor(all_token_ids, dtype=torch.long),
torch.tensor(all_segments, dtype=torch.long),
torch.tensor(valid_lens))
def _mp_worker(self, premise_hypothesis_tokens):
p_tokens, h_tokens = premise_hypothesis_tokens
self._truncate_pair_of_tokens(p_tokens, h_tokens)
tokens, segments = d2l.get_tokens_and_segments(p_tokens, h_tokens)
token_ids = self.vocab[tokens] + [self.vocab['<pad>']] \
* (self.max_len - len(tokens))
segments = segments + [0] * (self.max_len - len(segments))
valid_len = len(tokens)
return token_ids, segments, valid_len
def _truncate_pair_of_tokens(self, p_tokens, h_tokens):
# Reserve slots for '<cls>', '<sep>', and '<sep>' tokens for the BERT
# input
while len(p_tokens) + len(h_tokens) > self.max_len - 3:
if len(p_tokens) > len(h_tokens):
p_tokens.pop()
else:
h_tokens.pop()
def __getitem__(self, idx):
return (self.all_token_ids[idx], self.all_segments[idx],
self.valid_lens[idx]), self.labels[idx]
def __len__(self):
return len(self.all_token_ids)class SNLIBERTDataset:
def __init__(self, dataset, max_len, vocab=None):
all_premise_hypothesis_tokens = [[
p_tokens, h_tokens] for p_tokens, h_tokens in zip(
*[d2l.tokenize([s.lower() for s in sentences])
for sentences in dataset[:2]])]
self.labels = np.array(dataset[2])
self.vocab = vocab
self.max_len = max_len
(self.all_token_ids, self.all_segments,
self.valid_lens) = self._preprocess(all_premise_hypothesis_tokens)
print('read ' + str(len(self.all_token_ids)) + ' examples')
def _preprocess(self, all_premise_hypothesis_tokens):
with multiprocessing.Pool(4) as pool: # Use 4 worker processes
out = pool.map(self._mp_worker, all_premise_hypothesis_tokens)
all_token_ids = [
token_ids for token_ids, segments, valid_len in out]
all_segments = [segments for token_ids, segments, valid_len in out]
valid_lens = [valid_len for token_ids, segments, valid_len in out]
return (np.array(all_token_ids, dtype='int32'),
np.array(all_segments, dtype='int32'),
np.array(valid_lens))
def _mp_worker(self, premise_hypothesis_tokens):
p_tokens, h_tokens = premise_hypothesis_tokens
self._truncate_pair_of_tokens(p_tokens, h_tokens)
tokens, segments = d2l.get_tokens_and_segments(p_tokens, h_tokens)
token_ids = self.vocab[tokens] + [self.vocab['<pad>']] \
* (self.max_len - len(tokens))
segments = segments + [0] * (self.max_len - len(segments))
valid_len = len(tokens)
return token_ids, segments, valid_len
def _truncate_pair_of_tokens(self, p_tokens, h_tokens):
# Reserve slots for '<cls>', '<sep>', and '<sep>' tokens for the BERT
# input
while len(p_tokens) + len(h_tokens) > self.max_len - 3:
if len(p_tokens) > len(h_tokens):
p_tokens.pop()
else:
h_tokens.pop()
def __getitem__(self, idx):
return (self.all_token_ids[idx], self.all_segments[idx],
self.valid_lens[idx]), self.labels[idx]
def __len__(self):
return len(self.all_token_ids)class SNLIBERTDataset:
def __init__(self, dataset, max_len, vocab=None):
all_premise_hypothesis_tokens = [[
p_tokens, h_tokens] for p_tokens, h_tokens in zip(
*[d2l.tokenize([s.lower() for s in sentences])
for sentences in dataset[:2]])]
self.labels = np.asarray(dataset[2], dtype=np.int32)
self.vocab = vocab
self.max_len = max_len
(self.all_token_ids, self.all_segments,
self.valid_lens) = self._preprocess(all_premise_hypothesis_tokens)
print('read ' + str(len(self.all_token_ids)) + ' examples')
def _preprocess(self, all_premise_hypothesis_tokens):
# This Python token/list processing is inexpensive enough here that a
# list comprehension avoids multiprocessing setup and serialization.
out = [self._preprocess_pair(tokens)
for tokens in all_premise_hypothesis_tokens]
all_token_ids = [
token_ids for token_ids, segments, valid_len in out]
all_segments = [segments for token_ids, segments, valid_len in out]
valid_lens = [valid_len for token_ids, segments, valid_len in out]
return (np.asarray(all_token_ids, dtype=np.int32),
np.asarray(all_segments, dtype=np.int32),
np.asarray(valid_lens, dtype=np.float32))
def _preprocess_pair(self, premise_hypothesis_tokens):
p_tokens, h_tokens = premise_hypothesis_tokens
self._truncate_pair_of_tokens(p_tokens, h_tokens)
tokens, segments = d2l.get_tokens_and_segments(p_tokens, h_tokens)
token_ids = self.vocab[tokens] + [self.vocab['<pad>']] \
* (self.max_len - len(tokens))
segments = segments + [0] * (self.max_len - len(segments))
valid_len = len(tokens)
return token_ids, segments, valid_len
def _truncate_pair_of_tokens(self, p_tokens, h_tokens):
# Reserve slots for '<cls>', '<sep>', and '<sep>' tokens for the BERT
# input
while len(p_tokens) + len(h_tokens) > self.max_len - 3:
if len(p_tokens) > len(h_tokens):
p_tokens.pop()
else:
h_tokens.pop()
def __getitem__(self, idx):
return (self.all_token_ids[idx], self.all_segments[idx],
self.valid_lens[idx]), self.labels[idx]
def __len__(self):
return len(self.all_token_ids)class SNLIBERTDataset(gluon.data.Dataset):
def __init__(self, dataset, max_len, vocab=None):
all_premise_hypothesis_tokens = [[
p_tokens, h_tokens] for p_tokens, h_tokens in zip(
*[d2l.tokenize([s.lower() for s in sentences])
for sentences in dataset[:2]])]
self.labels = np.array(dataset[2])
self.vocab = vocab
self.max_len = max_len
(self.all_token_ids, self.all_segments,
self.valid_lens) = self._preprocess(all_premise_hypothesis_tokens)
print('read ' + str(len(self.all_token_ids)) + ' examples')
def _preprocess(self, all_premise_hypothesis_tokens):
with multiprocessing.Pool(4) as pool: # Use 4 worker processes
out = pool.map(self._mp_worker, all_premise_hypothesis_tokens)
all_token_ids = [
token_ids for token_ids, segments, valid_len in out]
all_segments = [segments for token_ids, segments, valid_len in out]
valid_lens = [valid_len for token_ids, segments, valid_len in out]
return (np.array(all_token_ids, dtype='int32'),
np.array(all_segments, dtype='int32'),
np.array(valid_lens))
def _mp_worker(self, premise_hypothesis_tokens):
p_tokens, h_tokens = premise_hypothesis_tokens
self._truncate_pair_of_tokens(p_tokens, h_tokens)
tokens, segments = d2l.get_tokens_and_segments(p_tokens, h_tokens)
token_ids = self.vocab[tokens] + [self.vocab['<pad>']] \
* (self.max_len - len(tokens))
segments = segments + [0] * (self.max_len - len(segments))
valid_len = len(tokens)
return token_ids, segments, valid_len
def _truncate_pair_of_tokens(self, p_tokens, h_tokens):
# Reserve slots for '<cls>', '<sep>', and '<sep>' tokens for the BERT
# input
while len(p_tokens) + len(h_tokens) > self.max_len - 3:
if len(p_tokens) > len(h_tokens):
p_tokens.pop()
else:
h_tokens.pop()
def __getitem__(self, idx):
return (self.all_token_ids[idx], self.all_segments[idx],
self.valid_lens[idx]), self.labels[idx]
def __len__(self):
return len(self.all_token_ids)After downloading the SNLI dataset, we generate training and testing examples by instantiating the SNLIBERTDataset class. Such examples will be read in minibatches during training and testing of natural language inference.
# Reduce `batch_size` if there is an out of memory error. In the original BERT
# model, `max_len` = 512
batch_size, max_len, num_workers = 512, 128, d2l.get_dataloader_workers()
data_dir = d2l.download_extract('SNLI')
train_set = SNLIBERTDataset(d2l.read_snli(data_dir, True), max_len, vocab)
test_set = SNLIBERTDataset(d2l.read_snli(data_dir, False), max_len, vocab)
train_iter = torch.utils.data.DataLoader(train_set, batch_size, shuffle=True,
num_workers=num_workers)
test_iter = torch.utils.data.DataLoader(test_set, batch_size,
num_workers=num_workers)read 549367 examplesread 9824 examples# Reduce `batch_size` if there is an out of memory error. In the original BERT
# model, `max_len` = 512
batch_size, max_len = 512, 128
data_dir = d2l.download_extract('SNLI')
train_set = SNLIBERTDataset(d2l.read_snli(data_dir, True), max_len, vocab)
test_set = SNLIBERTDataset(d2l.read_snli(data_dir, False), max_len, vocab)
AUTOTUNE = tf.data.AUTOTUNE
train_iter = tf.data.Dataset.from_tensor_slices(
(train_set.all_token_ids, train_set.all_segments,
train_set.valid_lens, train_set.labels)
).shuffle(buffer_size=len(train_set.labels)).batch(batch_size).prefetch(AUTOTUNE)
test_iter = tf.data.Dataset.from_tensor_slices(
(test_set.all_token_ids, test_set.all_segments,
test_set.valid_lens, test_set.labels)
).batch(batch_size).prefetch(AUTOTUNE)read 549367 examplesread 9824 examples# Reduce `batch_size` if there is an out of memory error. In the original BERT
# model, `max_len` = 512
batch_size, max_len = 512, 128
data_dir = d2l.download_extract('SNLI')
train_set = SNLIBERTDataset(d2l.read_snli(data_dir, True), max_len, vocab)
test_set = SNLIBERTDataset(d2l.read_snli(data_dir, False), max_len, vocab)
train_iter = d2l.load_array(
(train_set.all_token_ids, train_set.all_segments,
train_set.valid_lens, train_set.labels), batch_size, is_train=True)
test_iter = d2l.load_array(
(test_set.all_token_ids, test_set.all_segments,
test_set.valid_lens, test_set.labels), batch_size, is_train=False)read 549367 examplesread 9824 examples# Reduce `batch_size` if there is an out of memory error. In the original BERT
# model, `max_len` = 512
batch_size, max_len, num_workers = 512, 128, d2l.get_dataloader_workers()
data_dir = d2l.download_extract('SNLI')
train_set = SNLIBERTDataset(d2l.read_snli(data_dir, True), max_len, vocab)
test_set = SNLIBERTDataset(d2l.read_snli(data_dir, False), max_len, vocab)
train_iter = gluon.data.DataLoader(train_set, batch_size, shuffle=True,
num_workers=num_workers)
test_iter = gluon.data.DataLoader(test_set, batch_size,
num_workers=num_workers)read 549367 examplesread 9824 examples18.7.3 Fine-Tuning BERT
As Figure 18.6.2 indicates, fine-tuning BERT for natural language inference requires only an extra MLP consisting of two fully connected layers (see self.hidden and self.output—named self.output_layer in the TensorFlow tab to avoid clashing with Keras’s reserved output property—in the following BERTClassifier class). This MLP transforms the BERT representation of the special “<cls>” token, which encodes the information of both the premise and the hypothesis, into three outputs of natural language inference: entailment, contradiction, and neutral.
class BERTClassifier(nn.Module):
def __init__(self, bert):
super(BERTClassifier, self).__init__()
self.encoder = bert.encoder
self.hidden = bert.hidden
self.output = nn.LazyLinear(3)
def forward(self, inputs):
tokens_X, segments_X, valid_lens_x = inputs
encoded_X = self.encoder(tokens_X, segments_X, valid_lens_x)
return self.output(self.hidden(encoded_X[:, 0, :]))class BERTClassifier(keras.Model):
def __init__(self, bert):
super(BERTClassifier, self).__init__()
self.encoder = bert.encoder
self.hidden = bert.hidden
self.output_layer = keras.layers.Dense(3)
def call(self, inputs, training=False):
tokens_X, segments_X, valid_lens_x = inputs
encoded_X = self.encoder(tokens_X, segments_X, valid_lens_x,
training=training)
return self.output_layer(self.hidden(encoded_X[:, 0, :]))class BERTClassifier(nnx.Module):
def __init__(self, bert, rngs=None):
self.bert = bert
rngs = nnx.Rngs(0) if rngs is None else rngs
self.output = nnx.Linear(bert.hidden.out_features, 3, rngs=rngs)
def __call__(self, tokens_X, segments_X, valid_lens_x):
encoded_X = self.bert.encoder(tokens_X, segments_X, valid_lens_x)
return self.output(jnp.tanh(self.bert.hidden(encoded_X[:, 0, :])))class BERTClassifier(nn.Block):
def __init__(self, bert):
super(BERTClassifier, self).__init__()
self.encoder = bert.encoder
self.hidden = bert.hidden
self.output = nn.Dense(3)
def forward(self, inputs):
tokens_X, segments_X, valid_lens_x = inputs
encoded_X = self.encoder(tokens_X, segments_X, valid_lens_x)
return self.output(self.hidden(encoded_X[:, 0, :]))In the following, the pretrained BERT model bert is fed into the BERTClassifier instance net for the downstream application. In common implementations of BERT fine-tuning, only the parameters of the output layer of the additional MLP (net.output, or net.output_layer in the TensorFlow tab) will be learned from scratch. All the parameters of the pretrained BERT encoder (net.encoder) and the hidden layer of the additional MLP (net.hidden) will be fine-tuned.
net = BERTClassifier(bert)net = BERTClassifier(bert)
# Warm up the classifier with a dummy forward pass
dummy_tokens = tf.ones((2, max_len), dtype=tf.int32)
dummy_segments = tf.zeros((2, max_len), dtype=tf.int32)
dummy_valid_lens = tf.cast(tf.fill((2,), max_len), dtype=tf.float32)
net((dummy_tokens, dummy_segments, dummy_valid_lens), training=False)<tf.Tensor: shape=(2, 3), dtype=float32, numpy=
array([[ 0.7526041 , 0.1140694 , -0.73437357],
[ 0.7526041 , 0.1140694 , -0.73437357]], dtype=float32)>net = BERTClassifier(bert)net = BERTClassifier(bert)
net.output.initialize(ctx=devices)Recall that in Section 17.9 both the MaskLM class and the NextSentencePred class have parameters in their employed MLPs. These parameters are part of those in the pretrained BERT model bert, and thus part of parameters in net. However, such parameters are only for computing the masked language modeling loss and the next sentence prediction loss during pretraining. These two loss functions are irrelevant to fine-tuning downstream applications, thus the parameters of the employed MLPs in MaskLM and NextSentencePred are not updated (and so their gradients become stale) when BERT is fine-tuned.
To allow parameters with stale gradients, the flag ignore_stale_grad=True is set in the step function of d2l.train_batch_ch13. We use this function to train and evaluate the model net using the training set (train_iter) and the testing set (test_iter) of SNLI. Due to the limited computational resources, the training and testing accuracy can be further improved: we leave its discussions in the exercises.
lr, num_epochs = 1e-4, 5
trainer = torch.optim.Adam(net.parameters(), lr=lr)
loss = nn.CrossEntropyLoss(reduction='none')
net(next(iter(train_iter))[0])
d2l.train_ch13(net, train_iter, test_iter, loss, trainer, num_epochs, devices)loss 0.477, train acc 0.811, test acc 0.787
11892.3 examples/sec on [device(type='cuda', index=0)]
lr, num_epochs = 1e-4, 5
# Wrap tf.data batches for Keras: each batch is
# (tokens_X, segments_X, valid_lens_x, labels)
def reformat(tokens_X, segments_X, valid_lens_x, labels):
return (tokens_X, segments_X, valid_lens_x), labels
train_iter_tf = train_iter.map(reformat)
test_iter_tf = test_iter.map(reformat)
net.compile(
optimizer=keras.optimizers.Adam(lr),
loss=keras.losses.SparseCategoricalCrossentropy(from_logits=True),
metrics=['accuracy'])
net.fit(train_iter_tf, validation_data=test_iter_tf, epochs=num_epochs)Epoch 1/5 1/1073 ━━━━━━━━━━━━━━━━━━━━ 11:17:27 38s/step - accuracy: 0.3164 - loss: 1.2578 3/1073 ━━━━━━━━━━━━━━━━━━━━ 43s 41ms/step - accuracy: 0.3127 - loss: 1.2615 5/1073 ━━━━━━━━━━━━━━━━━━━━ 43s 41ms/step - accuracy: 0.3178 - loss: 1.2396 7/1073 ━━━━━━━━━━━━━━━━━━━━ 43s 41ms/step - accuracy: 0.3221 - loss: 1.2246 9/1073 ━━━━━━━━━━━━━━━━━━━━ 43s 41ms/step - accuracy: 0.3252 - loss: 1.2129 11/1073 ━━━━━━━━━━━━━━━━━━━━ 43s 41ms/step - accuracy: 0.3288 - loss: 1.2025 13/1073 ━━━━━━━━━━━━━━━━━━━━ 43s 41ms/step - accuracy: 0.3322 - loss: 1.1942 15/1073 ━━━━━━━━━━━━━━━━━━━━ 43s 41ms/step - accuracy: 0.3355 - loss: 1.1871 17/1073 ━━━━━━━━━━━━━━━━━━━━ 42s 41ms/step - accuracy: 0.3391 - loss: 1.1806 19/1073 ━━━━━━━━━━━━━━━━━━━━ 42s 41ms/step - accuracy: 0.3424 - loss: 1.1747 21/1073 ━━━━━━━━━━━━━━━━━━━━ 42s 41ms/step - accuracy: 0.3455 - loss: 1.1694 23/1073 ━━━━━━━━━━━━━━━━━━━━ 42s 41ms/step - accuracy: 0.3484 - loss: 1.1647 25/1073 ━━━━━━━━━━━━━━━━━━━━ 42s 41ms/step - accuracy: 0.3511 - loss: 1.1603 27/1073 ━━━━━━━━━━━━━━━━━━━━ 42s 41ms/step - accuracy: 0.3537 - loss: 1.1564 29/1073 ━━━━━━━━━━━━━━━━━━━━ 42s 41ms/step - accuracy: 0.3560 - loss: 1.1527 31/1073 ━━━━━━━━━━━━━━━━━━━━ 42s 41ms/step - accuracy: 0.3583 - loss: 1.1493 33/1073 ━━━━━━━━━━━━━━━━━━━━ 42s 41ms/step - accuracy: 0.3604 - loss: 1.1461 35/1073 ━━━━━━━━━━━━━━━━━━━━ 42s 41ms/step - accuracy: 0.3626 - loss: 1.1431 37/1073 ━━━━━━━━━━━━━━━━━━━━ 42s 41ms/step - accuracy: 0.3647 - loss: 1.1403 39/1073 ━━━━━━━━━━━━━━━━━━━━ 41s 41ms/step - accuracy: 0.3667 - loss: 1.1377 41/1073 ━━━━━━━━━━━━━━━━━━━━ 41s 41ms/step - accuracy: 0.3686 - loss: 1.1352 43/1073 ━━━━━━━━━━━━━━━━━━━━ 41s 41ms/step - accuracy: 0.3705 - loss: 1.1328 45/1073 ━━━━━━━━━━━━━━━━━━━━ 41s 41ms/step - accuracy: 0.3723 - loss: 1.1305 47/1073 ━━━━━━━━━━━━━━━━━━━━ 41s 41ms/step - accuracy: 0.3741 - loss: 1.1283 49/1073 ━━━━━━━━━━━━━━━━━━━━ 41s 41ms/step - accuracy: 0.3759 - loss: 1.1262 51/1073 ━━━━━━━━━━━━━━━━━━━━ 41s 41ms/step - accuracy: 0.3777 - loss: 1.1241 53/1073 ━━━━━━━━━━━━━━━━━━━━ 41s 41ms/step - accuracy: 0.3795 - loss: 1.1221 55/1073 ━━━━━━━━━━━━━━━━━━━━ 41s 41ms/step - accuracy: 0.3812 - loss: 1.1201 57/1073 ━━━━━━━━━━━━━━━━━━━━ 41s 41ms/step - accuracy: 0.3829 - loss: 1.1182 59/1073 ━━━━━━━━━━━━━━━━━━━━ 41s 41ms/step - accuracy: 0.3846 - loss: 1.1164 61/1073 ━━━━━━━━━━━━━━━━━━━━ 41s 41ms/step - accuracy: 0.3862 - loss: 1.1145 63/1073 ━━━━━━━━━━━━━━━━━━━━ 40s 41ms/step - accuracy: 0.3878 - loss: 1.1128 65/1073 ━━━━━━━━━━━━━━━━━━━━ 40s 41ms/step - accuracy: 0.3893 - loss: 1.1110 67/1073 ━━━━━━━━━━━━━━━━━━━━ 40s 41ms/step - accuracy: 0.3909 - loss: 1.1093 69/1073 ━━━━━━━━━━━━━━━━━━━━ 40s 41ms/step - accuracy: 0.3924 - loss: 1.1076 71/1073 ━━━━━━━━━━━━━━━━━━━━ 40s 41ms/step - accuracy: 0.3939 - loss: 1.1060 73/1073 ━━━━━━━━━━━━━━━━━━━━ 40s 41ms/step - accuracy: 0.3954 - loss: 1.1044 75/1073 ━━━━━━━━━━━━━━━━━━━━ 40s 41ms/step - accuracy: 0.3969 - loss: 1.1028 77/1073 ━━━━━━━━━━━━━━━━━━━━ 40s 41ms/step - accuracy: 0.3983 - loss: 1.1012 79/1073 ━━━━━━━━━━━━━━━━━━━━ 40s 41ms/step - accuracy: 0.3997 - loss: 1.0997 81/1073 ━━━━━━━━━━━━━━━━━━━━ 40s 41ms/step - accuracy: 0.4011 - loss: 1.0982 83/1073 ━━━━━━━━━━━━━━━━━━━━ 40s 41ms/step - accuracy: 0.4025 - loss: 1.0967 85/1073 ━━━━━━━━━━━━━━━━━━━━ 40s 41ms/step - accuracy: 0.4038 - loss: 1.0953 87/1073 ━━━━━━━━━━━━━━━━━━━━ 39s 40ms/step - accuracy: 0.4052 - loss: 1.0939 89/1073 ━━━━━━━━━━━━━━━━━━━━ 39s 40ms/step - accuracy: 0.4065 - loss: 1.0925 91/1073 ━━━━━━━━━━━━━━━━━━━━ 39s 40ms/step - accuracy: 0.4078 - loss: 1.0911 93/1073 ━━━━━━━━━━━━━━━━━━━━ 39s 40ms/step - accuracy: 0.4091 - loss: 1.0897 95/1073 ━━━━━━━━━━━━━━━━━━━━ 39s 40ms/step - accuracy: 0.4103 - loss: 1.0883 97/1073 ━━━━━━━━━━━━━━━━━━━━ 39s 40ms/step - accuracy: 0.4116 - loss: 1.0870 99/1073 ━━━━━━━━━━━━━━━━━━━━ 39s 40ms/step - accuracy: 0.4128 - loss: 1.0857 101/1073 ━━━━━━━━━━━━━━━━━━━━ 39s 40ms/step - accuracy: 0.4141 - loss: 1.0843 103/1073 ━━━━━━━━━━━━━━━━━━━━ 39s 41ms/step - accuracy: 0.4153 - loss: 1.0830 105/1073 ━━━━━━━━━━━━━━━━━━━━ 39s 41ms/step - accuracy: 0.4165 - loss: 1.0817 107/1073 ━━━━━━━━━━━━━━━━━━━━ 39s 41ms/step - accuracy: 0.4177 - loss: 1.0804 109/1073 ━━━━━━━━━━━━━━━━━━━━ 39s 41ms/step - accuracy: 0.4189 - loss: 1.0792 111/1073 ━━━━━━━━━━━━━━━━━━━━ 39s 41ms/step - accuracy: 0.4201 - loss: 1.0779 113/1073 ━━━━━━━━━━━━━━━━━━━━ 38s 41ms/step - accuracy: 0.4213 - loss: 1.0766 115/1073 ━━━━━━━━━━━━━━━━━━━━ 38s 41ms/step - accuracy: 0.4225 - loss: 1.0754 117/1073 ━━━━━━━━━━━━━━━━━━━━ 38s 41ms/step - accuracy: 0.4236 - loss: 1.0741 119/1073 ━━━━━━━━━━━━━━━━━━━━ 38s 41ms/step - accuracy: 0.4247 - loss: 1.0729 121/1073 ━━━━━━━━━━━━━━━━━━━━ 38s 41ms/step - accuracy: 0.4259 - loss: 1.0716 123/1073 ━━━━━━━━━━━━━━━━━━━━ 38s 41ms/step - accuracy: 0.4270 - loss: 1.0704 125/1073 ━━━━━━━━━━━━━━━━━━━━ 38s 41ms/step - accuracy: 0.4281 - loss: 1.0692 127/1073 ━━━━━━━━━━━━━━━━━━━━ 38s 41ms/step - accuracy: 0.4292 - loss: 1.0680 129/1073 ━━━━━━━━━━━━━━━━━━━━ 38s 41ms/step - accuracy: 0.4303 - loss: 1.0668 131/1073 ━━━━━━━━━━━━━━━━━━━━ 38s 41ms/step - accuracy: 0.4314 - loss: 1.0657 133/1073 ━━━━━━━━━━━━━━━━━━━━ 38s 41ms/step - accuracy: 0.4324 - loss: 1.0645 135/1073 ━━━━━━━━━━━━━━━━━━━━ 38s 41ms/step - accuracy: 0.4335 - loss: 1.0633 137/1073 ━━━━━━━━━━━━━━━━━━━━ 38s 41ms/step - accuracy: 0.4345 - loss: 1.0622 139/1073 ━━━━━━━━━━━━━━━━━━━━ 37s 41ms/step - accuracy: 0.4355 - loss: 1.0611 141/1073 ━━━━━━━━━━━━━━━━━━━━ 37s 41ms/step - accuracy: 0.4366 - loss: 1.0600 143/1073 ━━━━━━━━━━━━━━━━━━━━ 37s 41ms/step - accuracy: 0.4376 - loss: 1.0589 145/1073 ━━━━━━━━━━━━━━━━━━━━ 37s 41ms/step - accuracy: 0.4385 - loss: 1.0578 147/1073 ━━━━━━━━━━━━━━━━━━━━ 37s 41ms/step - accuracy: 0.4395 - loss: 1.0567 149/1073 ━━━━━━━━━━━━━━━━━━━━ 37s 41ms/step - accuracy: 0.4405 - loss: 1.0556 151/1073 ━━━━━━━━━━━━━━━━━━━━ 37s 41ms/step - accuracy: 0.4415 - loss: 1.0545 153/1073 ━━━━━━━━━━━━━━━━━━━━ 37s 41ms/step - accuracy: 0.4424 - loss: 1.0534 155/1073 ━━━━━━━━━━━━━━━━━━━━ 37s 41ms/step - accuracy: 0.4434 - loss: 1.0524 157/1073 ━━━━━━━━━━━━━━━━━━━━ 37s 41ms/step - accuracy: 0.4443 - loss: 1.0513 159/1073 ━━━━━━━━━━━━━━━━━━━━ 37s 41ms/step - accuracy: 0.4452 - loss: 1.0503 161/1073 ━━━━━━━━━━━━━━━━━━━━ 37s 41ms/step - accuracy: 0.4461 - loss: 1.0493 163/1073 ━━━━━━━━━━━━━━━━━━━━ 36s 41ms/step - accuracy: 0.4470 - loss: 1.0483 165/1073 ━━━━━━━━━━━━━━━━━━━━ 36s 41ms/step - accuracy: 0.4479 - loss: 1.0473 167/1073 ━━━━━━━━━━━━━━━━━━━━ 36s 41ms/step - accuracy: 0.4488 - loss: 1.0463 169/1073 ━━━━━━━━━━━━━━━━━━━━ 36s 41ms/step - accuracy: 0.4497 - loss: 1.0453 171/1073 ━━━━━━━━━━━━━━━━━━━━ 36s 41ms/step - accuracy: 0.4505 - loss: 1.0443 173/1073 ━━━━━━━━━━━━━━━━━━━━ 36s 41ms/step - accuracy: 0.4514 - loss: 1.0434 175/1073 ━━━━━━━━━━━━━━━━━━━━ 36s 41ms/step - accuracy: 0.4523 - loss: 1.0424 177/1073 ━━━━━━━━━━━━━━━━━━━━ 36s 41ms/step - accuracy: 0.4531 - loss: 1.0414 179/1073 ━━━━━━━━━━━━━━━━━━━━ 36s 41ms/step - accuracy: 0.4539 - loss: 1.0405 181/1073 ━━━━━━━━━━━━━━━━━━━━ 36s 41ms/step - accuracy: 0.4548 - loss: 1.0395 183/1073 ━━━━━━━━━━━━━━━━━━━━ 36s 41ms/step - accuracy: 0.4556 - loss: 1.0386 185/1073 ━━━━━━━━━━━━━━━━━━━━ 36s 41ms/step - accuracy: 0.4564 - loss: 1.0377 187/1073 ━━━━━━━━━━━━━━━━━━━━ 36s 41ms/step - accuracy: 0.4572 - loss: 1.0368 189/1073 ━━━━━━━━━━━━━━━━━━━━ 35s 41ms/step - accuracy: 0.4580 - loss: 1.0359 191/1073 ━━━━━━━━━━━━━━━━━━━━ 35s 41ms/step - accuracy: 0.4588 - loss: 1.0350 193/1073 ━━━━━━━━━━━━━━━━━━━━ 35s 41ms/step - accuracy: 0.4596 - loss: 1.0341 195/1073 ━━━━━━━━━━━━━━━━━━━━ 35s 41ms/step - accuracy: 0.4604 - loss: 1.0332 197/1073 ━━━━━━━━━━━━━━━━━━━━ 35s 41ms/step - accuracy: 0.4611 - loss: 1.0323 199/1073 ━━━━━━━━━━━━━━━━━━━━ 35s 41ms/step - accuracy: 0.4619 - loss: 1.0314 201/1073 ━━━━━━━━━━━━━━━━━━━━ 35s 41ms/step - accuracy: 0.4626 - loss: 1.0306 203/1073 ━━━━━━━━━━━━━━━━━━━━ 35s 41ms/step - accuracy: 0.4634 - loss: 1.0297 205/1073 ━━━━━━━━━━━━━━━━━━━━ 35s 41ms/step - accuracy: 0.4641 - loss: 1.0289 207/1073 ━━━━━━━━━━━━━━━━━━━━ 35s 41ms/step - accuracy: 0.4648 - loss: 1.0281 209/1073 ━━━━━━━━━━━━━━━━━━━━ 35s 41ms/step - accuracy: 0.4656 - loss: 1.0272 211/1073 ━━━━━━━━━━━━━━━━━━━━ 35s 41ms/step - accuracy: 0.4663 - loss: 1.0264 213/1073 ━━━━━━━━━━━━━━━━━━━━ 34s 41ms/step - accuracy: 0.4670 - loss: 1.0256 215/1073 ━━━━━━━━━━━━━━━━━━━━ 34s 41ms/step - accuracy: 0.4677 - loss: 1.0247 217/1073 ━━━━━━━━━━━━━━━━━━━━ 34s 41ms/step - accuracy: 0.4684 - loss: 1.0239 219/1073 ━━━━━━━━━━━━━━━━━━━━ 34s 41ms/step - accuracy: 0.4691 - loss: 1.0231 221/1073 ━━━━━━━━━━━━━━━━━━━━ 34s 41ms/step - accuracy: 0.4698 - loss: 1.0223 223/1073 ━━━━━━━━━━━━━━━━━━━━ 34s 41ms/step - accuracy: 0.4705 - loss: 1.0215 225/1073 ━━━━━━━━━━━━━━━━━━━━ 34s 41ms/step - accuracy: 0.4712 - loss: 1.0207 227/1073 ━━━━━━━━━━━━━━━━━━━━ 34s 41ms/step - accuracy: 0.4718 - loss: 1.0199 229/1073 ━━━━━━━━━━━━━━━━━━━━ 34s 41ms/step - accuracy: 0.4725 - loss: 1.0192 231/1073 ━━━━━━━━━━━━━━━━━━━━ 34s 41ms/step - accuracy: 0.4732 - loss: 1.0184 233/1073 ━━━━━━━━━━━━━━━━━━━━ 34s 41ms/step - accuracy: 0.4738 - loss: 1.0176 235/1073 ━━━━━━━━━━━━━━━━━━━━ 34s 41ms/step - accuracy: 0.4745 - loss: 1.0169 237/1073 ━━━━━━━━━━━━━━━━━━━━ 33s 41ms/step - accuracy: 0.4751 - loss: 1.0161 239/1073 ━━━━━━━━━━━━━━━━━━━━ 33s 41ms/step - accuracy: 0.4758 - loss: 1.0154 241/1073 ━━━━━━━━━━━━━━━━━━━━ 33s 41ms/step - accuracy: 0.4764 - loss: 1.0146 243/1073 ━━━━━━━━━━━━━━━━━━━━ 33s 41ms/step - accuracy: 0.4770 - loss: 1.0139 245/1073 ━━━━━━━━━━━━━━━━━━━━ 33s 41ms/step - accuracy: 0.4777 - loss: 1.0131 247/1073 ━━━━━━━━━━━━━━━━━━━━ 33s 41ms/step - accuracy: 0.4783 - loss: 1.0124 249/1073 ━━━━━━━━━━━━━━━━━━━━ 33s 41ms/step - accuracy: 0.4789 - loss: 1.0117 251/1073 ━━━━━━━━━━━━━━━━━━━━ 33s 41ms/step - accuracy: 0.4795 - loss: 1.0109 253/1073 ━━━━━━━━━━━━━━━━━━━━ 33s 41ms/step - accuracy: 0.4801 - loss: 1.0102 255/1073 ━━━━━━━━━━━━━━━━━━━━ 33s 41ms/step - accuracy: 0.4807 - loss: 1.0095 257/1073 ━━━━━━━━━━━━━━━━━━━━ 33s 41ms/step - accuracy: 0.4813 - loss: 1.0088 259/1073 ━━━━━━━━━━━━━━━━━━━━ 33s 41ms/step - accuracy: 0.4819 - loss: 1.0081 261/1073 ━━━━━━━━━━━━━━━━━━━━ 32s 41ms/step - accuracy: 0.4825 - loss: 1.0074 263/1073 ━━━━━━━━━━━━━━━━━━━━ 32s 41ms/step - accuracy: 0.4830 - loss: 1.0067 265/1073 ━━━━━━━━━━━━━━━━━━━━ 32s 41ms/step - accuracy: 0.4836 - loss: 1.0060 267/1073 ━━━━━━━━━━━━━━━━━━━━ 32s 41ms/step - accuracy: 0.4842 - loss: 1.0054 269/1073 ━━━━━━━━━━━━━━━━━━━━ 32s 41ms/step - accuracy: 0.4847 - loss: 1.0047 271/1073 ━━━━━━━━━━━━━━━━━━━━ 32s 41ms/step - accuracy: 0.4853 - loss: 1.0040 273/1073 ━━━━━━━━━━━━━━━━━━━━ 32s 41ms/step - accuracy: 0.4859 - loss: 1.0033 275/1073 ━━━━━━━━━━━━━━━━━━━━ 32s 41ms/step - accuracy: 0.4864 - loss: 1.0027 277/1073 ━━━━━━━━━━━━━━━━━━━━ 32s 41ms/step - accuracy: 0.4870 - loss: 1.0020 279/1073 ━━━━━━━━━━━━━━━━━━━━ 32s 41ms/step - accuracy: 0.4875 - loss: 1.0014 281/1073 ━━━━━━━━━━━━━━━━━━━━ 32s 41ms/step - accuracy: 0.4880 - loss: 1.0007 283/1073 ━━━━━━━━━━━━━━━━━━━━ 32s 41ms/step - accuracy: 0.4886 - loss: 1.0001 285/1073 ━━━━━━━━━━━━━━━━━━━━ 31s 41ms/step - accuracy: 0.4891 - loss: 0.9994 287/1073 ━━━━━━━━━━━━━━━━━━━━ 31s 41ms/step - accuracy: 0.4896 - loss: 0.9988 289/1073 ━━━━━━━━━━━━━━━━━━━━ 31s 41ms/step - accuracy: 0.4902 - loss: 0.9982 291/1073 ━━━━━━━━━━━━━━━━━━━━ 31s 41ms/step - accuracy: 0.4907 - loss: 0.9975 293/1073 ━━━━━━━━━━━━━━━━━━━━ 31s 41ms/step - accuracy: 0.4912 - loss: 0.9969 295/1073 ━━━━━━━━━━━━━━━━━━━━ 31s 41ms/step - accuracy: 0.4917 - loss: 0.9963 297/1073 ━━━━━━━━━━━━━━━━━━━━ 31s 41ms/step - accuracy: 0.4922 - loss: 0.9957 299/1073 ━━━━━━━━━━━━━━━━━━━━ 31s 41ms/step - accuracy: 0.4927 - loss: 0.9950 301/1073 ━━━━━━━━━━━━━━━━━━━━ 31s 41ms/step - accuracy: 0.4932 - loss: 0.9944 303/1073 ━━━━━━━━━━━━━━━━━━━━ 31s 41ms/step - accuracy: 0.4937 - loss: 0.9938 305/1073 ━━━━━━━━━━━━━━━━━━━━ 31s 41ms/step - accuracy: 0.4942 - loss: 0.9932 307/1073 ━━━━━━━━━━━━━━━━━━━━ 31s 41ms/step - accuracy: 0.4947 - loss: 0.9926 309/1073 ━━━━━━━━━━━━━━━━━━━━ 30s 41ms/step - accuracy: 0.4952 - loss: 0.9920 311/1073 ━━━━━━━━━━━━━━━━━━━━ 30s 41ms/step - accuracy: 0.4957 - loss: 0.9914 313/1073 ━━━━━━━━━━━━━━━━━━━━ 30s 41ms/step - accuracy: 0.4962 - loss: 0.9908 315/1073 ━━━━━━━━━━━━━━━━━━━━ 30s 41ms/step - accuracy: 0.4967 - loss: 0.9902 317/1073 ━━━━━━━━━━━━━━━━━━━━ 30s 41ms/step - accuracy: 0.4972 - loss: 0.9896 319/1073 ━━━━━━━━━━━━━━━━━━━━ 30s 41ms/step - accuracy: 0.4977 - loss: 0.9890 321/1073 ━━━━━━━━━━━━━━━━━━━━ 30s 41ms/step - accuracy: 0.4981 - loss: 0.9885 323/1073 ━━━━━━━━━━━━━━━━━━━━ 30s 41ms/step - accuracy: 0.4986 - loss: 0.9879 325/1073 ━━━━━━━━━━━━━━━━━━━━ 30s 41ms/step - accuracy: 0.4991 - loss: 0.9873 327/1073 ━━━━━━━━━━━━━━━━━━━━ 30s 41ms/step - accuracy: 0.4995 - loss: 0.9868 329/1073 ━━━━━━━━━━━━━━━━━━━━ 30s 41ms/step - accuracy: 0.5000 - loss: 0.9862 331/1073 ━━━━━━━━━━━━━━━━━━━━ 30s 41ms/step - accuracy: 0.5005 - loss: 0.9856 333/1073 ━━━━━━━━━━━━━━━━━━━━ 29s 41ms/step - accuracy: 0.5009 - loss: 0.9851 335/1073 ━━━━━━━━━━━━━━━━━━━━ 29s 41ms/step - accuracy: 0.5014 - loss: 0.9845 337/1073 ━━━━━━━━━━━━━━━━━━━━ 29s 41ms/step - accuracy: 0.5018 - loss: 0.9840 339/1073 ━━━━━━━━━━━━━━━━━━━━ 29s 41ms/step - accuracy: 0.5023 - loss: 0.9834 341/1073 ━━━━━━━━━━━━━━━━━━━━ 29s 41ms/step - accuracy: 0.5027 - loss: 0.9829 343/1073 ━━━━━━━━━━━━━━━━━━━━ 29s 41ms/step - accuracy: 0.5031 - loss: 0.9823 345/1073 ━━━━━━━━━━━━━━━━━━━━ 29s 41ms/step - accuracy: 0.5036 - loss: 0.9818 347/1073 ━━━━━━━━━━━━━━━━━━━━ 29s 41ms/step - accuracy: 0.5040 - loss: 0.9812 349/1073 ━━━━━━━━━━━━━━━━━━━━ 29s 41ms/step - accuracy: 0.5045 - loss: 0.9807 351/1073 ━━━━━━━━━━━━━━━━━━━━ 29s 41ms/step - accuracy: 0.5049 - loss: 0.9802 353/1073 ━━━━━━━━━━━━━━━━━━━━ 29s 41ms/step - accuracy: 0.5053 - loss: 0.9797 355/1073 ━━━━━━━━━━━━━━━━━━━━ 29s 41ms/step - accuracy: 0.5057 - loss: 0.9791 357/1073 ━━━━━━━━━━━━━━━━━━━━ 29s 41ms/step - accuracy: 0.5062 - loss: 0.9786 359/1073 ━━━━━━━━━━━━━━━━━━━━ 28s 41ms/step - accuracy: 0.5066 - loss: 0.9781 361/1073 ━━━━━━━━━━━━━━━━━━━━ 28s 41ms/step - accuracy: 0.5070 - loss: 0.9776 363/1073 ━━━━━━━━━━━━━━━━━━━━ 28s 41ms/step - accuracy: 0.5074 - loss: 0.9770 365/1073 ━━━━━━━━━━━━━━━━━━━━ 28s 41ms/step - accuracy: 0.5078 - loss: 0.9765 367/1073 ━━━━━━━━━━━━━━━━━━━━ 28s 41ms/step - accuracy: 0.5083 - loss: 0.9760 369/1073 ━━━━━━━━━━━━━━━━━━━━ 28s 40ms/step - accuracy: 0.5087 - loss: 0.9755 371/1073 ━━━━━━━━━━━━━━━━━━━━ 28s 40ms/step - accuracy: 0.5091 - loss: 0.9750 373/1073 ━━━━━━━━━━━━━━━━━━━━ 28s 40ms/step - accuracy: 0.5095 - loss: 0.9745 375/1073 ━━━━━━━━━━━━━━━━━━━━ 28s 40ms/step - accuracy: 0.5099 - loss: 0.9740 377/1073 ━━━━━━━━━━━━━━━━━━━━ 28s 40ms/step - accuracy: 0.5103 - loss: 0.9735 379/1073 ━━━━━━━━━━━━━━━━━━━━ 28s 40ms/step - accuracy: 0.5107 - loss: 0.9730 381/1073 ━━━━━━━━━━━━━━━━━━━━ 28s 40ms/step - accuracy: 0.5111 - loss: 0.9725 383/1073 ━━━━━━━━━━━━━━━━━━━━ 27s 40ms/step - accuracy: 0.5115 - loss: 0.9720 385/1073 ━━━━━━━━━━━━━━━━━━━━ 27s 40ms/step - accuracy: 0.5119 - loss: 0.9715 387/1073 ━━━━━━━━━━━━━━━━━━━━ 27s 40ms/step - accuracy: 0.5123 - loss: 0.9710 389/1073 ━━━━━━━━━━━━━━━━━━━━ 27s 40ms/step - accuracy: 0.5127 - loss: 0.9706 391/1073 ━━━━━━━━━━━━━━━━━━━━ 27s 40ms/step - accuracy: 0.5130 - loss: 0.9701 393/1073 ━━━━━━━━━━━━━━━━━━━━ 27s 40ms/step - accuracy: 0.5134 - loss: 0.9696 395/1073 ━━━━━━━━━━━━━━━━━━━━ 27s 40ms/step - accuracy: 0.5138 - loss: 0.9691 397/1073 ━━━━━━━━━━━━━━━━━━━━ 27s 40ms/step - accuracy: 0.5142 - loss: 0.9686 399/1073 ━━━━━━━━━━━━━━━━━━━━ 27s 40ms/step - accuracy: 0.5146 - loss: 0.9682 401/1073 ━━━━━━━━━━━━━━━━━━━━ 27s 40ms/step - accuracy: 0.5150 - loss: 0.9677 403/1073 ━━━━━━━━━━━━━━━━━━━━ 27s 40ms/step - accuracy: 0.5153 - loss: 0.9672 405/1073 ━━━━━━━━━━━━━━━━━━━━ 27s 40ms/step - accuracy: 0.5157 - loss: 0.9668 407/1073 ━━━━━━━━━━━━━━━━━━━━ 26s 40ms/step - accuracy: 0.5161 - loss: 0.9663 409/1073 ━━━━━━━━━━━━━━━━━━━━ 26s 40ms/step - accuracy: 0.5165 - loss: 0.9658 411/1073 ━━━━━━━━━━━━━━━━━━━━ 26s 40ms/step - accuracy: 0.5168 - loss: 0.9654 413/1073 ━━━━━━━━━━━━━━━━━━━━ 26s 40ms/step - accuracy: 0.5172 - loss: 0.9649 415/1073 ━━━━━━━━━━━━━━━━━━━━ 26s 40ms/step - accuracy: 0.5176 - loss: 0.9644 417/1073 ━━━━━━━━━━━━━━━━━━━━ 26s 40ms/step - accuracy: 0.5179 - loss: 0.9640 419/1073 ━━━━━━━━━━━━━━━━━━━━ 26s 40ms/step - accuracy: 0.5183 - loss: 0.9635 421/1073 ━━━━━━━━━━━━━━━━━━━━ 26s 40ms/step - accuracy: 0.5186 - loss: 0.9631 423/1073 ━━━━━━━━━━━━━━━━━━━━ 26s 40ms/step - accuracy: 0.5190 - loss: 0.9626 425/1073 ━━━━━━━━━━━━━━━━━━━━ 26s 40ms/step - accuracy: 0.5194 - loss: 0.9622 427/1073 ━━━━━━━━━━━━━━━━━━━━ 26s 40ms/step - accuracy: 0.5197 - loss: 0.9617 429/1073 ━━━━━━━━━━━━━━━━━━━━ 26s 40ms/step - accuracy: 0.5201 - loss: 0.9613 431/1073 ━━━━━━━━━━━━━━━━━━━━ 25s 40ms/step - accuracy: 0.5204 - loss: 0.9609 433/1073 ━━━━━━━━━━━━━━━━━━━━ 25s 40ms/step - accuracy: 0.5208 - loss: 0.9604 435/1073 ━━━━━━━━━━━━━━━━━━━━ 25s 40ms/step - accuracy: 0.5211 - loss: 0.9600 437/1073 ━━━━━━━━━━━━━━━━━━━━ 25s 40ms/step - accuracy: 0.5215 - loss: 0.9595 439/1073 ━━━━━━━━━━━━━━━━━━━━ 25s 40ms/step - accuracy: 0.5218 - loss: 0.9591 441/1073 ━━━━━━━━━━━━━━━━━━━━ 25s 40ms/step - accuracy: 0.5221 - loss: 0.9587 443/1073 ━━━━━━━━━━━━━━━━━━━━ 25s 40ms/step - accuracy: 0.5225 - loss: 0.9582 445/1073 ━━━━━━━━━━━━━━━━━━━━ 25s 40ms/step - accuracy: 0.5228 - loss: 0.9578 447/1073 ━━━━━━━━━━━━━━━━━━━━ 25s 40ms/step - accuracy: 0.5232 - loss: 0.9574 449/1073 ━━━━━━━━━━━━━━━━━━━━ 25s 40ms/step - accuracy: 0.5235 - loss: 0.9570 451/1073 ━━━━━━━━━━━━━━━━━━━━ 25s 40ms/step - accuracy: 0.5238 - loss: 0.9565 453/1073 ━━━━━━━━━━━━━━━━━━━━ 25s 40ms/step - accuracy: 0.5242 - loss: 0.9561 455/1073 ━━━━━━━━━━━━━━━━━━━━ 25s 40ms/step - accuracy: 0.5245 - loss: 0.9557 457/1073 ━━━━━━━━━━━━━━━━━━━━ 24s 40ms/step - accuracy: 0.5248 - loss: 0.9553 459/1073 ━━━━━━━━━━━━━━━━━━━━ 24s 40ms/step - accuracy: 0.5252 - loss: 0.9549 461/1073 ━━━━━━━━━━━━━━━━━━━━ 24s 40ms/step - accuracy: 0.5255 - loss: 0.9545 463/1073 ━━━━━━━━━━━━━━━━━━━━ 24s 40ms/step - accuracy: 0.5258 - loss: 0.9540 465/1073 ━━━━━━━━━━━━━━━━━━━━ 24s 40ms/step - accuracy: 0.5261 - loss: 0.9536 467/1073 ━━━━━━━━━━━━━━━━━━━━ 24s 40ms/step - accuracy: 0.5265 - loss: 0.9532 469/1073 ━━━━━━━━━━━━━━━━━━━━ 24s 40ms/step - accuracy: 0.5268 - loss: 0.9528 471/1073 ━━━━━━━━━━━━━━━━━━━━ 24s 40ms/step - accuracy: 0.5271 - loss: 0.9524 473/1073 ━━━━━━━━━━━━━━━━━━━━ 24s 40ms/step - accuracy: 0.5274 - loss: 0.9520 475/1073 ━━━━━━━━━━━━━━━━━━━━ 24s 40ms/step - accuracy: 0.5277 - loss: 0.9516 477/1073 ━━━━━━━━━━━━━━━━━━━━ 24s 40ms/step - accuracy: 0.5280 - loss: 0.9512 479/1073 ━━━━━━━━━━━━━━━━━━━━ 24s 40ms/step - accuracy: 0.5284 - loss: 0.9508 481/1073 ━━━━━━━━━━━━━━━━━━━━ 23s 40ms/step - accuracy: 0.5287 - loss: 0.9504 483/1073 ━━━━━━━━━━━━━━━━━━━━ 23s 40ms/step - accuracy: 0.5290 - loss: 0.9500 485/1073 ━━━━━━━━━━━━━━━━━━━━ 23s 40ms/step - accuracy: 0.5293 - loss: 0.9496 487/1073 ━━━━━━━━━━━━━━━━━━━━ 23s 40ms/step - accuracy: 0.5296 - loss: 0.9492 489/1073 ━━━━━━━━━━━━━━━━━━━━ 23s 40ms/step - accuracy: 0.5299 - loss: 0.9488 491/1073 ━━━━━━━━━━━━━━━━━━━━ 23s 40ms/step - accuracy: 0.5302 - loss: 0.9484 493/1073 ━━━━━━━━━━━━━━━━━━━━ 23s 40ms/step - accuracy: 0.5305 - loss: 0.9480 495/1073 ━━━━━━━━━━━━━━━━━━━━ 23s 40ms/step - accuracy: 0.5308 - loss: 0.9477 497/1073 ━━━━━━━━━━━━━━━━━━━━ 23s 40ms/step - accuracy: 0.5311 - loss: 0.9473 499/1073 ━━━━━━━━━━━━━━━━━━━━ 23s 40ms/step - accuracy: 0.5314 - loss: 0.9469 501/1073 ━━━━━━━━━━━━━━━━━━━━ 23s 40ms/step - accuracy: 0.5317 - loss: 0.9465 503/1073 ━━━━━━━━━━━━━━━━━━━━ 23s 40ms/step - accuracy: 0.5320 - loss: 0.9461 505/1073 ━━━━━━━━━━━━━━━━━━━━ 22s 40ms/step - accuracy: 0.5323 - loss: 0.9458 507/1073 ━━━━━━━━━━━━━━━━━━━━ 22s 40ms/step - accuracy: 0.5326 - loss: 0.9454 509/1073 ━━━━━━━━━━━━━━━━━━━━ 22s 40ms/step - accuracy: 0.5329 - loss: 0.9450 511/1073 ━━━━━━━━━━━━━━━━━━━━ 22s 40ms/step - accuracy: 0.5332 - loss: 0.9446 513/1073 ━━━━━━━━━━━━━━━━━━━━ 22s 40ms/step - accuracy: 0.5334 - loss: 0.9443 515/1073 ━━━━━━━━━━━━━━━━━━━━ 22s 40ms/step - accuracy: 0.5337 - loss: 0.9439 517/1073 ━━━━━━━━━━━━━━━━━━━━ 22s 40ms/step - accuracy: 0.5340 - loss: 0.9435 519/1073 ━━━━━━━━━━━━━━━━━━━━ 22s 40ms/step - accuracy: 0.5343 - loss: 0.9432 521/1073 ━━━━━━━━━━━━━━━━━━━━ 22s 40ms/step - accuracy: 0.5346 - loss: 0.9428 523/1073 ━━━━━━━━━━━━━━━━━━━━ 22s 40ms/step - accuracy: 0.5349 - loss: 0.9424 525/1073 ━━━━━━━━━━━━━━━━━━━━ 22s 40ms/step - accuracy: 0.5351 - loss: 0.9421 527/1073 ━━━━━━━━━━━━━━━━━━━━ 22s 40ms/step - accuracy: 0.5354 - loss: 0.9417 529/1073 ━━━━━━━━━━━━━━━━━━━━ 22s 40ms/step - accuracy: 0.5357 - loss: 0.9414 531/1073 ━━━━━━━━━━━━━━━━━━━━ 21s 40ms/step - accuracy: 0.5360 - loss: 0.9410 533/1073 ━━━━━━━━━━━━━━━━━━━━ 21s 40ms/step - accuracy: 0.5363 - loss: 0.9406 535/1073 ━━━━━━━━━━━━━━━━━━━━ 21s 40ms/step - accuracy: 0.5365 - loss: 0.9403 537/1073 ━━━━━━━━━━━━━━━━━━━━ 21s 40ms/step - accuracy: 0.5368 - loss: 0.9399 539/1073 ━━━━━━━━━━━━━━━━━━━━ 21s 40ms/step - accuracy: 0.5371 - loss: 0.9396 541/1073 ━━━━━━━━━━━━━━━━━━━━ 21s 40ms/step - accuracy: 0.5374 - loss: 0.9392 543/1073 ━━━━━━━━━━━━━━━━━━━━ 21s 40ms/step - accuracy: 0.5376 - loss: 0.9389 545/1073 ━━━━━━━━━━━━━━━━━━━━ 21s 40ms/step - accuracy: 0.5379 - loss: 0.9385 547/1073 ━━━━━━━━━━━━━━━━━━━━ 21s 40ms/step - accuracy: 0.5382 - loss: 0.9382 549/1073 ━━━━━━━━━━━━━━━━━━━━ 21s 40ms/step - accuracy: 0.5384 - loss: 0.9378 551/1073 ━━━━━━━━━━━━━━━━━━━━ 21s 40ms/step - accuracy: 0.5387 - loss: 0.9375 553/1073 ━━━━━━━━━━━━━━━━━━━━ 21s 40ms/step - accuracy: 0.5390 - loss: 0.9372 555/1073 ━━━━━━━━━━━━━━━━━━━━ 20s 40ms/step - accuracy: 0.5392 - loss: 0.9368 557/1073 ━━━━━━━━━━━━━━━━━━━━ 20s 40ms/step - accuracy: 0.5395 - loss: 0.9365 559/1073 ━━━━━━━━━━━━━━━━━━━━ 20s 40ms/step - accuracy: 0.5398 - loss: 0.9361 561/1073 ━━━━━━━━━━━━━━━━━━━━ 20s 40ms/step - accuracy: 0.5400 - loss: 0.9358 563/1073 ━━━━━━━━━━━━━━━━━━━━ 20s 40ms/step - accuracy: 0.5403 - loss: 0.9355 565/1073 ━━━━━━━━━━━━━━━━━━━━ 20s 40ms/step - accuracy: 0.5405 - loss: 0.9351 567/1073 ━━━━━━━━━━━━━━━━━━━━ 20s 40ms/step - accuracy: 0.5408 - loss: 0.9348 569/1073 ━━━━━━━━━━━━━━━━━━━━ 20s 40ms/step - accuracy: 0.5410 - loss: 0.9345 571/1073 ━━━━━━━━━━━━━━━━━━━━ 20s 40ms/step - accuracy: 0.5413 - loss: 0.9341 573/1073 ━━━━━━━━━━━━━━━━━━━━ 20s 40ms/step - accuracy: 0.5416 - loss: 0.9338 575/1073 ━━━━━━━━━━━━━━━━━━━━ 20s 40ms/step - accuracy: 0.5418 - loss: 0.9335 577/1073 ━━━━━━━━━━━━━━━━━━━━ 20s 40ms/step - accuracy: 0.5421 - loss: 0.9331 579/1073 ━━━━━━━━━━━━━━━━━━━━ 20s 40ms/step - accuracy: 0.5423 - loss: 0.9328 581/1073 ━━━━━━━━━━━━━━━━━━━━ 19s 40ms/step - accuracy: 0.5426 - loss: 0.9325 583/1073 ━━━━━━━━━━━━━━━━━━━━ 19s 40ms/step - accuracy: 0.5428 - loss: 0.9321 585/1073 ━━━━━━━━━━━━━━━━━━━━ 19s 40ms/step - accuracy: 0.5431 - loss: 0.9318 587/1073 ━━━━━━━━━━━━━━━━━━━━ 19s 40ms/step - accuracy: 0.5433 - loss: 0.9315 589/1073 ━━━━━━━━━━━━━━━━━━━━ 19s 40ms/step - accuracy: 0.5436 - loss: 0.9312 591/1073 ━━━━━━━━━━━━━━━━━━━━ 19s 40ms/step - accuracy: 0.5438 - loss: 0.9308 593/1073 ━━━━━━━━━━━━━━━━━━━━ 19s 40ms/step - accuracy: 0.5441 - loss: 0.9305 595/1073 ━━━━━━━━━━━━━━━━━━━━ 19s 40ms/step - accuracy: 0.5443 - loss: 0.9302 597/1073 ━━━━━━━━━━━━━━━━━━━━ 19s 40ms/step - accuracy: 0.5446 - loss: 0.9299 599/1073 ━━━━━━━━━━━━━━━━━━━━ 19s 40ms/step - accuracy: 0.5448 - loss: 0.9296 601/1073 ━━━━━━━━━━━━━━━━━━━━ 19s 40ms/step - accuracy: 0.5450 - loss: 0.9293 603/1073 ━━━━━━━━━━━━━━━━━━━━ 19s 40ms/step - accuracy: 0.5453 - loss: 0.9289 605/1073 ━━━━━━━━━━━━━━━━━━━━ 18s 40ms/step - accuracy: 0.5455 - loss: 0.9286 607/1073 ━━━━━━━━━━━━━━━━━━━━ 18s 40ms/step - accuracy: 0.5458 - loss: 0.9283 609/1073 ━━━━━━━━━━━━━━━━━━━━ 18s 40ms/step - accuracy: 0.5460 - loss: 0.9280 611/1073 ━━━━━━━━━━━━━━━━━━━━ 18s 40ms/step - accuracy: 0.5462 - loss: 0.9277 613/1073 ━━━━━━━━━━━━━━━━━━━━ 18s 40ms/step - accuracy: 0.5465 - loss: 0.9274 615/1073 ━━━━━━━━━━━━━━━━━━━━ 18s 40ms/step - accuracy: 0.5467 - loss: 0.9271 617/1073 ━━━━━━━━━━━━━━━━━━━━ 18s 40ms/step - accuracy: 0.5470 - loss: 0.9267 619/1073 ━━━━━━━━━━━━━━━━━━━━ 18s 40ms/step - accuracy: 0.5472 - loss: 0.9264 621/1073 ━━━━━━━━━━━━━━━━━━━━ 18s 40ms/step - accuracy: 0.5474 - loss: 0.9261 623/1073 ━━━━━━━━━━━━━━━━━━━━ 18s 40ms/step - accuracy: 0.5477 - loss: 0.9258 625/1073 ━━━━━━━━━━━━━━━━━━━━ 18s 40ms/step - accuracy: 0.5479 - loss: 0.9255 627/1073 ━━━━━━━━━━━━━━━━━━━━ 18s 40ms/step - accuracy: 0.5481 - loss: 0.9252 629/1073 ━━━━━━━━━━━━━━━━━━━━ 17s 40ms/step - accuracy: 0.5484 - loss: 0.9249 631/1073 ━━━━━━━━━━━━━━━━━━━━ 17s 40ms/step - accuracy: 0.5486 - loss: 0.9246 633/1073 ━━━━━━━━━━━━━━━━━━━━ 17s 40ms/step - accuracy: 0.5488 - loss: 0.9243 635/1073 ━━━━━━━━━━━━━━━━━━━━ 17s 40ms/step - accuracy: 0.5490 - loss: 0.9240 637/1073 ━━━━━━━━━━━━━━━━━━━━ 17s 40ms/step - accuracy: 0.5493 - loss: 0.9237 639/1073 ━━━━━━━━━━━━━━━━━━━━ 17s 40ms/step - accuracy: 0.5495 - loss: 0.9234 641/1073 ━━━━━━━━━━━━━━━━━━━━ 17s 40ms/step - accuracy: 0.5497 - loss: 0.9231 643/1073 ━━━━━━━━━━━━━━━━━━━━ 17s 40ms/step - accuracy: 0.5500 - loss: 0.9228 645/1073 ━━━━━━━━━━━━━━━━━━━━ 17s 40ms/step - accuracy: 0.5502 - loss: 0.9225 647/1073 ━━━━━━━━━━━━━━━━━━━━ 17s 40ms/step - accuracy: 0.5504 - loss: 0.9222 649/1073 ━━━━━━━━━━━━━━━━━━━━ 17s 40ms/step - accuracy: 0.5506 - loss: 0.9219 651/1073 ━━━━━━━━━━━━━━━━━━━━ 17s 40ms/step - accuracy: 0.5508 - loss: 0.9216 653/1073 ━━━━━━━━━━━━━━━━━━━━ 16s 40ms/step - accuracy: 0.5511 - loss: 0.9213 655/1073 ━━━━━━━━━━━━━━━━━━━━ 16s 40ms/step - accuracy: 0.5513 - loss: 0.9210 657/1073 ━━━━━━━━━━━━━━━━━━━━ 16s 40ms/step - accuracy: 0.5515 - loss: 0.9208 659/1073 ━━━━━━━━━━━━━━━━━━━━ 16s 40ms/step - accuracy: 0.5517 - loss: 0.9205 661/1073 ━━━━━━━━━━━━━━━━━━━━ 16s 40ms/step - accuracy: 0.5519 - loss: 0.9202 663/1073 ━━━━━━━━━━━━━━━━━━━━ 16s 40ms/step - accuracy: 0.5522 - loss: 0.9199 665/1073 ━━━━━━━━━━━━━━━━━━━━ 16s 40ms/step - accuracy: 0.5524 - loss: 0.9196 667/1073 ━━━━━━━━━━━━━━━━━━━━ 16s 40ms/step - accuracy: 0.5526 - loss: 0.9193 669/1073 ━━━━━━━━━━━━━━━━━━━━ 16s 40ms/step - accuracy: 0.5528 - loss: 0.9190 671/1073 ━━━━━━━━━━━━━━━━━━━━ 16s 40ms/step - accuracy: 0.5530 - loss: 0.9187 673/1073 ━━━━━━━━━━━━━━━━━━━━ 16s 40ms/step - accuracy: 0.5532 - loss: 0.9185 675/1073 ━━━━━━━━━━━━━━━━━━━━ 16s 40ms/step - accuracy: 0.5535 - loss: 0.9182 677/1073 ━━━━━━━━━━━━━━━━━━━━ 16s 40ms/step - accuracy: 0.5537 - loss: 0.9179 679/1073 ━━━━━━━━━━━━━━━━━━━━ 15s 40ms/step - accuracy: 0.5539 - loss: 0.9176 681/1073 ━━━━━━━━━━━━━━━━━━━━ 15s 40ms/step - accuracy: 0.5541 - loss: 0.9173 683/1073 ━━━━━━━━━━━━━━━━━━━━ 15s 40ms/step - accuracy: 0.5543 - loss: 0.9171 685/1073 ━━━━━━━━━━━━━━━━━━━━ 15s 40ms/step - accuracy: 0.5545 - loss: 0.9168 687/1073 ━━━━━━━━━━━━━━━━━━━━ 15s 40ms/step - accuracy: 0.5547 - loss: 0.9165 689/1073 ━━━━━━━━━━━━━━━━━━━━ 15s 40ms/step - accuracy: 0.5549 - loss: 0.9162 691/1073 ━━━━━━━━━━━━━━━━━━━━ 15s 40ms/step - accuracy: 0.5551 - loss: 0.9159 693/1073 ━━━━━━━━━━━━━━━━━━━━ 15s 40ms/step - accuracy: 0.5553 - loss: 0.9157 695/1073 ━━━━━━━━━━━━━━━━━━━━ 15s 40ms/step - accuracy: 0.5555 - loss: 0.9154 697/1073 ━━━━━━━━━━━━━━━━━━━━ 15s 40ms/step - accuracy: 0.5557 - loss: 0.9151 699/1073 ━━━━━━━━━━━━━━━━━━━━ 15s 40ms/step - accuracy: 0.5559 - loss: 0.9149 701/1073 ━━━━━━━━━━━━━━━━━━━━ 15s 40ms/step - accuracy: 0.5561 - loss: 0.9146 703/1073 ━━━━━━━━━━━━━━━━━━━━ 14s 40ms/step - accuracy: 0.5564 - loss: 0.9143 705/1073 ━━━━━━━━━━━━━━━━━━━━ 14s 40ms/step - accuracy: 0.5566 - loss: 0.9140 707/1073 ━━━━━━━━━━━━━━━━━━━━ 14s 40ms/step - accuracy: 0.5568 - loss: 0.9138 709/1073 ━━━━━━━━━━━━━━━━━━━━ 14s 40ms/step - accuracy: 0.5570 - loss: 0.9135 711/1073 ━━━━━━━━━━━━━━━━━━━━ 14s 40ms/step - accuracy: 0.5572 - loss: 0.9132 713/1073 ━━━━━━━━━━━━━━━━━━━━ 14s 40ms/step - accuracy: 0.5574 - loss: 0.9130 715/1073 ━━━━━━━━━━━━━━━━━━━━ 14s 40ms/step - accuracy: 0.5576 - loss: 0.9127 717/1073 ━━━━━━━━━━━━━━━━━━━━ 14s 40ms/step - accuracy: 0.5577 - loss: 0.9124 719/1073 ━━━━━━━━━━━━━━━━━━━━ 14s 40ms/step - accuracy: 0.5579 - loss: 0.9122 721/1073 ━━━━━━━━━━━━━━━━━━━━ 14s 40ms/step - accuracy: 0.5581 - loss: 0.9119 723/1073 ━━━━━━━━━━━━━━━━━━━━ 14s 40ms/step - accuracy: 0.5583 - loss: 0.9117 725/1073 ━━━━━━━━━━━━━━━━━━━━ 14s 40ms/step - accuracy: 0.5585 - loss: 0.9114 727/1073 ━━━━━━━━━━━━━━━━━━━━ 13s 40ms/step - accuracy: 0.5587 - loss: 0.9111 729/1073 ━━━━━━━━━━━━━━━━━━━━ 13s 40ms/step - accuracy: 0.5589 - loss: 0.9109 731/1073 ━━━━━━━━━━━━━━━━━━━━ 13s 40ms/step - accuracy: 0.5591 - loss: 0.9106 733/1073 ━━━━━━━━━━━━━━━━━━━━ 13s 40ms/step - accuracy: 0.5593 - loss: 0.9104 735/1073 ━━━━━━━━━━━━━━━━━━━━ 13s 40ms/step - accuracy: 0.5595 - loss: 0.9101 737/1073 ━━━━━━━━━━━━━━━━━━━━ 13s 40ms/step - accuracy: 0.5597 - loss: 0.9098 739/1073 ━━━━━━━━━━━━━━━━━━━━ 13s 40ms/step - accuracy: 0.5599 - loss: 0.9096 741/1073 ━━━━━━━━━━━━━━━━━━━━ 13s 40ms/step - accuracy: 0.5601 - loss: 0.9093 743/1073 ━━━━━━━━━━━━━━━━━━━━ 13s 40ms/step - accuracy: 0.5603 - loss: 0.9091 745/1073 ━━━━━━━━━━━━━━━━━━━━ 13s 40ms/step - accuracy: 0.5605 - loss: 0.9088 747/1073 ━━━━━━━━━━━━━━━━━━━━ 13s 40ms/step - accuracy: 0.5606 - loss: 0.9086 749/1073 ━━━━━━━━━━━━━━━━━━━━ 13s 40ms/step - accuracy: 0.5608 - loss: 0.9083 751/1073 ━━━━━━━━━━━━━━━━━━━━ 13s 40ms/step - accuracy: 0.5610 - loss: 0.9081 753/1073 ━━━━━━━━━━━━━━━━━━━━ 12s 40ms/step - accuracy: 0.5612 - loss: 0.9078 755/1073 ━━━━━━━━━━━━━━━━━━━━ 12s 40ms/step - accuracy: 0.5614 - loss: 0.9076 757/1073 ━━━━━━━━━━━━━━━━━━━━ 12s 40ms/step - accuracy: 0.5616 - loss: 0.9073 759/1073 ━━━━━━━━━━━━━━━━━━━━ 12s 40ms/step - accuracy: 0.5618 - loss: 0.9071 761/1073 ━━━━━━━━━━━━━━━━━━━━ 12s 40ms/step - accuracy: 0.5619 - loss: 0.9068 763/1073 ━━━━━━━━━━━━━━━━━━━━ 12s 40ms/step - accuracy: 0.5621 - loss: 0.9066 765/1073 ━━━━━━━━━━━━━━━━━━━━ 12s 40ms/step - accuracy: 0.5623 - loss: 0.9063 767/1073 ━━━━━━━━━━━━━━━━━━━━ 12s 40ms/step - accuracy: 0.5625 - loss: 0.9061 769/1073 ━━━━━━━━━━━━━━━━━━━━ 12s 40ms/step - accuracy: 0.5627 - loss: 0.9058 771/1073 ━━━━━━━━━━━━━━━━━━━━ 12s 40ms/step - accuracy: 0.5629 - loss: 0.9056 773/1073 ━━━━━━━━━━━━━━━━━━━━ 12s 40ms/step - accuracy: 0.5630 - loss: 0.9053 775/1073 ━━━━━━━━━━━━━━━━━━━━ 12s 40ms/step - accuracy: 0.5632 - loss: 0.9051 777/1073 ━━━━━━━━━━━━━━━━━━━━ 11s 40ms/step - accuracy: 0.5634 - loss: 0.9048 779/1073 ━━━━━━━━━━━━━━━━━━━━ 11s 40ms/step - accuracy: 0.5636 - loss: 0.9046 781/1073 ━━━━━━━━━━━━━━━━━━━━ 11s 40ms/step - accuracy: 0.5638 - loss: 0.9044 783/1073 ━━━━━━━━━━━━━━━━━━━━ 11s 40ms/step - accuracy: 0.5639 - loss: 0.9041 785/1073 ━━━━━━━━━━━━━━━━━━━━ 11s 40ms/step - accuracy: 0.5641 - loss: 0.9039 787/1073 ━━━━━━━━━━━━━━━━━━━━ 11s 40ms/step - accuracy: 0.5643 - loss: 0.9036 789/1073 ━━━━━━━━━━━━━━━━━━━━ 11s 40ms/step - accuracy: 0.5645 - loss: 0.9034 791/1073 ━━━━━━━━━━━━━━━━━━━━ 11s 40ms/step - accuracy: 0.5646 - loss: 0.9032 793/1073 ━━━━━━━━━━━━━━━━━━━━ 11s 40ms/step - accuracy: 0.5648 - loss: 0.9029 795/1073 ━━━━━━━━━━━━━━━━━━━━ 11s 40ms/step - accuracy: 0.5650 - loss: 0.9027 797/1073 ━━━━━━━━━━━━━━━━━━━━ 11s 40ms/step - accuracy: 0.5652 - loss: 0.9024 799/1073 ━━━━━━━━━━━━━━━━━━━━ 11s 40ms/step - accuracy: 0.5653 - loss: 0.9022 801/1073 ━━━━━━━━━━━━━━━━━━━━ 10s 40ms/step - accuracy: 0.5655 - loss: 0.9020 803/1073 ━━━━━━━━━━━━━━━━━━━━ 10s 40ms/step - accuracy: 0.5657 - loss: 0.9017 805/1073 ━━━━━━━━━━━━━━━━━━━━ 10s 40ms/step - accuracy: 0.5659 - loss: 0.9015 807/1073 ━━━━━━━━━━━━━━━━━━━━ 10s 40ms/step - accuracy: 0.5660 - loss: 0.9013 809/1073 ━━━━━━━━━━━━━━━━━━━━ 10s 40ms/step - accuracy: 0.5662 - loss: 0.9010 811/1073 ━━━━━━━━━━━━━━━━━━━━ 10s 40ms/step - accuracy: 0.5664 - loss: 0.9008 813/1073 ━━━━━━━━━━━━━━━━━━━━ 10s 40ms/step - accuracy: 0.5665 - loss: 0.9006 815/1073 ━━━━━━━━━━━━━━━━━━━━ 10s 40ms/step - accuracy: 0.5667 - loss: 0.9003 817/1073 ━━━━━━━━━━━━━━━━━━━━ 10s 40ms/step - accuracy: 0.5669 - loss: 0.9001 819/1073 ━━━━━━━━━━━━━━━━━━━━ 10s 40ms/step - accuracy: 0.5671 - loss: 0.8999 821/1073 ━━━━━━━━━━━━━━━━━━━━ 10s 40ms/step - accuracy: 0.5672 - loss: 0.8997 823/1073 ━━━━━━━━━━━━━━━━━━━━ 10s 40ms/step - accuracy: 0.5674 - loss: 0.8994 825/1073 ━━━━━━━━━━━━━━━━━━━━ 10s 40ms/step - accuracy: 0.5676 - loss: 0.8992 827/1073 ━━━━━━━━━━━━━━━━━━━━ 9s 40ms/step - accuracy: 0.5677 - loss: 0.8990 829/1073 ━━━━━━━━━━━━━━━━━━━━ 9s 40ms/step - accuracy: 0.5679 - loss: 0.8987 831/1073 ━━━━━━━━━━━━━━━━━━━━ 9s 40ms/step - accuracy: 0.5681 - loss: 0.8985 833/1073 ━━━━━━━━━━━━━━━━━━━━ 9s 40ms/step - accuracy: 0.5682 - loss: 0.8983 835/1073 ━━━━━━━━━━━━━━━━━━━━ 9s 40ms/step - accuracy: 0.5684 - loss: 0.8981 837/1073 ━━━━━━━━━━━━━━━━━━━━ 9s 40ms/step - accuracy: 0.5686 - loss: 0.8978 839/1073 ━━━━━━━━━━━━━━━━━━━━ 9s 40ms/step - accuracy: 0.5687 - loss: 0.8976 841/1073 ━━━━━━━━━━━━━━━━━━━━ 9s 40ms/step - accuracy: 0.5689 - loss: 0.8974 843/1073 ━━━━━━━━━━━━━━━━━━━━ 9s 40ms/step - accuracy: 0.5690 - loss: 0.8972 845/1073 ━━━━━━━━━━━━━━━━━━━━ 9s 40ms/step - accuracy: 0.5692 - loss: 0.8969 847/1073 ━━━━━━━━━━━━━━━━━━━━ 9s 40ms/step - accuracy: 0.5694 - loss: 0.8967 849/1073 ━━━━━━━━━━━━━━━━━━━━ 9s 40ms/step - accuracy: 0.5695 - loss: 0.8965 851/1073 ━━━━━━━━━━━━━━━━━━━━ 8s 40ms/step - accuracy: 0.5697 - loss: 0.8963 853/1073 ━━━━━━━━━━━━━━━━━━━━ 8s 40ms/step - accuracy: 0.5699 - loss: 0.8961 855/1073 ━━━━━━━━━━━━━━━━━━━━ 8s 40ms/step - accuracy: 0.5700 - loss: 0.8958 857/1073 ━━━━━━━━━━━━━━━━━━━━ 8s 40ms/step - accuracy: 0.5702 - loss: 0.8956 859/1073 ━━━━━━━━━━━━━━━━━━━━ 8s 40ms/step - accuracy: 0.5703 - loss: 0.8954 861/1073 ━━━━━━━━━━━━━━━━━━━━ 8s 40ms/step - accuracy: 0.5705 - loss: 0.8952 863/1073 ━━━━━━━━━━━━━━━━━━━━ 8s 40ms/step - accuracy: 0.5707 - loss: 0.8950 865/1073 ━━━━━━━━━━━━━━━━━━━━ 8s 40ms/step - accuracy: 0.5708 - loss: 0.8948 867/1073 ━━━━━━━━━━━━━━━━━━━━ 8s 40ms/step - accuracy: 0.5710 - loss: 0.8945 869/1073 ━━━━━━━━━━━━━━━━━━━━ 8s 40ms/step - accuracy: 0.5711 - loss: 0.8943 871/1073 ━━━━━━━━━━━━━━━━━━━━ 8s 40ms/step - accuracy: 0.5713 - loss: 0.8941 873/1073 ━━━━━━━━━━━━━━━━━━━━ 8s 40ms/step - accuracy: 0.5714 - loss: 0.8939 875/1073 ━━━━━━━━━━━━━━━━━━━━ 8s 40ms/step - accuracy: 0.5716 - loss: 0.8937 877/1073 ━━━━━━━━━━━━━━━━━━━━ 7s 40ms/step - accuracy: 0.5718 - loss: 0.8935 879/1073 ━━━━━━━━━━━━━━━━━━━━ 7s 40ms/step - accuracy: 0.5719 - loss: 0.8932 881/1073 ━━━━━━━━━━━━━━━━━━━━ 7s 40ms/step - accuracy: 0.5721 - loss: 0.8930 883/1073 ━━━━━━━━━━━━━━━━━━━━ 7s 40ms/step - accuracy: 0.5722 - loss: 0.8928 885/1073 ━━━━━━━━━━━━━━━━━━━━ 7s 40ms/step - accuracy: 0.5724 - loss: 0.8926 887/1073 ━━━━━━━━━━━━━━━━━━━━ 7s 40ms/step - accuracy: 0.5725 - loss: 0.8924 889/1073 ━━━━━━━━━━━━━━━━━━━━ 7s 40ms/step - accuracy: 0.5727 - loss: 0.8922 891/1073 ━━━━━━━━━━━━━━━━━━━━ 7s 40ms/step - accuracy: 0.5728 - loss: 0.8920 893/1073 ━━━━━━━━━━━━━━━━━━━━ 7s 40ms/step - accuracy: 0.5730 - loss: 0.8918 895/1073 ━━━━━━━━━━━━━━━━━━━━ 7s 40ms/step - accuracy: 0.5731 - loss: 0.8916 897/1073 ━━━━━━━━━━━━━━━━━━━━ 7s 40ms/step - accuracy: 0.5733 - loss: 0.8913 899/1073 ━━━━━━━━━━━━━━━━━━━━ 7s 40ms/step - accuracy: 0.5734 - loss: 0.8911 901/1073 ━━━━━━━━━━━━━━━━━━━━ 6s 40ms/step - accuracy: 0.5736 - loss: 0.8909 903/1073 ━━━━━━━━━━━━━━━━━━━━ 6s 40ms/step - accuracy: 0.5737 - loss: 0.8907 905/1073 ━━━━━━━━━━━━━━━━━━━━ 6s 40ms/step - accuracy: 0.5739 - loss: 0.8905 907/1073 ━━━━━━━━━━━━━━━━━━━━ 6s 40ms/step - accuracy: 0.5740 - loss: 0.8903 909/1073 ━━━━━━━━━━━━━━━━━━━━ 6s 40ms/step - accuracy: 0.5742 - loss: 0.8901 911/1073 ━━━━━━━━━━━━━━━━━━━━ 6s 40ms/step - accuracy: 0.5743 - loss: 0.8899 913/1073 ━━━━━━━━━━━━━━━━━━━━ 6s 40ms/step - accuracy: 0.5745 - loss: 0.8897 915/1073 ━━━━━━━━━━━━━━━━━━━━ 6s 40ms/step - accuracy: 0.5746 - loss: 0.8895 917/1073 ━━━━━━━━━━━━━━━━━━━━ 6s 40ms/step - accuracy: 0.5748 - loss: 0.8893 919/1073 ━━━━━━━━━━━━━━━━━━━━ 6s 40ms/step - accuracy: 0.5749 - loss: 0.8891 921/1073 ━━━━━━━━━━━━━━━━━━━━ 6s 40ms/step - accuracy: 0.5751 - loss: 0.8889 923/1073 ━━━━━━━━━━━━━━━━━━━━ 6s 40ms/step - accuracy: 0.5752 - loss: 0.8887 925/1073 ━━━━━━━━━━━━━━━━━━━━ 5s 40ms/step - accuracy: 0.5754 - loss: 0.8885 927/1073 ━━━━━━━━━━━━━━━━━━━━ 5s 40ms/step - accuracy: 0.5755 - loss: 0.8883 929/1073 ━━━━━━━━━━━━━━━━━━━━ 5s 40ms/step - accuracy: 0.5757 - loss: 0.8880 931/1073 ━━━━━━━━━━━━━━━━━━━━ 5s 40ms/step - accuracy: 0.5758 - loss: 0.8878 933/1073 ━━━━━━━━━━━━━━━━━━━━ 5s 40ms/step - accuracy: 0.5760 - loss: 0.8876 935/1073 ━━━━━━━━━━━━━━━━━━━━ 5s 40ms/step - accuracy: 0.5761 - loss: 0.8874 937/1073 ━━━━━━━━━━━━━━━━━━━━ 5s 40ms/step - accuracy: 0.5762 - loss: 0.8872 939/1073 ━━━━━━━━━━━━━━━━━━━━ 5s 40ms/step - accuracy: 0.5764 - loss: 0.8870 941/1073 ━━━━━━━━━━━━━━━━━━━━ 5s 40ms/step - accuracy: 0.5765 - loss: 0.8868 943/1073 ━━━━━━━━━━━━━━━━━━━━ 5s 40ms/step - accuracy: 0.5767 - loss: 0.8866 945/1073 ━━━━━━━━━━━━━━━━━━━━ 5s 40ms/step - accuracy: 0.5768 - loss: 0.8865 947/1073 ━━━━━━━━━━━━━━━━━━━━ 5s 40ms/step - accuracy: 0.5770 - loss: 0.8863 949/1073 ━━━━━━━━━━━━━━━━━━━━ 5s 40ms/step - accuracy: 0.5771 - loss: 0.8861 951/1073 ━━━━━━━━━━━━━━━━━━━━ 4s 40ms/step - accuracy: 0.5772 - loss: 0.8859 953/1073 ━━━━━━━━━━━━━━━━━━━━ 4s 40ms/step - accuracy: 0.5774 - loss: 0.8857 955/1073 ━━━━━━━━━━━━━━━━━━━━ 4s 40ms/step - accuracy: 0.5775 - loss: 0.8855 957/1073 ━━━━━━━━━━━━━━━━━━━━ 4s 40ms/step - accuracy: 0.5777 - loss: 0.8853 959/1073 ━━━━━━━━━━━━━━━━━━━━ 4s 40ms/step - accuracy: 0.5778 - loss: 0.8851 961/1073 ━━━━━━━━━━━━━━━━━━━━ 4s 40ms/step - accuracy: 0.5779 - loss: 0.8849 963/1073 ━━━━━━━━━━━━━━━━━━━━ 4s 40ms/step - accuracy: 0.5781 - loss: 0.8847 965/1073 ━━━━━━━━━━━━━━━━━━━━ 4s 40ms/step - accuracy: 0.5782 - loss: 0.8845 967/1073 ━━━━━━━━━━━━━━━━━━━━ 4s 40ms/step - accuracy: 0.5784 - loss: 0.8843 969/1073 ━━━━━━━━━━━━━━━━━━━━ 4s 40ms/step - accuracy: 0.5785 - loss: 0.8841 971/1073 ━━━━━━━━━━━━━━━━━━━━ 4s 40ms/step - accuracy: 0.5786 - loss: 0.8839 973/1073 ━━━━━━━━━━━━━━━━━━━━ 4s 40ms/step - accuracy: 0.5788 - loss: 0.8837 975/1073 ━━━━━━━━━━━━━━━━━━━━ 3s 40ms/step - accuracy: 0.5789 - loss: 0.8835 977/1073 ━━━━━━━━━━━━━━━━━━━━ 3s 40ms/step - accuracy: 0.5791 - loss: 0.8833 979/1073 ━━━━━━━━━━━━━━━━━━━━ 3s 40ms/step - accuracy: 0.5792 - loss: 0.8832 981/1073 ━━━━━━━━━━━━━━━━━━━━ 3s 40ms/step - accuracy: 0.5793 - loss: 0.8830 983/1073 ━━━━━━━━━━━━━━━━━━━━ 3s 40ms/step - accuracy: 0.5795 - loss: 0.8828 985/1073 ━━━━━━━━━━━━━━━━━━━━ 3s 40ms/step - accuracy: 0.5796 - loss: 0.8826 987/1073 ━━━━━━━━━━━━━━━━━━━━ 3s 40ms/step - accuracy: 0.5797 - loss: 0.8824 989/1073 ━━━━━━━━━━━━━━━━━━━━ 3s 40ms/step - accuracy: 0.5799 - loss: 0.8822 991/1073 ━━━━━━━━━━━━━━━━━━━━ 3s 40ms/step - accuracy: 0.5800 - loss: 0.8820 993/1073 ━━━━━━━━━━━━━━━━━━━━ 3s 40ms/step - accuracy: 0.5801 - loss: 0.8818 995/1073 ━━━━━━━━━━━━━━━━━━━━ 3s 40ms/step - accuracy: 0.5803 - loss: 0.8817 997/1073 ━━━━━━━━━━━━━━━━━━━━ 3s 40ms/step - accuracy: 0.5804 - loss: 0.8815 999/1073 ━━━━━━━━━━━━━━━━━━━━ 2s 40ms/step - accuracy: 0.5805 - loss: 0.88131001/1073 ━━━━━━━━━━━━━━━━━━━━ 2s 40ms/step - accuracy: 0.5807 - loss: 0.88111003/1073 ━━━━━━━━━━━━━━━━━━━━ 2s 40ms/step - accuracy: 0.5808 - loss: 0.88091005/1073 ━━━━━━━━━━━━━━━━━━━━ 2s 40ms/step - accuracy: 0.5809 - loss: 0.88071007/1073 ━━━━━━━━━━━━━━━━━━━━ 2s 40ms/step - accuracy: 0.5811 - loss: 0.88051009/1073 ━━━━━━━━━━━━━━━━━━━━ 2s 40ms/step - accuracy: 0.5812 - loss: 0.88041011/1073 ━━━━━━━━━━━━━━━━━━━━ 2s 40ms/step - accuracy: 0.5813 - loss: 0.88021013/1073 ━━━━━━━━━━━━━━━━━━━━ 2s 40ms/step - accuracy: 0.5815 - loss: 0.88001015/1073 ━━━━━━━━━━━━━━━━━━━━ 2s 40ms/step - accuracy: 0.5816 - loss: 0.87981017/1073 ━━━━━━━━━━━━━━━━━━━━ 2s 40ms/step - accuracy: 0.5817 - loss: 0.87961019/1073 ━━━━━━━━━━━━━━━━━━━━ 2s 40ms/step - accuracy: 0.5818 - loss: 0.87941021/1073 ━━━━━━━━━━━━━━━━━━━━ 2s 40ms/step - accuracy: 0.5820 - loss: 0.87931023/1073 ━━━━━━━━━━━━━━━━━━━━ 2s 40ms/step - accuracy: 0.5821 - loss: 0.87911025/1073 ━━━━━━━━━━━━━━━━━━━━ 1s 40ms/step - accuracy: 0.5822 - loss: 0.87891027/1073 ━━━━━━━━━━━━━━━━━━━━ 1s 40ms/step - accuracy: 0.5824 - loss: 0.87871029/1073 ━━━━━━━━━━━━━━━━━━━━ 1s 40ms/step - accuracy: 0.5825 - loss: 0.87851031/1073 ━━━━━━━━━━━━━━━━━━━━ 1s 40ms/step - accuracy: 0.5826 - loss: 0.87841033/1073 ━━━━━━━━━━━━━━━━━━━━ 1s 40ms/step - accuracy: 0.5828 - loss: 0.87821035/1073 ━━━━━━━━━━━━━━━━━━━━ 1s 40ms/step - accuracy: 0.5829 - loss: 0.87801037/1073 ━━━━━━━━━━━━━━━━━━━━ 1s 40ms/step - accuracy: 0.5830 - loss: 0.87781039/1073 ━━━━━━━━━━━━━━━━━━━━ 1s 40ms/step - accuracy: 0.5831 - loss: 0.87761041/1073 ━━━━━━━━━━━━━━━━━━━━ 1s 40ms/step - accuracy: 0.5833 - loss: 0.87751043/1073 ━━━━━━━━━━━━━━━━━━━━ 1s 40ms/step - accuracy: 0.5834 - loss: 0.87731045/1073 ━━━━━━━━━━━━━━━━━━━━ 1s 40ms/step - accuracy: 0.5835 - loss: 0.87711047/1073 ━━━━━━━━━━━━━━━━━━━━ 1s 40ms/step - accuracy: 0.5836 - loss: 0.87691049/1073 ━━━━━━━━━━━━━━━━━━━━ 0s 40ms/step - accuracy: 0.5838 - loss: 0.87671051/1073 ━━━━━━━━━━━━━━━━━━━━ 0s 40ms/step - accuracy: 0.5839 - loss: 0.87661053/1073 ━━━━━━━━━━━━━━━━━━━━ 0s 40ms/step - accuracy: 0.5840 - loss: 0.87641055/1073 ━━━━━━━━━━━━━━━━━━━━ 0s 40ms/step - accuracy: 0.5841 - loss: 0.87621057/1073 ━━━━━━━━━━━━━━━━━━━━ 0s 40ms/step - accuracy: 0.5843 - loss: 0.87601059/1073 ━━━━━━━━━━━━━━━━━━━━ 0s 40ms/step - accuracy: 0.5844 - loss: 0.87591061/1073 ━━━━━━━━━━━━━━━━━━━━ 0s 40ms/step - accuracy: 0.5845 - loss: 0.87571063/1073 ━━━━━━━━━━━━━━━━━━━━ 0s 40ms/step - accuracy: 0.5846 - loss: 0.87551065/1073 ━━━━━━━━━━━━━━━━━━━━ 0s 40ms/step - accuracy: 0.5848 - loss: 0.87531067/1073 ━━━━━━━━━━━━━━━━━━━━ 0s 40ms/step - accuracy: 0.5849 - loss: 0.87521069/1073 ━━━━━━━━━━━━━━━━━━━━ 0s 40ms/step - accuracy: 0.5850 - loss: 0.87501071/1073 ━━━━━━━━━━━━━━━━━━━━ 0s 40ms/step - accuracy: 0.5851 - loss: 0.87481073/1073 ━━━━━━━━━━━━━━━━━━━━ 0s 67ms/step - accuracy: 0.5852 - loss: 0.87471073/1073 ━━━━━━━━━━━━━━━━━━━━ 124s 80ms/step - accuracy: 0.6507 - loss: 0.7823 - val_accuracy: 0.7255 - val_loss: 0.6553Epoch 2/5 1/1073 ━━━━━━━━━━━━━━━━━━━━ 17:28 978ms/step - accuracy: 0.7637 - loss: 0.6044 3/1073 ━━━━━━━━━━━━━━━━━━━━ 43s 41ms/step - accuracy: 0.7402 - loss: 0.6258 5/1073 ━━━━━━━━━━━━━━━━━━━━ 43s 40ms/step - accuracy: 0.7360 - loss: 0.6296 7/1073 ━━━━━━━━━━━━━━━━━━━━ 42s 40ms/step - accuracy: 0.7321 - loss: 0.6361 9/1073 ━━━━━━━━━━━━━━━━━━━━ 42s 40ms/step - accuracy: 0.7302 - loss: 0.6397 11/1073 ━━━━━━━━━━━━━━━━━━━━ 42s 40ms/step - accuracy: 0.7289 - loss: 0.6425 13/1073 ━━━━━━━━━━━━━━━━━━━━ 42s 40ms/step - accuracy: 0.7279 - loss: 0.6445 15/1073 ━━━━━━━━━━━━━━━━━━━━ 42s 40ms/step - accuracy: 0.7270 - loss: 0.6463 17/1073 ━━━━━━━━━━━━━━━━━━━━ 42s 40ms/step - accuracy: 0.7260 - loss: 0.6482 19/1073 ━━━━━━━━━━━━━━━━━━━━ 42s 40ms/step - accuracy: 0.7252 - loss: 0.6500 21/1073 ━━━━━━━━━━━━━━━━━━━━ 42s 40ms/step - accuracy: 0.7245 - loss: 0.6517 23/1073 ━━━━━━━━━━━━━━━━━━━━ 42s 40ms/step - accuracy: 0.7237 - loss: 0.6532 25/1073 ━━━━━━━━━━━━━━━━━━━━ 41s 40ms/step - accuracy: 0.7231 - loss: 0.6545 27/1073 ━━━━━━━━━━━━━━━━━━━━ 41s 40ms/step - accuracy: 0.7227 - loss: 0.6556 29/1073 ━━━━━━━━━━━━━━━━━━━━ 41s 40ms/step - accuracy: 0.7222 - loss: 0.6567 31/1073 ━━━━━━━━━━━━━━━━━━━━ 41s 40ms/step - accuracy: 0.7218 - loss: 0.6577 33/1073 ━━━━━━━━━━━━━━━━━━━━ 41s 40ms/step - accuracy: 0.7214 - loss: 0.6586 35/1073 ━━━━━━━━━━━━━━━━━━━━ 41s 40ms/step - accuracy: 0.7210 - loss: 0.6594 37/1073 ━━━━━━━━━━━━━━━━━━━━ 41s 40ms/step - accuracy: 0.7207 - loss: 0.6600 39/1073 ━━━━━━━━━━━━━━━━━━━━ 41s 40ms/step - accuracy: 0.7205 - loss: 0.6605 41/1073 ━━━━━━━━━━━━━━━━━━━━ 41s 40ms/step - accuracy: 0.7203 - loss: 0.6609 43/1073 ━━━━━━━━━━━━━━━━━━━━ 41s 40ms/step - accuracy: 0.7202 - loss: 0.6613 45/1073 ━━━━━━━━━━━━━━━━━━━━ 41s 40ms/step - accuracy: 0.7202 - loss: 0.6616 47/1073 ━━━━━━━━━━━━━━━━━━━━ 41s 40ms/step - accuracy: 0.7201 - loss: 0.6619 49/1073 ━━━━━━━━━━━━━━━━━━━━ 40s 40ms/step - accuracy: 0.7200 - loss: 0.6621 51/1073 ━━━━━━━━━━━━━━━━━━━━ 40s 40ms/step - accuracy: 0.7199 - loss: 0.6624 53/1073 ━━━━━━━━━━━━━━━━━━━━ 40s 40ms/step - accuracy: 0.7198 - loss: 0.6626 55/1073 ━━━━━━━━━━━━━━━━━━━━ 40s 40ms/step - accuracy: 0.7197 - loss: 0.6629 57/1073 ━━━━━━━━━━━━━━━━━━━━ 40s 40ms/step - accuracy: 0.7196 - loss: 0.6631 59/1073 ━━━━━━━━━━━━━━━━━━━━ 40s 40ms/step - accuracy: 0.7196 - loss: 0.6632 61/1073 ━━━━━━━━━━━━━━━━━━━━ 40s 40ms/step - accuracy: 0.7196 - loss: 0.6634 63/1073 ━━━━━━━━━━━━━━━━━━━━ 40s 40ms/step - accuracy: 0.7195 - loss: 0.6634 65/1073 ━━━━━━━━━━━━━━━━━━━━ 40s 40ms/step - accuracy: 0.7196 - loss: 0.6635 67/1073 ━━━━━━━━━━━━━━━━━━━━ 40s 40ms/step - accuracy: 0.7196 - loss: 0.6635 69/1073 ━━━━━━━━━━━━━━━━━━━━ 40s 40ms/step - accuracy: 0.7196 - loss: 0.6636 71/1073 ━━━━━━━━━━━━━━━━━━━━ 39s 40ms/step - accuracy: 0.7195 - loss: 0.6636 73/1073 ━━━━━━━━━━━━━━━━━━━━ 39s 40ms/step - accuracy: 0.7195 - loss: 0.6637 75/1073 ━━━━━━━━━━━━━━━━━━━━ 39s 40ms/step - accuracy: 0.7195 - loss: 0.6637 77/1073 ━━━━━━━━━━━━━━━━━━━━ 39s 40ms/step - accuracy: 0.7195 - loss: 0.6638 79/1073 ━━━━━━━━━━━━━━━━━━━━ 39s 40ms/step - accuracy: 0.7195 - loss: 0.6639 81/1073 ━━━━━━━━━━━━━━━━━━━━ 39s 40ms/step - accuracy: 0.7195 - loss: 0.6639 83/1073 ━━━━━━━━━━━━━━━━━━━━ 39s 40ms/step - accuracy: 0.7195 - loss: 0.6639 85/1073 ━━━━━━━━━━━━━━━━━━━━ 39s 40ms/step - accuracy: 0.7195 - loss: 0.6639 87/1073 ━━━━━━━━━━━━━━━━━━━━ 39s 40ms/step - accuracy: 0.7195 - loss: 0.6640 89/1073 ━━━━━━━━━━━━━━━━━━━━ 39s 40ms/step - accuracy: 0.7195 - loss: 0.6640 91/1073 ━━━━━━━━━━━━━━━━━━━━ 39s 40ms/step - accuracy: 0.7195 - loss: 0.6640 93/1073 ━━━━━━━━━━━━━━━━━━━━ 39s 40ms/step - accuracy: 0.7195 - loss: 0.6640 95/1073 ━━━━━━━━━━━━━━━━━━━━ 39s 40ms/step - accuracy: 0.7195 - loss: 0.6640 97/1073 ━━━━━━━━━━━━━━━━━━━━ 39s 40ms/step - accuracy: 0.7195 - loss: 0.6640 99/1073 ━━━━━━━━━━━━━━━━━━━━ 38s 40ms/step - accuracy: 0.7195 - loss: 0.6640 101/1073 ━━━━━━━━━━━━━━━━━━━━ 38s 40ms/step - accuracy: 0.7195 - loss: 0.6640 103/1073 ━━━━━━━━━━━━━━━━━━━━ 38s 40ms/step - accuracy: 0.7195 - loss: 0.6639 105/1073 ━━━━━━━━━━━━━━━━━━━━ 38s 40ms/step - accuracy: 0.7195 - loss: 0.6639 107/1073 ━━━━━━━━━━━━━━━━━━━━ 38s 40ms/step - accuracy: 0.7196 - loss: 0.6639 109/1073 ━━━━━━━━━━━━━━━━━━━━ 38s 40ms/step - accuracy: 0.7196 - loss: 0.6638 111/1073 ━━━━━━━━━━━━━━━━━━━━ 38s 40ms/step - accuracy: 0.7196 - loss: 0.6638 113/1073 ━━━━━━━━━━━━━━━━━━━━ 38s 40ms/step - accuracy: 0.7197 - loss: 0.6638 115/1073 ━━━━━━━━━━━━━━━━━━━━ 38s 40ms/step - accuracy: 0.7197 - loss: 0.6637 117/1073 ━━━━━━━━━━━━━━━━━━━━ 38s 40ms/step - accuracy: 0.7197 - loss: 0.6637 119/1073 ━━━━━━━━━━━━━━━━━━━━ 38s 40ms/step - accuracy: 0.7198 - loss: 0.6636 121/1073 ━━━━━━━━━━━━━━━━━━━━ 38s 40ms/step - accuracy: 0.7198 - loss: 0.6635 123/1073 ━━━━━━━━━━━━━━━━━━━━ 38s 40ms/step - accuracy: 0.7198 - loss: 0.6635 125/1073 ━━━━━━━━━━━━━━━━━━━━ 38s 40ms/step - accuracy: 0.7199 - loss: 0.6634 127/1073 ━━━━━━━━━━━━━━━━━━━━ 37s 40ms/step - accuracy: 0.7199 - loss: 0.6633 129/1073 ━━━━━━━━━━━━━━━━━━━━ 37s 40ms/step - accuracy: 0.7200 - loss: 0.6633 131/1073 ━━━━━━━━━━━━━━━━━━━━ 37s 40ms/step - accuracy: 0.7200 - loss: 0.6632 133/1073 ━━━━━━━━━━━━━━━━━━━━ 37s 40ms/step - accuracy: 0.7200 - loss: 0.6632 135/1073 ━━━━━━━━━━━━━━━━━━━━ 37s 40ms/step - accuracy: 0.7201 - loss: 0.6631 137/1073 ━━━━━━━━━━━━━━━━━━━━ 37s 40ms/step - accuracy: 0.7201 - loss: 0.6631 139/1073 ━━━━━━━━━━━━━━━━━━━━ 37s 40ms/step - accuracy: 0.7201 - loss: 0.6630 141/1073 ━━━━━━━━━━━━━━━━━━━━ 37s 40ms/step - accuracy: 0.7201 - loss: 0.6629 143/1073 ━━━━━━━━━━━━━━━━━━━━ 37s 40ms/step - accuracy: 0.7202 - loss: 0.6629 145/1073 ━━━━━━━━━━━━━━━━━━━━ 37s 40ms/step - accuracy: 0.7202 - loss: 0.6628 147/1073 ━━━━━━━━━━━━━━━━━━━━ 37s 40ms/step - accuracy: 0.7202 - loss: 0.6628 149/1073 ━━━━━━━━━━━━━━━━━━━━ 37s 40ms/step - accuracy: 0.7203 - loss: 0.6627 151/1073 ━━━━━━━━━━━━━━━━━━━━ 36s 40ms/step - accuracy: 0.7203 - loss: 0.6627 153/1073 ━━━━━━━━━━━━━━━━━━━━ 36s 40ms/step - accuracy: 0.7203 - loss: 0.6626 155/1073 ━━━━━━━━━━━━━━━━━━━━ 36s 40ms/step - accuracy: 0.7204 - loss: 0.6626 157/1073 ━━━━━━━━━━━━━━━━━━━━ 36s 40ms/step - accuracy: 0.7204 - loss: 0.6625 159/1073 ━━━━━━━━━━━━━━━━━━━━ 36s 40ms/step - accuracy: 0.7204 - loss: 0.6625 161/1073 ━━━━━━━━━━━━━━━━━━━━ 36s 40ms/step - accuracy: 0.7205 - loss: 0.6624 163/1073 ━━━━━━━━━━━━━━━━━━━━ 36s 40ms/step - accuracy: 0.7205 - loss: 0.6624 165/1073 ━━━━━━━━━━━━━━━━━━━━ 36s 40ms/step - accuracy: 0.7205 - loss: 0.6624 167/1073 ━━━━━━━━━━━━━━━━━━━━ 36s 40ms/step - accuracy: 0.7206 - loss: 0.6623 169/1073 ━━━━━━━━━━━━━━━━━━━━ 36s 40ms/step - accuracy: 0.7206 - loss: 0.6623 171/1073 ━━━━━━━━━━━━━━━━━━━━ 36s 40ms/step - accuracy: 0.7206 - loss: 0.6623 173/1073 ━━━━━━━━━━━━━━━━━━━━ 36s 40ms/step - accuracy: 0.7206 - loss: 0.6622 175/1073 ━━━━━━━━━━━━━━━━━━━━ 35s 40ms/step - accuracy: 0.7207 - loss: 0.6622 177/1073 ━━━━━━━━━━━━━━━━━━━━ 35s 40ms/step - accuracy: 0.7207 - loss: 0.6621 179/1073 ━━━━━━━━━━━━━━━━━━━━ 35s 40ms/step - accuracy: 0.7207 - loss: 0.6621 181/1073 ━━━━━━━━━━━━━━━━━━━━ 35s 40ms/step - accuracy: 0.7208 - loss: 0.6621 183/1073 ━━━━━━━━━━━━━━━━━━━━ 35s 40ms/step - accuracy: 0.7208 - loss: 0.6620 185/1073 ━━━━━━━━━━━━━━━━━━━━ 35s 40ms/step - accuracy: 0.7208 - loss: 0.6620 187/1073 ━━━━━━━━━━━━━━━━━━━━ 35s 40ms/step - accuracy: 0.7209 - loss: 0.6619 189/1073 ━━━━━━━━━━━━━━━━━━━━ 35s 40ms/step - accuracy: 0.7209 - loss: 0.6619 191/1073 ━━━━━━━━━━━━━━━━━━━━ 35s 40ms/step - accuracy: 0.7209 - loss: 0.6619 193/1073 ━━━━━━━━━━━━━━━━━━━━ 35s 40ms/step - accuracy: 0.7209 - loss: 0.6618 195/1073 ━━━━━━━━━━━━━━━━━━━━ 35s 40ms/step - accuracy: 0.7210 - loss: 0.6618 197/1073 ━━━━━━━━━━━━━━━━━━━━ 35s 40ms/step - accuracy: 0.7210 - loss: 0.6618 199/1073 ━━━━━━━━━━━━━━━━━━━━ 35s 40ms/step - accuracy: 0.7210 - loss: 0.6617 201/1073 ━━━━━━━━━━━━━━━━━━━━ 34s 40ms/step - accuracy: 0.7211 - loss: 0.6617 203/1073 ━━━━━━━━━━━━━━━━━━━━ 34s 40ms/step - accuracy: 0.7211 - loss: 0.6617 205/1073 ━━━━━━━━━━━━━━━━━━━━ 34s 40ms/step - accuracy: 0.7211 - loss: 0.6616 207/1073 ━━━━━━━━━━━━━━━━━━━━ 34s 40ms/step - accuracy: 0.7212 - loss: 0.6616 209/1073 ━━━━━━━━━━━━━━━━━━━━ 34s 40ms/step - accuracy: 0.7212 - loss: 0.6616 211/1073 ━━━━━━━━━━━━━━━━━━━━ 34s 40ms/step - accuracy: 0.7212 - loss: 0.6615 213/1073 ━━━━━━━━━━━━━━━━━━━━ 34s 40ms/step - accuracy: 0.7212 - loss: 0.6615 215/1073 ━━━━━━━━━━━━━━━━━━━━ 34s 40ms/step - accuracy: 0.7213 - loss: 0.6615 217/1073 ━━━━━━━━━━━━━━━━━━━━ 34s 40ms/step - accuracy: 0.7213 - loss: 0.6614 219/1073 ━━━━━━━━━━━━━━━━━━━━ 34s 40ms/step - accuracy: 0.7213 - loss: 0.6614 221/1073 ━━━━━━━━━━━━━━━━━━━━ 34s 40ms/step - accuracy: 0.7214 - loss: 0.6614 223/1073 ━━━━━━━━━━━━━━━━━━━━ 34s 40ms/step - accuracy: 0.7214 - loss: 0.6613 225/1073 ━━━━━━━━━━━━━━━━━━━━ 33s 40ms/step - accuracy: 0.7214 - loss: 0.6613 227/1073 ━━━━━━━━━━━━━━━━━━━━ 33s 40ms/step - accuracy: 0.7214 - loss: 0.6613 229/1073 ━━━━━━━━━━━━━━━━━━━━ 33s 40ms/step - accuracy: 0.7215 - loss: 0.6612 231/1073 ━━━━━━━━━━━━━━━━━━━━ 33s 40ms/step - accuracy: 0.7215 - loss: 0.6612 233/1073 ━━━━━━━━━━━━━━━━━━━━ 33s 40ms/step - accuracy: 0.7215 - loss: 0.6612 235/1073 ━━━━━━━━━━━━━━━━━━━━ 33s 40ms/step - accuracy: 0.7215 - loss: 0.6611 237/1073 ━━━━━━━━━━━━━━━━━━━━ 33s 40ms/step - accuracy: 0.7216 - loss: 0.6611 239/1073 ━━━━━━━━━━━━━━━━━━━━ 33s 40ms/step - accuracy: 0.7216 - loss: 0.6611 241/1073 ━━━━━━━━━━━━━━━━━━━━ 33s 40ms/step - accuracy: 0.7216 - loss: 0.6610 243/1073 ━━━━━━━━━━━━━━━━━━━━ 33s 40ms/step - accuracy: 0.7216 - loss: 0.6610 245/1073 ━━━━━━━━━━━━━━━━━━━━ 33s 40ms/step - accuracy: 0.7217 - loss: 0.6610 247/1073 ━━━━━━━━━━━━━━━━━━━━ 33s 40ms/step - accuracy: 0.7217 - loss: 0.6609 249/1073 ━━━━━━━━━━━━━━━━━━━━ 32s 40ms/step - accuracy: 0.7217 - loss: 0.6609 251/1073 ━━━━━━━━━━━━━━━━━━━━ 32s 40ms/step - accuracy: 0.7217 - loss: 0.6609 253/1073 ━━━━━━━━━━━━━━━━━━━━ 32s 40ms/step - accuracy: 0.7218 - loss: 0.6608 255/1073 ━━━━━━━━━━━━━━━━━━━━ 32s 40ms/step - accuracy: 0.7218 - loss: 0.6608 257/1073 ━━━━━━━━━━━━━━━━━━━━ 32s 40ms/step - accuracy: 0.7218 - loss: 0.6608 259/1073 ━━━━━━━━━━━━━━━━━━━━ 32s 40ms/step - accuracy: 0.7218 - loss: 0.6607 261/1073 ━━━━━━━━━━━━━━━━━━━━ 32s 40ms/step - accuracy: 0.7219 - loss: 0.6607 263/1073 ━━━━━━━━━━━━━━━━━━━━ 32s 40ms/step - accuracy: 0.7219 - loss: 0.6607 265/1073 ━━━━━━━━━━━━━━━━━━━━ 32s 40ms/step - accuracy: 0.7219 - loss: 0.6606 267/1073 ━━━━━━━━━━━━━━━━━━━━ 32s 40ms/step - accuracy: 0.7219 - loss: 0.6606 269/1073 ━━━━━━━━━━━━━━━━━━━━ 32s 40ms/step - accuracy: 0.7220 - loss: 0.6606 271/1073 ━━━━━━━━━━━━━━━━━━━━ 32s 40ms/step - accuracy: 0.7220 - loss: 0.6605 273/1073 ━━━━━━━━━━━━━━━━━━━━ 32s 40ms/step - accuracy: 0.7220 - loss: 0.6605 275/1073 ━━━━━━━━━━━━━━━━━━━━ 31s 40ms/step - accuracy: 0.7220 - loss: 0.6604 277/1073 ━━━━━━━━━━━━━━━━━━━━ 31s 40ms/step - accuracy: 0.7221 - loss: 0.6604 279/1073 ━━━━━━━━━━━━━━━━━━━━ 31s 40ms/step - accuracy: 0.7221 - loss: 0.6604 281/1073 ━━━━━━━━━━━━━━━━━━━━ 31s 40ms/step - accuracy: 0.7221 - loss: 0.6603 283/1073 ━━━━━━━━━━━━━━━━━━━━ 31s 40ms/step - accuracy: 0.7221 - loss: 0.6603 285/1073 ━━━━━━━━━━━━━━━━━━━━ 31s 40ms/step - accuracy: 0.7222 - loss: 0.6603 287/1073 ━━━━━━━━━━━━━━━━━━━━ 31s 40ms/step - accuracy: 0.7222 - loss: 0.6602 289/1073 ━━━━━━━━━━━━━━━━━━━━ 31s 40ms/step - accuracy: 0.7222 - loss: 0.6602 291/1073 ━━━━━━━━━━━━━━━━━━━━ 31s 40ms/step - accuracy: 0.7222 - loss: 0.6602 293/1073 ━━━━━━━━━━━━━━━━━━━━ 31s 40ms/step - accuracy: 0.7222 - loss: 0.6601 295/1073 ━━━━━━━━━━━━━━━━━━━━ 31s 40ms/step - accuracy: 0.7223 - loss: 0.6601 297/1073 ━━━━━━━━━━━━━━━━━━━━ 31s 40ms/step - accuracy: 0.7223 - loss: 0.6601 299/1073 ━━━━━━━━━━━━━━━━━━━━ 30s 40ms/step - accuracy: 0.7223 - loss: 0.6600 301/1073 ━━━━━━━━━━━━━━━━━━━━ 30s 40ms/step - accuracy: 0.7223 - loss: 0.6600 303/1073 ━━━━━━━━━━━━━━━━━━━━ 30s 40ms/step - accuracy: 0.7224 - loss: 0.6600 305/1073 ━━━━━━━━━━━━━━━━━━━━ 30s 40ms/step - accuracy: 0.7224 - loss: 0.6599 307/1073 ━━━━━━━━━━━━━━━━━━━━ 30s 40ms/step - accuracy: 0.7224 - loss: 0.6599 309/1073 ━━━━━━━━━━━━━━━━━━━━ 30s 40ms/step - accuracy: 0.7224 - loss: 0.6599 311/1073 ━━━━━━━━━━━━━━━━━━━━ 30s 40ms/step - accuracy: 0.7224 - loss: 0.6598 313/1073 ━━━━━━━━━━━━━━━━━━━━ 30s 40ms/step - accuracy: 0.7225 - loss: 0.6598 315/1073 ━━━━━━━━━━━━━━━━━━━━ 30s 40ms/step - accuracy: 0.7225 - loss: 0.6598 317/1073 ━━━━━━━━━━━━━━━━━━━━ 30s 40ms/step - accuracy: 0.7225 - loss: 0.6597 319/1073 ━━━━━━━━━━━━━━━━━━━━ 30s 40ms/step - accuracy: 0.7225 - loss: 0.6597 321/1073 ━━━━━━━━━━━━━━━━━━━━ 30s 40ms/step - accuracy: 0.7225 - loss: 0.6597 323/1073 ━━━━━━━━━━━━━━━━━━━━ 30s 40ms/step - accuracy: 0.7225 - loss: 0.6596 325/1073 ━━━━━━━━━━━━━━━━━━━━ 29s 40ms/step - accuracy: 0.7226 - loss: 0.6596 327/1073 ━━━━━━━━━━━━━━━━━━━━ 29s 40ms/step - accuracy: 0.7226 - loss: 0.6596 329/1073 ━━━━━━━━━━━━━━━━━━━━ 29s 40ms/step - accuracy: 0.7226 - loss: 0.6595 331/1073 ━━━━━━━━━━━━━━━━━━━━ 29s 40ms/step - accuracy: 0.7226 - loss: 0.6595 333/1073 ━━━━━━━━━━━━━━━━━━━━ 29s 40ms/step - accuracy: 0.7226 - loss: 0.6595 335/1073 ━━━━━━━━━━━━━━━━━━━━ 29s 40ms/step - accuracy: 0.7227 - loss: 0.6594 337/1073 ━━━━━━━━━━━━━━━━━━━━ 29s 40ms/step - accuracy: 0.7227 - loss: 0.6594 339/1073 ━━━━━━━━━━━━━━━━━━━━ 29s 40ms/step - accuracy: 0.7227 - loss: 0.6594 341/1073 ━━━━━━━━━━━━━━━━━━━━ 29s 40ms/step - accuracy: 0.7227 - loss: 0.6593 343/1073 ━━━━━━━━━━━━━━━━━━━━ 29s 40ms/step - accuracy: 0.7227 - loss: 0.6593 345/1073 ━━━━━━━━━━━━━━━━━━━━ 29s 40ms/step - accuracy: 0.7227 - loss: 0.6593 347/1073 ━━━━━━━━━━━━━━━━━━━━ 29s 40ms/step - accuracy: 0.7228 - loss: 0.6592 349/1073 ━━━━━━━━━━━━━━━━━━━━ 28s 40ms/step - accuracy: 0.7228 - loss: 0.6592 351/1073 ━━━━━━━━━━━━━━━━━━━━ 28s 40ms/step - accuracy: 0.7228 - loss: 0.6592 353/1073 ━━━━━━━━━━━━━━━━━━━━ 28s 40ms/step - accuracy: 0.7228 - loss: 0.6591 355/1073 ━━━━━━━━━━━━━━━━━━━━ 28s 40ms/step - accuracy: 0.7228 - loss: 0.6591 357/1073 ━━━━━━━━━━━━━━━━━━━━ 28s 40ms/step - accuracy: 0.7229 - loss: 0.6591 359/1073 ━━━━━━━━━━━━━━━━━━━━ 28s 40ms/step - accuracy: 0.7229 - loss: 0.6590 361/1073 ━━━━━━━━━━━━━━━━━━━━ 28s 40ms/step - accuracy: 0.7229 - loss: 0.6590 363/1073 ━━━━━━━━━━━━━━━━━━━━ 28s 40ms/step - accuracy: 0.7229 - loss: 0.6590 365/1073 ━━━━━━━━━━━━━━━━━━━━ 28s 40ms/step - accuracy: 0.7229 - loss: 0.6589 367/1073 ━━━━━━━━━━━━━━━━━━━━ 28s 40ms/step - accuracy: 0.7229 - loss: 0.6589 369/1073 ━━━━━━━━━━━━━━━━━━━━ 28s 40ms/step - accuracy: 0.7230 - loss: 0.6589 371/1073 ━━━━━━━━━━━━━━━━━━━━ 28s 40ms/step - accuracy: 0.7230 - loss: 0.6588 373/1073 ━━━━━━━━━━━━━━━━━━━━ 27s 40ms/step - accuracy: 0.7230 - loss: 0.6588 375/1073 ━━━━━━━━━━━━━━━━━━━━ 27s 40ms/step - accuracy: 0.7230 - loss: 0.6588 377/1073 ━━━━━━━━━━━━━━━━━━━━ 27s 40ms/step - accuracy: 0.7230 - loss: 0.6587 379/1073 ━━━━━━━━━━━━━━━━━━━━ 27s 40ms/step - accuracy: 0.7230 - loss: 0.6587 381/1073 ━━━━━━━━━━━━━━━━━━━━ 27s 40ms/step - accuracy: 0.7231 - loss: 0.6587 383/1073 ━━━━━━━━━━━━━━━━━━━━ 27s 40ms/step - accuracy: 0.7231 - loss: 0.6587 385/1073 ━━━━━━━━━━━━━━━━━━━━ 27s 40ms/step - accuracy: 0.7231 - loss: 0.6586 387/1073 ━━━━━━━━━━━━━━━━━━━━ 27s 40ms/step - accuracy: 0.7231 - loss: 0.6586 389/1073 ━━━━━━━━━━━━━━━━━━━━ 27s 40ms/step - accuracy: 0.7231 - loss: 0.6586 391/1073 ━━━━━━━━━━━━━━━━━━━━ 27s 40ms/step - accuracy: 0.7231 - loss: 0.6585 393/1073 ━━━━━━━━━━━━━━━━━━━━ 27s 40ms/step - accuracy: 0.7231 - loss: 0.6585 395/1073 ━━━━━━━━━━━━━━━━━━━━ 27s 40ms/step - accuracy: 0.7232 - loss: 0.6585 397/1073 ━━━━━━━━━━━━━━━━━━━━ 27s 40ms/step - accuracy: 0.7232 - loss: 0.6585 399/1073 ━━━━━━━━━━━━━━━━━━━━ 26s 40ms/step - accuracy: 0.7232 - loss: 0.6584 401/1073 ━━━━━━━━━━━━━━━━━━━━ 26s 40ms/step - accuracy: 0.7232 - loss: 0.6584 403/1073 ━━━━━━━━━━━━━━━━━━━━ 26s 40ms/step - accuracy: 0.7232 - loss: 0.6584 405/1073 ━━━━━━━━━━━━━━━━━━━━ 26s 40ms/step - accuracy: 0.7232 - loss: 0.6583 407/1073 ━━━━━━━━━━━━━━━━━━━━ 26s 40ms/step - accuracy: 0.7232 - loss: 0.6583 409/1073 ━━━━━━━━━━━━━━━━━━━━ 26s 40ms/step - accuracy: 0.7233 - loss: 0.6583 411/1073 ━━━━━━━━━━━━━━━━━━━━ 26s 40ms/step - accuracy: 0.7233 - loss: 0.6583 413/1073 ━━━━━━━━━━━━━━━━━━━━ 26s 40ms/step - accuracy: 0.7233 - loss: 0.6582 415/1073 ━━━━━━━━━━━━━━━━━━━━ 26s 40ms/step - accuracy: 0.7233 - loss: 0.6582 417/1073 ━━━━━━━━━━━━━━━━━━━━ 26s 40ms/step - accuracy: 0.7233 - loss: 0.6582 419/1073 ━━━━━━━━━━━━━━━━━━━━ 26s 40ms/step - accuracy: 0.7233 - loss: 0.6582 421/1073 ━━━━━━━━━━━━━━━━━━━━ 26s 40ms/step - accuracy: 0.7233 - loss: 0.6581 423/1073 ━━━━━━━━━━━━━━━━━━━━ 26s 40ms/step - accuracy: 0.7234 - loss: 0.6581 425/1073 ━━━━━━━━━━━━━━━━━━━━ 25s 40ms/step - accuracy: 0.7234 - loss: 0.6581 427/1073 ━━━━━━━━━━━━━━━━━━━━ 25s 40ms/step - accuracy: 0.7234 - loss: 0.6580 429/1073 ━━━━━━━━━━━━━━━━━━━━ 25s 40ms/step - accuracy: 0.7234 - loss: 0.6580 431/1073 ━━━━━━━━━━━━━━━━━━━━ 25s 40ms/step - accuracy: 0.7234 - loss: 0.6580 433/1073 ━━━━━━━━━━━━━━━━━━━━ 25s 40ms/step - accuracy: 0.7234 - loss: 0.6580 435/1073 ━━━━━━━━━━━━━━━━━━━━ 25s 40ms/step - accuracy: 0.7234 - loss: 0.6579 437/1073 ━━━━━━━━━━━━━━━━━━━━ 25s 40ms/step - accuracy: 0.7235 - loss: 0.6579 439/1073 ━━━━━━━━━━━━━━━━━━━━ 25s 40ms/step - accuracy: 0.7235 - loss: 0.6579 441/1073 ━━━━━━━━━━━━━━━━━━━━ 25s 40ms/step - accuracy: 0.7235 - loss: 0.6579 443/1073 ━━━━━━━━━━━━━━━━━━━━ 25s 40ms/step - accuracy: 0.7235 - loss: 0.6578 445/1073 ━━━━━━━━━━━━━━━━━━━━ 25s 40ms/step - accuracy: 0.7235 - loss: 0.6578 447/1073 ━━━━━━━━━━━━━━━━━━━━ 25s 40ms/step - accuracy: 0.7235 - loss: 0.6578 449/1073 ━━━━━━━━━━━━━━━━━━━━ 24s 40ms/step - accuracy: 0.7235 - loss: 0.6578 451/1073 ━━━━━━━━━━━━━━━━━━━━ 24s 40ms/step - accuracy: 0.7235 - loss: 0.6577 453/1073 ━━━━━━━━━━━━━━━━━━━━ 24s 40ms/step - accuracy: 0.7236 - loss: 0.6577 455/1073 ━━━━━━━━━━━━━━━━━━━━ 24s 40ms/step - accuracy: 0.7236 - loss: 0.6577 457/1073 ━━━━━━━━━━━━━━━━━━━━ 24s 40ms/step - accuracy: 0.7236 - loss: 0.6577 459/1073 ━━━━━━━━━━━━━━━━━━━━ 24s 40ms/step - accuracy: 0.7236 - loss: 0.6577 461/1073 ━━━━━━━━━━━━━━━━━━━━ 24s 40ms/step - accuracy: 0.7236 - loss: 0.6576 463/1073 ━━━━━━━━━━━━━━━━━━━━ 24s 40ms/step - accuracy: 0.7236 - loss: 0.6576 465/1073 ━━━━━━━━━━━━━━━━━━━━ 24s 40ms/step - accuracy: 0.7236 - loss: 0.6576 467/1073 ━━━━━━━━━━━━━━━━━━━━ 24s 40ms/step - accuracy: 0.7236 - loss: 0.6576 469/1073 ━━━━━━━━━━━━━━━━━━━━ 24s 40ms/step - accuracy: 0.7237 - loss: 0.6575 471/1073 ━━━━━━━━━━━━━━━━━━━━ 24s 40ms/step - accuracy: 0.7237 - loss: 0.6575 473/1073 ━━━━━━━━━━━━━━━━━━━━ 24s 40ms/step - accuracy: 0.7237 - loss: 0.6575 475/1073 ━━━━━━━━━━━━━━━━━━━━ 23s 40ms/step - accuracy: 0.7237 - loss: 0.6575 477/1073 ━━━━━━━━━━━━━━━━━━━━ 23s 40ms/step - accuracy: 0.7237 - loss: 0.6574 479/1073 ━━━━━━━━━━━━━━━━━━━━ 23s 40ms/step - accuracy: 0.7237 - loss: 0.6574 481/1073 ━━━━━━━━━━━━━━━━━━━━ 23s 40ms/step - accuracy: 0.7237 - loss: 0.6574 483/1073 ━━━━━━━━━━━━━━━━━━━━ 23s 40ms/step - accuracy: 0.7237 - loss: 0.6574 485/1073 ━━━━━━━━━━━━━━━━━━━━ 23s 40ms/step - accuracy: 0.7238 - loss: 0.6573 487/1073 ━━━━━━━━━━━━━━━━━━━━ 23s 40ms/step - accuracy: 0.7238 - loss: 0.6573 489/1073 ━━━━━━━━━━━━━━━━━━━━ 23s 40ms/step - accuracy: 0.7238 - loss: 0.6573 491/1073 ━━━━━━━━━━━━━━━━━━━━ 23s 40ms/step - accuracy: 0.7238 - loss: 0.6573 493/1073 ━━━━━━━━━━━━━━━━━━━━ 23s 40ms/step - accuracy: 0.7238 - loss: 0.6572 495/1073 ━━━━━━━━━━━━━━━━━━━━ 23s 40ms/step - accuracy: 0.7238 - loss: 0.6572 497/1073 ━━━━━━━━━━━━━━━━━━━━ 23s 40ms/step - accuracy: 0.7238 - loss: 0.6572 499/1073 ━━━━━━━━━━━━━━━━━━━━ 23s 40ms/step - accuracy: 0.7238 - loss: 0.6572 501/1073 ━━━━━━━━━━━━━━━━━━━━ 22s 40ms/step - accuracy: 0.7239 - loss: 0.6572 503/1073 ━━━━━━━━━━━━━━━━━━━━ 22s 40ms/step - accuracy: 0.7239 - loss: 0.6571 505/1073 ━━━━━━━━━━━━━━━━━━━━ 22s 40ms/step - accuracy: 0.7239 - loss: 0.6571 507/1073 ━━━━━━━━━━━━━━━━━━━━ 22s 40ms/step - accuracy: 0.7239 - loss: 0.6571 509/1073 ━━━━━━━━━━━━━━━━━━━━ 22s 40ms/step - accuracy: 0.7239 - loss: 0.6571 511/1073 ━━━━━━━━━━━━━━━━━━━━ 22s 40ms/step - accuracy: 0.7239 - loss: 0.6570 513/1073 ━━━━━━━━━━━━━━━━━━━━ 22s 40ms/step - accuracy: 0.7239 - loss: 0.6570 515/1073 ━━━━━━━━━━━━━━━━━━━━ 22s 40ms/step - accuracy: 0.7239 - loss: 0.6570 517/1073 ━━━━━━━━━━━━━━━━━━━━ 22s 40ms/step - accuracy: 0.7240 - loss: 0.6570 519/1073 ━━━━━━━━━━━━━━━━━━━━ 22s 40ms/step - accuracy: 0.7240 - loss: 0.6569 521/1073 ━━━━━━━━━━━━━━━━━━━━ 22s 40ms/step - accuracy: 0.7240 - loss: 0.6569 523/1073 ━━━━━━━━━━━━━━━━━━━━ 22s 40ms/step - accuracy: 0.7240 - loss: 0.6569 525/1073 ━━━━━━━━━━━━━━━━━━━━ 21s 40ms/step - accuracy: 0.7240 - loss: 0.6569 527/1073 ━━━━━━━━━━━━━━━━━━━━ 21s 40ms/step - accuracy: 0.7240 - loss: 0.6568 529/1073 ━━━━━━━━━━━━━━━━━━━━ 21s 40ms/step - accuracy: 0.7240 - loss: 0.6568 531/1073 ━━━━━━━━━━━━━━━━━━━━ 21s 40ms/step - accuracy: 0.7240 - loss: 0.6568 533/1073 ━━━━━━━━━━━━━━━━━━━━ 21s 40ms/step - accuracy: 0.7241 - loss: 0.6568 535/1073 ━━━━━━━━━━━━━━━━━━━━ 21s 40ms/step - accuracy: 0.7241 - loss: 0.6567 537/1073 ━━━━━━━━━━━━━━━━━━━━ 21s 40ms/step - accuracy: 0.7241 - loss: 0.6567 539/1073 ━━━━━━━━━━━━━━━━━━━━ 21s 40ms/step - accuracy: 0.7241 - loss: 0.6567 541/1073 ━━━━━━━━━━━━━━━━━━━━ 21s 40ms/step - accuracy: 0.7241 - loss: 0.6567 543/1073 ━━━━━━━━━━━━━━━━━━━━ 21s 40ms/step - accuracy: 0.7241 - loss: 0.6567 545/1073 ━━━━━━━━━━━━━━━━━━━━ 21s 40ms/step - accuracy: 0.7241 - loss: 0.6566 547/1073 ━━━━━━━━━━━━━━━━━━━━ 21s 40ms/step - accuracy: 0.7242 - loss: 0.6566 549/1073 ━━━━━━━━━━━━━━━━━━━━ 20s 40ms/step - accuracy: 0.7242 - loss: 0.6566 551/1073 ━━━━━━━━━━━━━━━━━━━━ 20s 40ms/step - accuracy: 0.7242 - loss: 0.6566 553/1073 ━━━━━━━━━━━━━━━━━━━━ 20s 40ms/step - accuracy: 0.7242 - loss: 0.6565 555/1073 ━━━━━━━━━━━━━━━━━━━━ 20s 40ms/step - accuracy: 0.7242 - loss: 0.6565 557/1073 ━━━━━━━━━━━━━━━━━━━━ 20s 40ms/step - accuracy: 0.7242 - loss: 0.6565 559/1073 ━━━━━━━━━━━━━━━━━━━━ 20s 40ms/step - accuracy: 0.7242 - loss: 0.6565 561/1073 ━━━━━━━━━━━━━━━━━━━━ 20s 40ms/step - accuracy: 0.7242 - loss: 0.6564 563/1073 ━━━━━━━━━━━━━━━━━━━━ 20s 40ms/step - accuracy: 0.7243 - loss: 0.6564 565/1073 ━━━━━━━━━━━━━━━━━━━━ 20s 40ms/step - accuracy: 0.7243 - loss: 0.6564 567/1073 ━━━━━━━━━━━━━━━━━━━━ 20s 40ms/step - accuracy: 0.7243 - loss: 0.6564 569/1073 ━━━━━━━━━━━━━━━━━━━━ 20s 40ms/step - accuracy: 0.7243 - loss: 0.6563 571/1073 ━━━━━━━━━━━━━━━━━━━━ 20s 40ms/step - accuracy: 0.7243 - loss: 0.6563 573/1073 ━━━━━━━━━━━━━━━━━━━━ 19s 40ms/step - accuracy: 0.7243 - loss: 0.6563 575/1073 ━━━━━━━━━━━━━━━━━━━━ 19s 40ms/step - accuracy: 0.7243 - loss: 0.6563 577/1073 ━━━━━━━━━━━━━━━━━━━━ 19s 40ms/step - accuracy: 0.7243 - loss: 0.6562 579/1073 ━━━━━━━━━━━━━━━━━━━━ 19s 40ms/step - accuracy: 0.7244 - loss: 0.6562 581/1073 ━━━━━━━━━━━━━━━━━━━━ 19s 40ms/step - accuracy: 0.7244 - loss: 0.6562 583/1073 ━━━━━━━━━━━━━━━━━━━━ 19s 40ms/step - accuracy: 0.7244 - loss: 0.6562 585/1073 ━━━━━━━━━━━━━━━━━━━━ 19s 40ms/step - accuracy: 0.7244 - loss: 0.6561 587/1073 ━━━━━━━━━━━━━━━━━━━━ 19s 40ms/step - accuracy: 0.7244 - loss: 0.6561 589/1073 ━━━━━━━━━━━━━━━━━━━━ 19s 40ms/step - accuracy: 0.7244 - loss: 0.6561 591/1073 ━━━━━━━━━━━━━━━━━━━━ 19s 40ms/step - accuracy: 0.7244 - loss: 0.6561 593/1073 ━━━━━━━━━━━━━━━━━━━━ 19s 40ms/step - accuracy: 0.7244 - loss: 0.6560 595/1073 ━━━━━━━━━━━━━━━━━━━━ 19s 40ms/step - accuracy: 0.7245 - loss: 0.6560 597/1073 ━━━━━━━━━━━━━━━━━━━━ 19s 40ms/step - accuracy: 0.7245 - loss: 0.6560 599/1073 ━━━━━━━━━━━━━━━━━━━━ 18s 40ms/step - accuracy: 0.7245 - loss: 0.6560 601/1073 ━━━━━━━━━━━━━━━━━━━━ 18s 40ms/step - accuracy: 0.7245 - loss: 0.6559 603/1073 ━━━━━━━━━━━━━━━━━━━━ 18s 40ms/step - accuracy: 0.7245 - loss: 0.6559 605/1073 ━━━━━━━━━━━━━━━━━━━━ 18s 40ms/step - accuracy: 0.7245 - loss: 0.6559 607/1073 ━━━━━━━━━━━━━━━━━━━━ 18s 40ms/step - accuracy: 0.7245 - loss: 0.6559 609/1073 ━━━━━━━━━━━━━━━━━━━━ 18s 40ms/step - accuracy: 0.7246 - loss: 0.6558 611/1073 ━━━━━━━━━━━━━━━━━━━━ 18s 40ms/step - accuracy: 0.7246 - loss: 0.6558 613/1073 ━━━━━━━━━━━━━━━━━━━━ 18s 40ms/step - accuracy: 0.7246 - loss: 0.6558 615/1073 ━━━━━━━━━━━━━━━━━━━━ 18s 40ms/step - accuracy: 0.7246 - loss: 0.6558 617/1073 ━━━━━━━━━━━━━━━━━━━━ 18s 40ms/step - accuracy: 0.7246 - loss: 0.6557 619/1073 ━━━━━━━━━━━━━━━━━━━━ 18s 40ms/step - accuracy: 0.7246 - loss: 0.6557 621/1073 ━━━━━━━━━━━━━━━━━━━━ 18s 40ms/step - accuracy: 0.7246 - loss: 0.6557 623/1073 ━━━━━━━━━━━━━━━━━━━━ 17s 40ms/step - accuracy: 0.7246 - loss: 0.6557 625/1073 ━━━━━━━━━━━━━━━━━━━━ 17s 40ms/step - accuracy: 0.7247 - loss: 0.6556 627/1073 ━━━━━━━━━━━━━━━━━━━━ 17s 40ms/step - accuracy: 0.7247 - loss: 0.6556 629/1073 ━━━━━━━━━━━━━━━━━━━━ 17s 40ms/step - accuracy: 0.7247 - loss: 0.6556 631/1073 ━━━━━━━━━━━━━━━━━━━━ 17s 40ms/step - accuracy: 0.7247 - loss: 0.6556 633/1073 ━━━━━━━━━━━━━━━━━━━━ 17s 40ms/step - accuracy: 0.7247 - loss: 0.6556 635/1073 ━━━━━━━━━━━━━━━━━━━━ 17s 40ms/step - accuracy: 0.7247 - loss: 0.6555 637/1073 ━━━━━━━━━━━━━━━━━━━━ 17s 40ms/step - accuracy: 0.7247 - loss: 0.6555 639/1073 ━━━━━━━━━━━━━━━━━━━━ 17s 40ms/step - accuracy: 0.7247 - loss: 0.6555 641/1073 ━━━━━━━━━━━━━━━━━━━━ 17s 40ms/step - accuracy: 0.7248 - loss: 0.6555 643/1073 ━━━━━━━━━━━━━━━━━━━━ 17s 40ms/step - accuracy: 0.7248 - loss: 0.6554 645/1073 ━━━━━━━━━━━━━━━━━━━━ 17s 40ms/step - accuracy: 0.7248 - loss: 0.6554 647/1073 ━━━━━━━━━━━━━━━━━━━━ 17s 40ms/step - accuracy: 0.7248 - loss: 0.6554 649/1073 ━━━━━━━━━━━━━━━━━━━━ 16s 40ms/step - accuracy: 0.7248 - loss: 0.6554 651/1073 ━━━━━━━━━━━━━━━━━━━━ 16s 40ms/step - accuracy: 0.7248 - loss: 0.6554 653/1073 ━━━━━━━━━━━━━━━━━━━━ 16s 40ms/step - accuracy: 0.7248 - loss: 0.6553 655/1073 ━━━━━━━━━━━━━━━━━━━━ 16s 40ms/step - accuracy: 0.7248 - loss: 0.6553 657/1073 ━━━━━━━━━━━━━━━━━━━━ 16s 40ms/step - accuracy: 0.7248 - loss: 0.6553 659/1073 ━━━━━━━━━━━━━━━━━━━━ 16s 40ms/step - accuracy: 0.7249 - loss: 0.6553 661/1073 ━━━━━━━━━━━━━━━━━━━━ 16s 40ms/step - accuracy: 0.7249 - loss: 0.6553 663/1073 ━━━━━━━━━━━━━━━━━━━━ 16s 40ms/step - accuracy: 0.7249 - loss: 0.6552 665/1073 ━━━━━━━━━━━━━━━━━━━━ 16s 40ms/step - accuracy: 0.7249 - loss: 0.6552 667/1073 ━━━━━━━━━━━━━━━━━━━━ 16s 40ms/step - accuracy: 0.7249 - loss: 0.6552 669/1073 ━━━━━━━━━━━━━━━━━━━━ 16s 40ms/step - accuracy: 0.7249 - loss: 0.6552 671/1073 ━━━━━━━━━━━━━━━━━━━━ 16s 40ms/step - accuracy: 0.7249 - loss: 0.6552 673/1073 ━━━━━━━━━━━━━━━━━━━━ 15s 40ms/step - accuracy: 0.7249 - loss: 0.6551 675/1073 ━━━━━━━━━━━━━━━━━━━━ 15s 40ms/step - accuracy: 0.7249 - loss: 0.6551 677/1073 ━━━━━━━━━━━━━━━━━━━━ 15s 40ms/step - accuracy: 0.7250 - loss: 0.6551 679/1073 ━━━━━━━━━━━━━━━━━━━━ 15s 40ms/step - accuracy: 0.7250 - loss: 0.6551 681/1073 ━━━━━━━━━━━━━━━━━━━━ 15s 40ms/step - accuracy: 0.7250 - loss: 0.6550 683/1073 ━━━━━━━━━━━━━━━━━━━━ 15s 40ms/step - accuracy: 0.7250 - loss: 0.6550 685/1073 ━━━━━━━━━━━━━━━━━━━━ 15s 40ms/step - accuracy: 0.7250 - loss: 0.6550 687/1073 ━━━━━━━━━━━━━━━━━━━━ 15s 40ms/step - accuracy: 0.7250 - loss: 0.6550 689/1073 ━━━━━━━━━━━━━━━━━━━━ 15s 40ms/step - accuracy: 0.7250 - loss: 0.6550 691/1073 ━━━━━━━━━━━━━━━━━━━━ 15s 40ms/step - accuracy: 0.7250 - loss: 0.6549 693/1073 ━━━━━━━━━━━━━━━━━━━━ 15s 40ms/step - accuracy: 0.7250 - loss: 0.6549 695/1073 ━━━━━━━━━━━━━━━━━━━━ 15s 40ms/step - accuracy: 0.7251 - loss: 0.6549 697/1073 ━━━━━━━━━━━━━━━━━━━━ 15s 40ms/step - accuracy: 0.7251 - loss: 0.6549 699/1073 ━━━━━━━━━━━━━━━━━━━━ 14s 40ms/step - accuracy: 0.7251 - loss: 0.6549 701/1073 ━━━━━━━━━━━━━━━━━━━━ 14s 40ms/step - accuracy: 0.7251 - loss: 0.6548 703/1073 ━━━━━━━━━━━━━━━━━━━━ 14s 40ms/step - accuracy: 0.7251 - loss: 0.6548 705/1073 ━━━━━━━━━━━━━━━━━━━━ 14s 40ms/step - accuracy: 0.7251 - loss: 0.6548 707/1073 ━━━━━━━━━━━━━━━━━━━━ 14s 40ms/step - accuracy: 0.7251 - loss: 0.6548 709/1073 ━━━━━━━━━━━━━━━━━━━━ 14s 40ms/step - accuracy: 0.7251 - loss: 0.6548 711/1073 ━━━━━━━━━━━━━━━━━━━━ 14s 40ms/step - accuracy: 0.7251 - loss: 0.6547 713/1073 ━━━━━━━━━━━━━━━━━━━━ 14s 40ms/step - accuracy: 0.7252 - loss: 0.6547 715/1073 ━━━━━━━━━━━━━━━━━━━━ 14s 40ms/step - accuracy: 0.7252 - loss: 0.6547 717/1073 ━━━━━━━━━━━━━━━━━━━━ 14s 40ms/step - accuracy: 0.7252 - loss: 0.6547 719/1073 ━━━━━━━━━━━━━━━━━━━━ 14s 40ms/step - accuracy: 0.7252 - loss: 0.6546 721/1073 ━━━━━━━━━━━━━━━━━━━━ 14s 40ms/step - accuracy: 0.7252 - loss: 0.6546 723/1073 ━━━━━━━━━━━━━━━━━━━━ 13s 40ms/step - accuracy: 0.7252 - loss: 0.6546 725/1073 ━━━━━━━━━━━━━━━━━━━━ 13s 40ms/step - accuracy: 0.7252 - loss: 0.6546 727/1073 ━━━━━━━━━━━━━━━━━━━━ 13s 40ms/step - accuracy: 0.7252 - loss: 0.6546 729/1073 ━━━━━━━━━━━━━━━━━━━━ 13s 40ms/step - accuracy: 0.7253 - loss: 0.6545 731/1073 ━━━━━━━━━━━━━━━━━━━━ 13s 40ms/step - accuracy: 0.7253 - loss: 0.6545 733/1073 ━━━━━━━━━━━━━━━━━━━━ 13s 40ms/step - accuracy: 0.7253 - loss: 0.6545 735/1073 ━━━━━━━━━━━━━━━━━━━━ 13s 40ms/step - accuracy: 0.7253 - loss: 0.6545 737/1073 ━━━━━━━━━━━━━━━━━━━━ 13s 40ms/step - accuracy: 0.7253 - loss: 0.6545 739/1073 ━━━━━━━━━━━━━━━━━━━━ 13s 40ms/step - accuracy: 0.7253 - loss: 0.6544 741/1073 ━━━━━━━━━━━━━━━━━━━━ 13s 40ms/step - accuracy: 0.7253 - loss: 0.6544 743/1073 ━━━━━━━━━━━━━━━━━━━━ 13s 40ms/step - accuracy: 0.7253 - loss: 0.6544 745/1073 ━━━━━━━━━━━━━━━━━━━━ 13s 40ms/step - accuracy: 0.7253 - loss: 0.6544 747/1073 ━━━━━━━━━━━━━━━━━━━━ 13s 40ms/step - accuracy: 0.7254 - loss: 0.6544 749/1073 ━━━━━━━━━━━━━━━━━━━━ 12s 40ms/step - accuracy: 0.7254 - loss: 0.6543 751/1073 ━━━━━━━━━━━━━━━━━━━━ 12s 40ms/step - accuracy: 0.7254 - loss: 0.6543 753/1073 ━━━━━━━━━━━━━━━━━━━━ 12s 40ms/step - accuracy: 0.7254 - loss: 0.6543 755/1073 ━━━━━━━━━━━━━━━━━━━━ 12s 40ms/step - accuracy: 0.7254 - loss: 0.6543 757/1073 ━━━━━━━━━━━━━━━━━━━━ 12s 40ms/step - accuracy: 0.7254 - loss: 0.6543 759/1073 ━━━━━━━━━━━━━━━━━━━━ 12s 40ms/step - accuracy: 0.7254 - loss: 0.6542 761/1073 ━━━━━━━━━━━━━━━━━━━━ 12s 40ms/step - accuracy: 0.7254 - loss: 0.6542 763/1073 ━━━━━━━━━━━━━━━━━━━━ 12s 40ms/step - accuracy: 0.7254 - loss: 0.6542 765/1073 ━━━━━━━━━━━━━━━━━━━━ 12s 40ms/step - accuracy: 0.7255 - loss: 0.6542 767/1073 ━━━━━━━━━━━━━━━━━━━━ 12s 40ms/step - accuracy: 0.7255 - loss: 0.6541 769/1073 ━━━━━━━━━━━━━━━━━━━━ 12s 40ms/step - accuracy: 0.7255 - loss: 0.6541 771/1073 ━━━━━━━━━━━━━━━━━━━━ 12s 40ms/step - accuracy: 0.7255 - loss: 0.6541 773/1073 ━━━━━━━━━━━━━━━━━━━━ 11s 40ms/step - accuracy: 0.7255 - loss: 0.6541 775/1073 ━━━━━━━━━━━━━━━━━━━━ 11s 40ms/step - accuracy: 0.7255 - loss: 0.6541 777/1073 ━━━━━━━━━━━━━━━━━━━━ 11s 40ms/step - accuracy: 0.7255 - loss: 0.6540 779/1073 ━━━━━━━━━━━━━━━━━━━━ 11s 40ms/step - accuracy: 0.7255 - loss: 0.6540 781/1073 ━━━━━━━━━━━━━━━━━━━━ 11s 40ms/step - accuracy: 0.7255 - loss: 0.6540 783/1073 ━━━━━━━━━━━━━━━━━━━━ 11s 40ms/step - accuracy: 0.7256 - loss: 0.6540 785/1073 ━━━━━━━━━━━━━━━━━━━━ 11s 40ms/step - accuracy: 0.7256 - loss: 0.6540 787/1073 ━━━━━━━━━━━━━━━━━━━━ 11s 40ms/step - accuracy: 0.7256 - loss: 0.6539 789/1073 ━━━━━━━━━━━━━━━━━━━━ 11s 40ms/step - accuracy: 0.7256 - loss: 0.6539 791/1073 ━━━━━━━━━━━━━━━━━━━━ 11s 40ms/step - accuracy: 0.7256 - loss: 0.6539 793/1073 ━━━━━━━━━━━━━━━━━━━━ 11s 40ms/step - accuracy: 0.7256 - loss: 0.6539 795/1073 ━━━━━━━━━━━━━━━━━━━━ 11s 40ms/step - accuracy: 0.7256 - loss: 0.6539 797/1073 ━━━━━━━━━━━━━━━━━━━━ 11s 40ms/step - accuracy: 0.7256 - loss: 0.6538 799/1073 ━━━━━━━━━━━━━━━━━━━━ 10s 40ms/step - accuracy: 0.7257 - loss: 0.6538 801/1073 ━━━━━━━━━━━━━━━━━━━━ 10s 40ms/step - accuracy: 0.7257 - loss: 0.6538 803/1073 ━━━━━━━━━━━━━━━━━━━━ 10s 40ms/step - accuracy: 0.7257 - loss: 0.6538 805/1073 ━━━━━━━━━━━━━━━━━━━━ 10s 40ms/step - accuracy: 0.7257 - loss: 0.6538 807/1073 ━━━━━━━━━━━━━━━━━━━━ 10s 40ms/step - accuracy: 0.7257 - loss: 0.6537 809/1073 ━━━━━━━━━━━━━━━━━━━━ 10s 40ms/step - accuracy: 0.7257 - loss: 0.6537 811/1073 ━━━━━━━━━━━━━━━━━━━━ 10s 40ms/step - accuracy: 0.7257 - loss: 0.6537 813/1073 ━━━━━━━━━━━━━━━━━━━━ 10s 40ms/step - accuracy: 0.7257 - loss: 0.6537 815/1073 ━━━━━━━━━━━━━━━━━━━━ 10s 40ms/step - accuracy: 0.7257 - loss: 0.6537 817/1073 ━━━━━━━━━━━━━━━━━━━━ 10s 40ms/step - accuracy: 0.7258 - loss: 0.6536 819/1073 ━━━━━━━━━━━━━━━━━━━━ 10s 40ms/step - accuracy: 0.7258 - loss: 0.6536 821/1073 ━━━━━━━━━━━━━━━━━━━━ 10s 40ms/step - accuracy: 0.7258 - loss: 0.6536 823/1073 ━━━━━━━━━━━━━━━━━━━━ 10s 40ms/step - accuracy: 0.7258 - loss: 0.6536 825/1073 ━━━━━━━━━━━━━━━━━━━━ 9s 40ms/step - accuracy: 0.7258 - loss: 0.6536 827/1073 ━━━━━━━━━━━━━━━━━━━━ 9s 40ms/step - accuracy: 0.7258 - loss: 0.6535 829/1073 ━━━━━━━━━━━━━━━━━━━━ 9s 40ms/step - accuracy: 0.7258 - loss: 0.6535 831/1073 ━━━━━━━━━━━━━━━━━━━━ 9s 40ms/step - accuracy: 0.7258 - loss: 0.6535 833/1073 ━━━━━━━━━━━━━━━━━━━━ 9s 40ms/step - accuracy: 0.7258 - loss: 0.6535 835/1073 ━━━━━━━━━━━━━━━━━━━━ 9s 40ms/step - accuracy: 0.7259 - loss: 0.6534 837/1073 ━━━━━━━━━━━━━━━━━━━━ 9s 40ms/step - accuracy: 0.7259 - loss: 0.6534 839/1073 ━━━━━━━━━━━━━━━━━━━━ 9s 40ms/step - accuracy: 0.7259 - loss: 0.6534 841/1073 ━━━━━━━━━━━━━━━━━━━━ 9s 40ms/step - accuracy: 0.7259 - loss: 0.6534 843/1073 ━━━━━━━━━━━━━━━━━━━━ 9s 40ms/step - accuracy: 0.7259 - loss: 0.6534 845/1073 ━━━━━━━━━━━━━━━━━━━━ 9s 40ms/step - accuracy: 0.7259 - loss: 0.6533 847/1073 ━━━━━━━━━━━━━━━━━━━━ 9s 40ms/step - accuracy: 0.7259 - loss: 0.6533 849/1073 ━━━━━━━━━━━━━━━━━━━━ 8s 40ms/step - accuracy: 0.7259 - loss: 0.6533 851/1073 ━━━━━━━━━━━━━━━━━━━━ 8s 40ms/step - accuracy: 0.7259 - loss: 0.6533 853/1073 ━━━━━━━━━━━━━━━━━━━━ 8s 40ms/step - accuracy: 0.7260 - loss: 0.6533 855/1073 ━━━━━━━━━━━━━━━━━━━━ 8s 40ms/step - accuracy: 0.7260 - loss: 0.6532 857/1073 ━━━━━━━━━━━━━━━━━━━━ 8s 40ms/step - accuracy: 0.7260 - loss: 0.6532 859/1073 ━━━━━━━━━━━━━━━━━━━━ 8s 40ms/step - accuracy: 0.7260 - loss: 0.6532 861/1073 ━━━━━━━━━━━━━━━━━━━━ 8s 40ms/step - accuracy: 0.7260 - loss: 0.6532 863/1073 ━━━━━━━━━━━━━━━━━━━━ 8s 40ms/step - accuracy: 0.7260 - loss: 0.6532 865/1073 ━━━━━━━━━━━━━━━━━━━━ 8s 40ms/step - accuracy: 0.7260 - loss: 0.6531 867/1073 ━━━━━━━━━━━━━━━━━━━━ 8s 40ms/step - accuracy: 0.7260 - loss: 0.6531 869/1073 ━━━━━━━━━━━━━━━━━━━━ 8s 40ms/step - accuracy: 0.7261 - loss: 0.6531 871/1073 ━━━━━━━━━━━━━━━━━━━━ 8s 40ms/step - accuracy: 0.7261 - loss: 0.6531 873/1073 ━━━━━━━━━━━━━━━━━━━━ 8s 40ms/step - accuracy: 0.7261 - loss: 0.6531 875/1073 ━━━━━━━━━━━━━━━━━━━━ 7s 40ms/step - accuracy: 0.7261 - loss: 0.6530 877/1073 ━━━━━━━━━━━━━━━━━━━━ 7s 40ms/step - accuracy: 0.7261 - loss: 0.6530 879/1073 ━━━━━━━━━━━━━━━━━━━━ 7s 40ms/step - accuracy: 0.7261 - loss: 0.6530 881/1073 ━━━━━━━━━━━━━━━━━━━━ 7s 40ms/step - accuracy: 0.7261 - loss: 0.6530 883/1073 ━━━━━━━━━━━━━━━━━━━━ 7s 40ms/step - accuracy: 0.7261 - loss: 0.6530 885/1073 ━━━━━━━━━━━━━━━━━━━━ 7s 40ms/step - accuracy: 0.7261 - loss: 0.6529 887/1073 ━━━━━━━━━━━━━━━━━━━━ 7s 40ms/step - accuracy: 0.7262 - loss: 0.6529 889/1073 ━━━━━━━━━━━━━━━━━━━━ 7s 40ms/step - accuracy: 0.7262 - loss: 0.6529 891/1073 ━━━━━━━━━━━━━━━━━━━━ 7s 40ms/step - accuracy: 0.7262 - loss: 0.6529 893/1073 ━━━━━━━━━━━━━━━━━━━━ 7s 40ms/step - accuracy: 0.7262 - loss: 0.6529 895/1073 ━━━━━━━━━━━━━━━━━━━━ 7s 40ms/step - accuracy: 0.7262 - loss: 0.6528 897/1073 ━━━━━━━━━━━━━━━━━━━━ 7s 40ms/step - accuracy: 0.7262 - loss: 0.6528 899/1073 ━━━━━━━━━━━━━━━━━━━━ 6s 40ms/step - accuracy: 0.7262 - loss: 0.6528 901/1073 ━━━━━━━━━━━━━━━━━━━━ 6s 40ms/step - accuracy: 0.7262 - loss: 0.6528 903/1073 ━━━━━━━━━━━━━━━━━━━━ 6s 40ms/step - accuracy: 0.7262 - loss: 0.6528 905/1073 ━━━━━━━━━━━━━━━━━━━━ 6s 40ms/step - accuracy: 0.7263 - loss: 0.6527 907/1073 ━━━━━━━━━━━━━━━━━━━━ 6s 40ms/step - accuracy: 0.7263 - loss: 0.6527 909/1073 ━━━━━━━━━━━━━━━━━━━━ 6s 40ms/step - accuracy: 0.7263 - loss: 0.6527 911/1073 ━━━━━━━━━━━━━━━━━━━━ 6s 40ms/step - accuracy: 0.7263 - loss: 0.6527 913/1073 ━━━━━━━━━━━━━━━━━━━━ 6s 40ms/step - accuracy: 0.7263 - loss: 0.6527 915/1073 ━━━━━━━━━━━━━━━━━━━━ 6s 40ms/step - accuracy: 0.7263 - loss: 0.6526 917/1073 ━━━━━━━━━━━━━━━━━━━━ 6s 40ms/step - accuracy: 0.7263 - loss: 0.6526 919/1073 ━━━━━━━━━━━━━━━━━━━━ 6s 40ms/step - accuracy: 0.7263 - loss: 0.6526 921/1073 ━━━━━━━━━━━━━━━━━━━━ 6s 40ms/step - accuracy: 0.7263 - loss: 0.6526 923/1073 ━━━━━━━━━━━━━━━━━━━━ 6s 40ms/step - accuracy: 0.7264 - loss: 0.6525 925/1073 ━━━━━━━━━━━━━━━━━━━━ 5s 40ms/step - accuracy: 0.7264 - loss: 0.6525 927/1073 ━━━━━━━━━━━━━━━━━━━━ 5s 40ms/step - accuracy: 0.7264 - loss: 0.6525 929/1073 ━━━━━━━━━━━━━━━━━━━━ 5s 40ms/step - accuracy: 0.7264 - loss: 0.6525 931/1073 ━━━━━━━━━━━━━━━━━━━━ 5s 40ms/step - accuracy: 0.7264 - loss: 0.6525 933/1073 ━━━━━━━━━━━━━━━━━━━━ 5s 40ms/step - accuracy: 0.7264 - loss: 0.6524 935/1073 ━━━━━━━━━━━━━━━━━━━━ 5s 40ms/step - accuracy: 0.7264 - loss: 0.6524 937/1073 ━━━━━━━━━━━━━━━━━━━━ 5s 40ms/step - accuracy: 0.7264 - loss: 0.6524 939/1073 ━━━━━━━━━━━━━━━━━━━━ 5s 40ms/step - accuracy: 0.7265 - loss: 0.6524 941/1073 ━━━━━━━━━━━━━━━━━━━━ 5s 40ms/step - accuracy: 0.7265 - loss: 0.6524 943/1073 ━━━━━━━━━━━━━━━━━━━━ 5s 40ms/step - accuracy: 0.7265 - loss: 0.6523 945/1073 ━━━━━━━━━━━━━━━━━━━━ 5s 40ms/step - accuracy: 0.7265 - loss: 0.6523 947/1073 ━━━━━━━━━━━━━━━━━━━━ 5s 40ms/step - accuracy: 0.7265 - loss: 0.6523 949/1073 ━━━━━━━━━━━━━━━━━━━━ 4s 40ms/step - accuracy: 0.7265 - loss: 0.6523 951/1073 ━━━━━━━━━━━━━━━━━━━━ 4s 40ms/step - accuracy: 0.7265 - loss: 0.6523 953/1073 ━━━━━━━━━━━━━━━━━━━━ 4s 40ms/step - accuracy: 0.7265 - loss: 0.6522 955/1073 ━━━━━━━━━━━━━━━━━━━━ 4s 40ms/step - accuracy: 0.7265 - loss: 0.6522 957/1073 ━━━━━━━━━━━━━━━━━━━━ 4s 40ms/step - accuracy: 0.7266 - loss: 0.6522 959/1073 ━━━━━━━━━━━━━━━━━━━━ 4s 40ms/step - accuracy: 0.7266 - loss: 0.6522 961/1073 ━━━━━━━━━━━━━━━━━━━━ 4s 40ms/step - accuracy: 0.7266 - loss: 0.6522 963/1073 ━━━━━━━━━━━━━━━━━━━━ 4s 40ms/step - accuracy: 0.7266 - loss: 0.6521 965/1073 ━━━━━━━━━━━━━━━━━━━━ 4s 40ms/step - accuracy: 0.7266 - loss: 0.6521 967/1073 ━━━━━━━━━━━━━━━━━━━━ 4s 40ms/step - accuracy: 0.7266 - loss: 0.6521 969/1073 ━━━━━━━━━━━━━━━━━━━━ 4s 40ms/step - accuracy: 0.7266 - loss: 0.6521 971/1073 ━━━━━━━━━━━━━━━━━━━━ 4s 40ms/step - accuracy: 0.7266 - loss: 0.6520 973/1073 ━━━━━━━━━━━━━━━━━━━━ 4s 40ms/step - accuracy: 0.7266 - loss: 0.6520 975/1073 ━━━━━━━━━━━━━━━━━━━━ 3s 40ms/step - accuracy: 0.7267 - loss: 0.6520 977/1073 ━━━━━━━━━━━━━━━━━━━━ 3s 40ms/step - accuracy: 0.7267 - loss: 0.6520 979/1073 ━━━━━━━━━━━━━━━━━━━━ 3s 40ms/step - accuracy: 0.7267 - loss: 0.6520 981/1073 ━━━━━━━━━━━━━━━━━━━━ 3s 40ms/step - accuracy: 0.7267 - loss: 0.6519 983/1073 ━━━━━━━━━━━━━━━━━━━━ 3s 40ms/step - accuracy: 0.7267 - loss: 0.6519 985/1073 ━━━━━━━━━━━━━━━━━━━━ 3s 40ms/step - accuracy: 0.7267 - loss: 0.6519 987/1073 ━━━━━━━━━━━━━━━━━━━━ 3s 40ms/step - accuracy: 0.7267 - loss: 0.6519 989/1073 ━━━━━━━━━━━━━━━━━━━━ 3s 40ms/step - accuracy: 0.7267 - loss: 0.6519 991/1073 ━━━━━━━━━━━━━━━━━━━━ 3s 40ms/step - accuracy: 0.7267 - loss: 0.6518 993/1073 ━━━━━━━━━━━━━━━━━━━━ 3s 40ms/step - accuracy: 0.7268 - loss: 0.6518 995/1073 ━━━━━━━━━━━━━━━━━━━━ 3s 40ms/step - accuracy: 0.7268 - loss: 0.6518 997/1073 ━━━━━━━━━━━━━━━━━━━━ 3s 40ms/step - accuracy: 0.7268 - loss: 0.6518 999/1073 ━━━━━━━━━━━━━━━━━━━━ 2s 40ms/step - accuracy: 0.7268 - loss: 0.65181001/1073 ━━━━━━━━━━━━━━━━━━━━ 2s 40ms/step - accuracy: 0.7268 - loss: 0.65171003/1073 ━━━━━━━━━━━━━━━━━━━━ 2s 40ms/step - accuracy: 0.7268 - loss: 0.65171005/1073 ━━━━━━━━━━━━━━━━━━━━ 2s 40ms/step - accuracy: 0.7268 - loss: 0.65171007/1073 ━━━━━━━━━━━━━━━━━━━━ 2s 40ms/step - accuracy: 0.7268 - loss: 0.65171009/1073 ━━━━━━━━━━━━━━━━━━━━ 2s 40ms/step - accuracy: 0.7268 - loss: 0.65171011/1073 ━━━━━━━━━━━━━━━━━━━━ 2s 40ms/step - accuracy: 0.7269 - loss: 0.65161013/1073 ━━━━━━━━━━━━━━━━━━━━ 2s 40ms/step - accuracy: 0.7269 - loss: 0.65161015/1073 ━━━━━━━━━━━━━━━━━━━━ 2s 40ms/step - accuracy: 0.7269 - loss: 0.65161017/1073 ━━━━━━━━━━━━━━━━━━━━ 2s 40ms/step - accuracy: 0.7269 - loss: 0.65161019/1073 ━━━━━━━━━━━━━━━━━━━━ 2s 40ms/step - accuracy: 0.7269 - loss: 0.65161021/1073 ━━━━━━━━━━━━━━━━━━━━ 2s 40ms/step - accuracy: 0.7269 - loss: 0.65151023/1073 ━━━━━━━━━━━━━━━━━━━━ 2s 40ms/step - accuracy: 0.7269 - loss: 0.65151025/1073 ━━━━━━━━━━━━━━━━━━━━ 1s 40ms/step - accuracy: 0.7269 - loss: 0.65151027/1073 ━━━━━━━━━━━━━━━━━━━━ 1s 40ms/step - accuracy: 0.7269 - loss: 0.65151029/1073 ━━━━━━━━━━━━━━━━━━━━ 1s 40ms/step - accuracy: 0.7270 - loss: 0.65151031/1073 ━━━━━━━━━━━━━━━━━━━━ 1s 40ms/step - accuracy: 0.7270 - loss: 0.65141033/1073 ━━━━━━━━━━━━━━━━━━━━ 1s 40ms/step - accuracy: 0.7270 - loss: 0.65141035/1073 ━━━━━━━━━━━━━━━━━━━━ 1s 40ms/step - accuracy: 0.7270 - loss: 0.65141037/1073 ━━━━━━━━━━━━━━━━━━━━ 1s 40ms/step - accuracy: 0.7270 - loss: 0.65141039/1073 ━━━━━━━━━━━━━━━━━━━━ 1s 40ms/step - accuracy: 0.7270 - loss: 0.65141041/1073 ━━━━━━━━━━━━━━━━━━━━ 1s 40ms/step - accuracy: 0.7270 - loss: 0.65131043/1073 ━━━━━━━━━━━━━━━━━━━━ 1s 40ms/step - accuracy: 0.7270 - loss: 0.65131045/1073 ━━━━━━━━━━━━━━━━━━━━ 1s 40ms/step - accuracy: 0.7270 - loss: 0.65131047/1073 ━━━━━━━━━━━━━━━━━━━━ 1s 40ms/step - accuracy: 0.7271 - loss: 0.65131049/1073 ━━━━━━━━━━━━━━━━━━━━ 0s 40ms/step - accuracy: 0.7271 - loss: 0.65131051/1073 ━━━━━━━━━━━━━━━━━━━━ 0s 40ms/step - accuracy: 0.7271 - loss: 0.65121053/1073 ━━━━━━━━━━━━━━━━━━━━ 0s 40ms/step - accuracy: 0.7271 - loss: 0.65121055/1073 ━━━━━━━━━━━━━━━━━━━━ 0s 40ms/step - accuracy: 0.7271 - loss: 0.65121057/1073 ━━━━━━━━━━━━━━━━━━━━ 0s 40ms/step - accuracy: 0.7271 - loss: 0.65121059/1073 ━━━━━━━━━━━━━━━━━━━━ 0s 40ms/step - accuracy: 0.7271 - loss: 0.65121061/1073 ━━━━━━━━━━━━━━━━━━━━ 0s 40ms/step - accuracy: 0.7271 - loss: 0.65111063/1073 ━━━━━━━━━━━━━━━━━━━━ 0s 40ms/step - accuracy: 0.7271 - loss: 0.65111065/1073 ━━━━━━━━━━━━━━━━━━━━ 0s 40ms/step - accuracy: 0.7271 - loss: 0.65111067/1073 ━━━━━━━━━━━━━━━━━━━━ 0s 40ms/step - accuracy: 0.7272 - loss: 0.65111069/1073 ━━━━━━━━━━━━━━━━━━━━ 0s 40ms/step - accuracy: 0.7272 - loss: 0.65111071/1073 ━━━━━━━━━━━━━━━━━━━━ 0s 40ms/step - accuracy: 0.7272 - loss: 0.65101073/1073 ━━━━━━━━━━━━━━━━━━━━ 0s 40ms/step - accuracy: 0.7272 - loss: 0.65101073/1073 ━━━━━━━━━━━━━━━━━━━━ 44s 40ms/step - accuracy: 0.7329 - loss: 0.6404 - val_accuracy: 0.7465 - val_loss: 0.6032Epoch 3/5 1/1073 ━━━━━━━━━━━━━━━━━━━━ 16:43 936ms/step - accuracy: 0.7695 - loss: 0.5752 3/1073 ━━━━━━━━━━━━━━━━━━━━ 42s 39ms/step - accuracy: 0.7614 - loss: 0.5770 5/1073 ━━━━━━━━━━━━━━━━━━━━ 41s 39ms/step - accuracy: 0.7607 - loss: 0.5773 7/1073 ━━━━━━━━━━━━━━━━━━━━ 41s 39ms/step - accuracy: 0.7607 - loss: 0.5764 9/1073 ━━━━━━━━━━━━━━━━━━━━ 41s 39ms/step - accuracy: 0.7613 - loss: 0.5758 11/1073 ━━━━━━━━━━━━━━━━━━━━ 41s 40ms/step - accuracy: 0.7615 - loss: 0.5760 13/1073 ━━━━━━━━━━━━━━━━━━━━ 41s 40ms/step - accuracy: 0.7617 - loss: 0.5762 15/1073 ━━━━━━━━━━━━━━━━━━━━ 41s 40ms/step - accuracy: 0.7619 - loss: 0.5765 17/1073 ━━━━━━━━━━━━━━━━━━━━ 41s 40ms/step - accuracy: 0.7619 - loss: 0.5771 19/1073 ━━━━━━━━━━━━━━━━━━━━ 41s 40ms/step - accuracy: 0.7622 - loss: 0.5772 21/1073 ━━━━━━━━━━━━━━━━━━━━ 41s 40ms/step - accuracy: 0.7626 - loss: 0.5770 23/1073 ━━━━━━━━━━━━━━━━━━━━ 41s 40ms/step - accuracy: 0.7629 - loss: 0.5767 25/1073 ━━━━━━━━━━━━━━━━━━━━ 41s 40ms/step - accuracy: 0.7632 - loss: 0.5763 27/1073 ━━━━━━━━━━━━━━━━━━━━ 41s 40ms/step - accuracy: 0.7636 - loss: 0.5758 29/1073 ━━━━━━━━━━━━━━━━━━━━ 41s 40ms/step - accuracy: 0.7639 - loss: 0.5753 31/1073 ━━━━━━━━━━━━━━━━━━━━ 41s 40ms/step - accuracy: 0.7643 - loss: 0.5748 33/1073 ━━━━━━━━━━━━━━━━━━━━ 41s 40ms/step - accuracy: 0.7646 - loss: 0.5742 35/1073 ━━━━━━━━━━━━━━━━━━━━ 41s 40ms/step - accuracy: 0.7649 - loss: 0.5737 37/1073 ━━━━━━━━━━━━━━━━━━━━ 41s 40ms/step - accuracy: 0.7651 - loss: 0.5732 39/1073 ━━━━━━━━━━━━━━━━━━━━ 40s 40ms/step - accuracy: 0.7653 - loss: 0.5729 41/1073 ━━━━━━━━━━━━━━━━━━━━ 40s 40ms/step - accuracy: 0.7655 - loss: 0.5726 43/1073 ━━━━━━━━━━━━━━━━━━━━ 40s 40ms/step - accuracy: 0.7656 - loss: 0.5724 45/1073 ━━━━━━━━━━━━━━━━━━━━ 40s 40ms/step - accuracy: 0.7656 - loss: 0.5722 47/1073 ━━━━━━━━━━━━━━━━━━━━ 40s 40ms/step - accuracy: 0.7656 - loss: 0.5721 49/1073 ━━━━━━━━━━━━━━━━━━━━ 40s 40ms/step - accuracy: 0.7656 - loss: 0.5720 51/1073 ━━━━━━━━━━━━━━━━━━━━ 40s 40ms/step - accuracy: 0.7657 - loss: 0.5719 53/1073 ━━━━━━━━━━━━━━━━━━━━ 40s 40ms/step - accuracy: 0.7657 - loss: 0.5718 55/1073 ━━━━━━━━━━━━━━━━━━━━ 40s 40ms/step - accuracy: 0.7657 - loss: 0.5717 57/1073 ━━━━━━━━━━━━━━━━━━━━ 40s 40ms/step - accuracy: 0.7657 - loss: 0.5717 59/1073 ━━━━━━━━━━━━━━━━━━━━ 40s 40ms/step - accuracy: 0.7657 - loss: 0.5716 61/1073 ━━━━━━━━━━━━━━━━━━━━ 40s 40ms/step - accuracy: 0.7657 - loss: 0.5716 63/1073 ━━━━━━━━━━━━━━━━━━━━ 39s 40ms/step - accuracy: 0.7657 - loss: 0.5716 65/1073 ━━━━━━━━━━━━━━━━━━━━ 39s 40ms/step - accuracy: 0.7657 - loss: 0.5715 67/1073 ━━━━━━━━━━━━━━━━━━━━ 39s 40ms/step - accuracy: 0.7657 - loss: 0.5714 69/1073 ━━━━━━━━━━━━━━━━━━━━ 39s 40ms/step - accuracy: 0.7657 - loss: 0.5714 71/1073 ━━━━━━━━━━━━━━━━━━━━ 39s 40ms/step - accuracy: 0.7657 - loss: 0.5713 73/1073 ━━━━━━━━━━━━━━━━━━━━ 39s 40ms/step - accuracy: 0.7658 - loss: 0.5712 75/1073 ━━━━━━━━━━━━━━━━━━━━ 39s 40ms/step - accuracy: 0.7658 - loss: 0.5711 77/1073 ━━━━━━━━━━━━━━━━━━━━ 39s 40ms/step - accuracy: 0.7658 - loss: 0.5711 79/1073 ━━━━━━━━━━━━━━━━━━━━ 39s 40ms/step - accuracy: 0.7658 - loss: 0.5710 81/1073 ━━━━━━━━━━━━━━━━━━━━ 39s 40ms/step - accuracy: 0.7658 - loss: 0.5710 83/1073 ━━━━━━━━━━━━━━━━━━━━ 39s 40ms/step - accuracy: 0.7658 - loss: 0.5709 85/1073 ━━━━━━━━━━━━━━━━━━━━ 39s 40ms/step - accuracy: 0.7658 - loss: 0.5709 87/1073 ━━━━━━━━━━━━━━━━━━━━ 38s 40ms/step - accuracy: 0.7658 - loss: 0.5709 89/1073 ━━━━━━━━━━━━━━━━━━━━ 38s 40ms/step - accuracy: 0.7658 - loss: 0.5709 91/1073 ━━━━━━━━━━━━━━━━━━━━ 38s 40ms/step - accuracy: 0.7658 - loss: 0.5708 93/1073 ━━━━━━━━━━━━━━━━━━━━ 38s 40ms/step - accuracy: 0.7658 - loss: 0.5708 95/1073 ━━━━━━━━━━━━━━━━━━━━ 38s 40ms/step - accuracy: 0.7657 - loss: 0.5708 97/1073 ━━━━━━━━━━━━━━━━━━━━ 38s 40ms/step - accuracy: 0.7657 - loss: 0.5708 99/1073 ━━━━━━━━━━━━━━━━━━━━ 38s 40ms/step - accuracy: 0.7657 - loss: 0.5707 101/1073 ━━━━━━━━━━━━━━━━━━━━ 38s 40ms/step - accuracy: 0.7657 - loss: 0.5707 103/1073 ━━━━━━━━━━━━━━━━━━━━ 38s 40ms/step - accuracy: 0.7657 - loss: 0.5707 105/1073 ━━━━━━━━━━━━━━━━━━━━ 38s 40ms/step - accuracy: 0.7657 - loss: 0.5707 107/1073 ━━━━━━━━━━━━━━━━━━━━ 38s 40ms/step - accuracy: 0.7657 - loss: 0.5707 109/1073 ━━━━━━━━━━━━━━━━━━━━ 38s 40ms/step - accuracy: 0.7657 - loss: 0.5707 111/1073 ━━━━━━━━━━━━━━━━━━━━ 38s 40ms/step - accuracy: 0.7657 - loss: 0.5707 113/1073 ━━━━━━━━━━━━━━━━━━━━ 38s 40ms/step - accuracy: 0.7657 - loss: 0.5707 115/1073 ━━━━━━━━━━━━━━━━━━━━ 38s 40ms/step - accuracy: 0.7656 - loss: 0.5707 117/1073 ━━━━━━━━━━━━━━━━━━━━ 37s 40ms/step - accuracy: 0.7656 - loss: 0.5708 119/1073 ━━━━━━━━━━━━━━━━━━━━ 37s 40ms/step - accuracy: 0.7656 - loss: 0.5708 121/1073 ━━━━━━━━━━━━━━━━━━━━ 37s 40ms/step - accuracy: 0.7656 - loss: 0.5708 123/1073 ━━━━━━━━━━━━━━━━━━━━ 37s 40ms/step - accuracy: 0.7656 - loss: 0.5708 125/1073 ━━━━━━━━━━━━━━━━━━━━ 37s 40ms/step - accuracy: 0.7656 - loss: 0.5708 127/1073 ━━━━━━━━━━━━━━━━━━━━ 37s 40ms/step - accuracy: 0.7656 - loss: 0.5709 129/1073 ━━━━━━━━━━━━━━━━━━━━ 37s 40ms/step - accuracy: 0.7656 - loss: 0.5709 131/1073 ━━━━━━━━━━━━━━━━━━━━ 37s 40ms/step - accuracy: 0.7656 - loss: 0.5709 133/1073 ━━━━━━━━━━━━━━━━━━━━ 37s 40ms/step - accuracy: 0.7656 - loss: 0.5709 135/1073 ━━━━━━━━━━━━━━━━━━━━ 37s 40ms/step - accuracy: 0.7656 - loss: 0.5709 137/1073 ━━━━━━━━━━━━━━━━━━━━ 37s 40ms/step - accuracy: 0.7655 - loss: 0.5709 139/1073 ━━━━━━━━━━━━━━━━━━━━ 36s 40ms/step - accuracy: 0.7655 - loss: 0.5710 141/1073 ━━━━━━━━━━━━━━━━━━━━ 36s 40ms/step - accuracy: 0.7655 - loss: 0.5710 143/1073 ━━━━━━━━━━━━━━━━━━━━ 36s 40ms/step - accuracy: 0.7655 - loss: 0.5710 145/1073 ━━━━━━━━━━━━━━━━━━━━ 36s 40ms/step - accuracy: 0.7655 - loss: 0.5710 147/1073 ━━━━━━━━━━━━━━━━━━━━ 36s 39ms/step - accuracy: 0.7655 - loss: 0.5710 149/1073 ━━━━━━━━━━━━━━━━━━━━ 36s 39ms/step - accuracy: 0.7655 - loss: 0.5710 151/1073 ━━━━━━━━━━━━━━━━━━━━ 36s 40ms/step - accuracy: 0.7655 - loss: 0.5710 153/1073 ━━━━━━━━━━━━━━━━━━━━ 36s 39ms/step - accuracy: 0.7655 - loss: 0.5710 155/1073 ━━━━━━━━━━━━━━━━━━━━ 36s 39ms/step - accuracy: 0.7655 - loss: 0.5710 157/1073 ━━━━━━━━━━━━━━━━━━━━ 36s 39ms/step - accuracy: 0.7655 - loss: 0.5711 159/1073 ━━━━━━━━━━━━━━━━━━━━ 36s 39ms/step - accuracy: 0.7655 - loss: 0.5711 161/1073 ━━━━━━━━━━━━━━━━━━━━ 36s 39ms/step - accuracy: 0.7655 - loss: 0.5711 163/1073 ━━━━━━━━━━━━━━━━━━━━ 35s 39ms/step - accuracy: 0.7654 - loss: 0.5711 165/1073 ━━━━━━━━━━━━━━━━━━━━ 35s 39ms/step - accuracy: 0.7654 - loss: 0.5711 167/1073 ━━━━━━━━━━━━━━━━━━━━ 35s 39ms/step - accuracy: 0.7654 - loss: 0.5711 169/1073 ━━━━━━━━━━━━━━━━━━━━ 35s 39ms/step - accuracy: 0.7654 - loss: 0.5711 171/1073 ━━━━━━━━━━━━━━━━━━━━ 35s 39ms/step - accuracy: 0.7654 - loss: 0.5711 173/1073 ━━━━━━━━━━━━━━━━━━━━ 35s 39ms/step - accuracy: 0.7654 - loss: 0.5711 175/1073 ━━━━━━━━━━━━━━━━━━━━ 35s 39ms/step - accuracy: 0.7654 - loss: 0.5712 177/1073 ━━━━━━━━━━━━━━━━━━━━ 35s 39ms/step - accuracy: 0.7654 - loss: 0.5712 179/1073 ━━━━━━━━━━━━━━━━━━━━ 35s 39ms/step - accuracy: 0.7654 - loss: 0.5712 181/1073 ━━━━━━━━━━━━━━━━━━━━ 35s 39ms/step - accuracy: 0.7653 - loss: 0.5712 183/1073 ━━━━━━━━━━━━━━━━━━━━ 35s 39ms/step - accuracy: 0.7653 - loss: 0.5712 185/1073 ━━━━━━━━━━━━━━━━━━━━ 35s 39ms/step - accuracy: 0.7653 - loss: 0.5712 187/1073 ━━━━━━━━━━━━━━━━━━━━ 34s 39ms/step - accuracy: 0.7653 - loss: 0.5712 189/1073 ━━━━━━━━━━━━━━━━━━━━ 34s 39ms/step - accuracy: 0.7653 - loss: 0.5712 191/1073 ━━━━━━━━━━━━━━━━━━━━ 34s 40ms/step - accuracy: 0.7653 - loss: 0.5712 193/1073 ━━━━━━━━━━━━━━━━━━━━ 34s 40ms/step - accuracy: 0.7653 - loss: 0.5713 195/1073 ━━━━━━━━━━━━━━━━━━━━ 34s 40ms/step - accuracy: 0.7653 - loss: 0.5713 197/1073 ━━━━━━━━━━━━━━━━━━━━ 34s 40ms/step - accuracy: 0.7653 - loss: 0.5713 199/1073 ━━━━━━━━━━━━━━━━━━━━ 34s 40ms/step - accuracy: 0.7653 - loss: 0.5713 201/1073 ━━━━━━━━━━━━━━━━━━━━ 34s 40ms/step - accuracy: 0.7653 - loss: 0.5713 203/1073 ━━━━━━━━━━━━━━━━━━━━ 34s 40ms/step - accuracy: 0.7653 - loss: 0.5713 205/1073 ━━━━━━━━━━━━━━━━━━━━ 34s 40ms/step - accuracy: 0.7652 - loss: 0.5713 207/1073 ━━━━━━━━━━━━━━━━━━━━ 34s 40ms/step - accuracy: 0.7652 - loss: 0.5713 209/1073 ━━━━━━━━━━━━━━━━━━━━ 34s 40ms/step - accuracy: 0.7652 - loss: 0.5714 211/1073 ━━━━━━━━━━━━━━━━━━━━ 34s 40ms/step - accuracy: 0.7652 - loss: 0.5714 213/1073 ━━━━━━━━━━━━━━━━━━━━ 34s 40ms/step - accuracy: 0.7652 - loss: 0.5714 215/1073 ━━━━━━━━━━━━━━━━━━━━ 34s 40ms/step - accuracy: 0.7652 - loss: 0.5714 217/1073 ━━━━━━━━━━━━━━━━━━━━ 33s 40ms/step - accuracy: 0.7652 - loss: 0.5714 219/1073 ━━━━━━━━━━━━━━━━━━━━ 33s 40ms/step - accuracy: 0.7652 - loss: 0.5714 221/1073 ━━━━━━━━━━━━━━━━━━━━ 33s 40ms/step - accuracy: 0.7652 - loss: 0.5714 223/1073 ━━━━━━━━━━━━━━━━━━━━ 33s 40ms/step - accuracy: 0.7652 - loss: 0.5714 225/1073 ━━━━━━━━━━━━━━━━━━━━ 33s 40ms/step - accuracy: 0.7652 - loss: 0.5714 227/1073 ━━━━━━━━━━━━━━━━━━━━ 33s 40ms/step - accuracy: 0.7652 - loss: 0.5714 229/1073 ━━━━━━━━━━━━━━━━━━━━ 33s 40ms/step - accuracy: 0.7652 - loss: 0.5714 231/1073 ━━━━━━━━━━━━━━━━━━━━ 33s 40ms/step - accuracy: 0.7652 - loss: 0.5714 233/1073 ━━━━━━━━━━━━━━━━━━━━ 33s 40ms/step - accuracy: 0.7652 - loss: 0.5714 235/1073 ━━━━━━━━━━━━━━━━━━━━ 33s 40ms/step - accuracy: 0.7652 - loss: 0.5714 237/1073 ━━━━━━━━━━━━━━━━━━━━ 33s 40ms/step - accuracy: 0.7652 - loss: 0.5714 239/1073 ━━━━━━━━━━━━━━━━━━━━ 33s 40ms/step - accuracy: 0.7652 - loss: 0.5714 241/1073 ━━━━━━━━━━━━━━━━━━━━ 33s 40ms/step - accuracy: 0.7652 - loss: 0.5714 243/1073 ━━━━━━━━━━━━━━━━━━━━ 32s 40ms/step - accuracy: 0.7652 - loss: 0.5714 245/1073 ━━━━━━━━━━━━━━━━━━━━ 32s 40ms/step - accuracy: 0.7652 - loss: 0.5714 247/1073 ━━━━━━━━━━━━━━━━━━━━ 32s 40ms/step - accuracy: 0.7652 - loss: 0.5715 249/1073 ━━━━━━━━━━━━━━━━━━━━ 32s 40ms/step - accuracy: 0.7652 - loss: 0.5715 251/1073 ━━━━━━━━━━━━━━━━━━━━ 32s 40ms/step - accuracy: 0.7652 - loss: 0.5715 253/1073 ━━━━━━━━━━━━━━━━━━━━ 32s 40ms/step - accuracy: 0.7652 - loss: 0.5715 255/1073 ━━━━━━━━━━━━━━━━━━━━ 32s 40ms/step - accuracy: 0.7652 - loss: 0.5715 257/1073 ━━━━━━━━━━━━━━━━━━━━ 32s 40ms/step - accuracy: 0.7652 - loss: 0.5715 259/1073 ━━━━━━━━━━━━━━━━━━━━ 32s 40ms/step - accuracy: 0.7652 - loss: 0.5715 261/1073 ━━━━━━━━━━━━━━━━━━━━ 32s 40ms/step - accuracy: 0.7652 - loss: 0.5715 263/1073 ━━━━━━━━━━━━━━━━━━━━ 32s 40ms/step - accuracy: 0.7652 - loss: 0.5715 265/1073 ━━━━━━━━━━━━━━━━━━━━ 32s 40ms/step - accuracy: 0.7652 - loss: 0.5715 267/1073 ━━━━━━━━━━━━━━━━━━━━ 32s 40ms/step - accuracy: 0.7652 - loss: 0.5715 269/1073 ━━━━━━━━━━━━━━━━━━━━ 31s 40ms/step - accuracy: 0.7652 - loss: 0.5715 271/1073 ━━━━━━━━━━━━━━━━━━━━ 31s 40ms/step - accuracy: 0.7652 - loss: 0.5715 273/1073 ━━━━━━━━━━━━━━━━━━━━ 31s 40ms/step - accuracy: 0.7652 - loss: 0.5715 275/1073 ━━━━━━━━━━━━━━━━━━━━ 31s 40ms/step - accuracy: 0.7652 - loss: 0.5715 277/1073 ━━━━━━━━━━━━━━━━━━━━ 31s 40ms/step - accuracy: 0.7652 - loss: 0.5715 279/1073 ━━━━━━━━━━━━━━━━━━━━ 31s 40ms/step - accuracy: 0.7652 - loss: 0.5715 281/1073 ━━━━━━━━━━━━━━━━━━━━ 31s 40ms/step - accuracy: 0.7652 - loss: 0.5715 283/1073 ━━━━━━━━━━━━━━━━━━━━ 31s 40ms/step - accuracy: 0.7652 - loss: 0.5715 285/1073 ━━━━━━━━━━━━━━━━━━━━ 31s 40ms/step - accuracy: 0.7652 - loss: 0.5715 287/1073 ━━━━━━━━━━━━━━━━━━━━ 31s 40ms/step - accuracy: 0.7652 - loss: 0.5715 289/1073 ━━━━━━━━━━━━━━━━━━━━ 31s 40ms/step - accuracy: 0.7652 - loss: 0.5715 291/1073 ━━━━━━━━━━━━━━━━━━━━ 31s 40ms/step - accuracy: 0.7652 - loss: 0.5715 293/1073 ━━━━━━━━━━━━━━━━━━━━ 31s 40ms/step - accuracy: 0.7652 - loss: 0.5715 295/1073 ━━━━━━━━━━━━━━━━━━━━ 31s 40ms/step - accuracy: 0.7652 - loss: 0.5715 297/1073 ━━━━━━━━━━━━━━━━━━━━ 30s 40ms/step - accuracy: 0.7652 - loss: 0.5716 299/1073 ━━━━━━━━━━━━━━━━━━━━ 30s 40ms/step - accuracy: 0.7651 - loss: 0.5716 301/1073 ━━━━━━━━━━━━━━━━━━━━ 30s 40ms/step - accuracy: 0.7651 - loss: 0.5716 303/1073 ━━━━━━━━━━━━━━━━━━━━ 30s 40ms/step - accuracy: 0.7651 - loss: 0.5716 305/1073 ━━━━━━━━━━━━━━━━━━━━ 30s 40ms/step - accuracy: 0.7651 - loss: 0.5716 307/1073 ━━━━━━━━━━━━━━━━━━━━ 30s 40ms/step - accuracy: 0.7651 - loss: 0.5716 309/1073 ━━━━━━━━━━━━━━━━━━━━ 30s 40ms/step - accuracy: 0.7651 - loss: 0.5716 311/1073 ━━━━━━━━━━━━━━━━━━━━ 30s 40ms/step - accuracy: 0.7651 - loss: 0.5716 313/1073 ━━━━━━━━━━━━━━━━━━━━ 30s 40ms/step - accuracy: 0.7651 - loss: 0.5716 315/1073 ━━━━━━━━━━━━━━━━━━━━ 30s 40ms/step - accuracy: 0.7651 - loss: 0.5716 317/1073 ━━━━━━━━━━━━━━━━━━━━ 30s 40ms/step - accuracy: 0.7651 - loss: 0.5716 319/1073 ━━━━━━━━━━━━━━━━━━━━ 30s 40ms/step - accuracy: 0.7651 - loss: 0.5716 321/1073 ━━━━━━━━━━━━━━━━━━━━ 29s 40ms/step - accuracy: 0.7651 - loss: 0.5716 323/1073 ━━━━━━━━━━━━━━━━━━━━ 29s 40ms/step - accuracy: 0.7651 - loss: 0.5716 325/1073 ━━━━━━━━━━━━━━━━━━━━ 29s 40ms/step - accuracy: 0.7651 - loss: 0.5717 327/1073 ━━━━━━━━━━━━━━━━━━━━ 29s 40ms/step - accuracy: 0.7651 - loss: 0.5717 329/1073 ━━━━━━━━━━━━━━━━━━━━ 29s 40ms/step - accuracy: 0.7651 - loss: 0.5717 331/1073 ━━━━━━━━━━━━━━━━━━━━ 29s 40ms/step - accuracy: 0.7651 - loss: 0.5717 333/1073 ━━━━━━━━━━━━━━━━━━━━ 29s 40ms/step - accuracy: 0.7651 - loss: 0.5717 335/1073 ━━━━━━━━━━━━━━━━━━━━ 29s 40ms/step - accuracy: 0.7651 - loss: 0.5717 337/1073 ━━━━━━━━━━━━━━━━━━━━ 29s 40ms/step - accuracy: 0.7651 - loss: 0.5717 339/1073 ━━━━━━━━━━━━━━━━━━━━ 29s 40ms/step - accuracy: 0.7651 - loss: 0.5717 341/1073 ━━━━━━━━━━━━━━━━━━━━ 29s 40ms/step - accuracy: 0.7651 - loss: 0.5717 343/1073 ━━━━━━━━━━━━━━━━━━━━ 29s 40ms/step - accuracy: 0.7651 - loss: 0.5717 345/1073 ━━━━━━━━━━━━━━━━━━━━ 29s 40ms/step - accuracy: 0.7651 - loss: 0.5717 347/1073 ━━━━━━━━━━━━━━━━━━━━ 28s 40ms/step - accuracy: 0.7651 - loss: 0.5717 349/1073 ━━━━━━━━━━━━━━━━━━━━ 28s 40ms/step - accuracy: 0.7651 - loss: 0.5717 351/1073 ━━━━━━━━━━━━━━━━━━━━ 28s 40ms/step - accuracy: 0.7651 - loss: 0.5717 353/1073 ━━━━━━━━━━━━━━━━━━━━ 28s 40ms/step - accuracy: 0.7651 - loss: 0.5717 355/1073 ━━━━━━━━━━━━━━━━━━━━ 28s 40ms/step - accuracy: 0.7651 - loss: 0.5718 357/1073 ━━━━━━━━━━━━━━━━━━━━ 28s 40ms/step - accuracy: 0.7651 - loss: 0.5718 359/1073 ━━━━━━━━━━━━━━━━━━━━ 28s 40ms/step - accuracy: 0.7651 - loss: 0.5718 361/1073 ━━━━━━━━━━━━━━━━━━━━ 28s 40ms/step - accuracy: 0.7650 - loss: 0.5718 363/1073 ━━━━━━━━━━━━━━━━━━━━ 28s 40ms/step - accuracy: 0.7650 - loss: 0.5718 365/1073 ━━━━━━━━━━━━━━━━━━━━ 28s 40ms/step - accuracy: 0.7650 - loss: 0.5718 367/1073 ━━━━━━━━━━━━━━━━━━━━ 28s 40ms/step - accuracy: 0.7650 - loss: 0.5718 369/1073 ━━━━━━━━━━━━━━━━━━━━ 28s 40ms/step - accuracy: 0.7650 - loss: 0.5718 371/1073 ━━━━━━━━━━━━━━━━━━━━ 28s 40ms/step - accuracy: 0.7650 - loss: 0.5718 373/1073 ━━━━━━━━━━━━━━━━━━━━ 27s 40ms/step - accuracy: 0.7650 - loss: 0.5718 375/1073 ━━━━━━━━━━━━━━━━━━━━ 27s 40ms/step - accuracy: 0.7650 - loss: 0.5718 377/1073 ━━━━━━━━━━━━━━━━━━━━ 27s 40ms/step - accuracy: 0.7650 - loss: 0.5718 379/1073 ━━━━━━━━━━━━━━━━━━━━ 27s 40ms/step - accuracy: 0.7650 - loss: 0.5718 381/1073 ━━━━━━━━━━━━━━━━━━━━ 27s 40ms/step - accuracy: 0.7650 - loss: 0.5718 383/1073 ━━━━━━━━━━━━━━━━━━━━ 27s 40ms/step - accuracy: 0.7650 - loss: 0.5718 385/1073 ━━━━━━━━━━━━━━━━━━━━ 27s 40ms/step - accuracy: 0.7650 - loss: 0.5718 387/1073 ━━━━━━━━━━━━━━━━━━━━ 27s 40ms/step - accuracy: 0.7650 - loss: 0.5718 389/1073 ━━━━━━━━━━━━━━━━━━━━ 27s 40ms/step - accuracy: 0.7650 - loss: 0.5719 391/1073 ━━━━━━━━━━━━━━━━━━━━ 27s 40ms/step - accuracy: 0.7650 - loss: 0.5719 393/1073 ━━━━━━━━━━━━━━━━━━━━ 27s 40ms/step - accuracy: 0.7650 - loss: 0.5719 395/1073 ━━━━━━━━━━━━━━━━━━━━ 27s 40ms/step - accuracy: 0.7650 - loss: 0.5719 397/1073 ━━━━━━━━━━━━━━━━━━━━ 26s 40ms/step - accuracy: 0.7650 - loss: 0.5719 399/1073 ━━━━━━━━━━━━━━━━━━━━ 26s 40ms/step - accuracy: 0.7650 - loss: 0.5719 401/1073 ━━━━━━━━━━━━━━━━━━━━ 26s 40ms/step - accuracy: 0.7650 - loss: 0.5719 403/1073 ━━━━━━━━━━━━━━━━━━━━ 26s 40ms/step - accuracy: 0.7650 - loss: 0.5719 405/1073 ━━━━━━━━━━━━━━━━━━━━ 26s 40ms/step - accuracy: 0.7650 - loss: 0.5719 407/1073 ━━━━━━━━━━━━━━━━━━━━ 26s 40ms/step - accuracy: 0.7650 - loss: 0.5719 409/1073 ━━━━━━━━━━━━━━━━━━━━ 26s 40ms/step - accuracy: 0.7650 - loss: 0.5719 411/1073 ━━━━━━━━━━━━━━━━━━━━ 26s 40ms/step - accuracy: 0.7650 - loss: 0.5719 413/1073 ━━━━━━━━━━━━━━━━━━━━ 26s 40ms/step - accuracy: 0.7650 - loss: 0.5719 415/1073 ━━━━━━━━━━━━━━━━━━━━ 26s 40ms/step - accuracy: 0.7650 - loss: 0.5719 417/1073 ━━━━━━━━━━━━━━━━━━━━ 26s 40ms/step - accuracy: 0.7650 - loss: 0.5719 419/1073 ━━━━━━━━━━━━━━━━━━━━ 26s 40ms/step - accuracy: 0.7650 - loss: 0.5719 421/1073 ━━━━━━━━━━━━━━━━━━━━ 25s 40ms/step - accuracy: 0.7650 - loss: 0.5719 423/1073 ━━━━━━━━━━━━━━━━━━━━ 25s 40ms/step - accuracy: 0.7650 - loss: 0.5719 425/1073 ━━━━━━━━━━━━━━━━━━━━ 25s 40ms/step - accuracy: 0.7650 - loss: 0.5719 427/1073 ━━━━━━━━━━━━━━━━━━━━ 25s 40ms/step - accuracy: 0.7650 - loss: 0.5720 429/1073 ━━━━━━━━━━━━━━━━━━━━ 25s 40ms/step - accuracy: 0.7650 - loss: 0.5720 431/1073 ━━━━━━━━━━━━━━━━━━━━ 25s 40ms/step - accuracy: 0.7650 - loss: 0.5720 433/1073 ━━━━━━━━━━━━━━━━━━━━ 25s 40ms/step - accuracy: 0.7650 - loss: 0.5720 435/1073 ━━━━━━━━━━━━━━━━━━━━ 25s 40ms/step - accuracy: 0.7650 - loss: 0.5720 437/1073 ━━━━━━━━━━━━━━━━━━━━ 25s 40ms/step - accuracy: 0.7650 - loss: 0.5720 439/1073 ━━━━━━━━━━━━━━━━━━━━ 25s 40ms/step - accuracy: 0.7650 - loss: 0.5720 441/1073 ━━━━━━━━━━━━━━━━━━━━ 25s 40ms/step - accuracy: 0.7650 - loss: 0.5720 443/1073 ━━━━━━━━━━━━━━━━━━━━ 25s 40ms/step - accuracy: 0.7650 - loss: 0.5720 445/1073 ━━━━━━━━━━━━━━━━━━━━ 25s 40ms/step - accuracy: 0.7650 - loss: 0.5720 447/1073 ━━━━━━━━━━━━━━━━━━━━ 24s 40ms/step - accuracy: 0.7650 - loss: 0.5720 449/1073 ━━━━━━━━━━━━━━━━━━━━ 24s 40ms/step - accuracy: 0.7650 - loss: 0.5720 451/1073 ━━━━━━━━━━━━━━━━━━━━ 24s 40ms/step - accuracy: 0.7650 - loss: 0.5720 453/1073 ━━━━━━━━━━━━━━━━━━━━ 24s 40ms/step - accuracy: 0.7650 - loss: 0.5720 455/1073 ━━━━━━━━━━━━━━━━━━━━ 24s 40ms/step - accuracy: 0.7650 - loss: 0.5720 457/1073 ━━━━━━━━━━━━━━━━━━━━ 24s 40ms/step - accuracy: 0.7650 - loss: 0.5720 459/1073 ━━━━━━━━━━━━━━━━━━━━ 24s 40ms/step - accuracy: 0.7650 - loss: 0.5721 461/1073 ━━━━━━━━━━━━━━━━━━━━ 24s 40ms/step - accuracy: 0.7650 - loss: 0.5721 463/1073 ━━━━━━━━━━━━━━━━━━━━ 24s 40ms/step - accuracy: 0.7649 - loss: 0.5721 465/1073 ━━━━━━━━━━━━━━━━━━━━ 24s 40ms/step - accuracy: 0.7649 - loss: 0.5721 467/1073 ━━━━━━━━━━━━━━━━━━━━ 24s 40ms/step - accuracy: 0.7649 - loss: 0.5721 469/1073 ━━━━━━━━━━━━━━━━━━━━ 24s 40ms/step - accuracy: 0.7649 - loss: 0.5721 471/1073 ━━━━━━━━━━━━━━━━━━━━ 23s 40ms/step - accuracy: 0.7649 - loss: 0.5721 473/1073 ━━━━━━━━━━━━━━━━━━━━ 23s 40ms/step - accuracy: 0.7649 - loss: 0.5721 475/1073 ━━━━━━━━━━━━━━━━━━━━ 23s 40ms/step - accuracy: 0.7649 - loss: 0.5721 477/1073 ━━━━━━━━━━━━━━━━━━━━ 23s 40ms/step - accuracy: 0.7649 - loss: 0.5721 479/1073 ━━━━━━━━━━━━━━━━━━━━ 23s 40ms/step - accuracy: 0.7649 - loss: 0.5721 481/1073 ━━━━━━━━━━━━━━━━━━━━ 23s 40ms/step - accuracy: 0.7649 - loss: 0.5721 483/1073 ━━━━━━━━━━━━━━━━━━━━ 23s 40ms/step - accuracy: 0.7649 - loss: 0.5721 485/1073 ━━━━━━━━━━━━━━━━━━━━ 23s 40ms/step - accuracy: 0.7649 - loss: 0.5721 487/1073 ━━━━━━━━━━━━━━━━━━━━ 23s 40ms/step - accuracy: 0.7649 - loss: 0.5722 489/1073 ━━━━━━━━━━━━━━━━━━━━ 23s 40ms/step - accuracy: 0.7649 - loss: 0.5722 491/1073 ━━━━━━━━━━━━━━━━━━━━ 23s 40ms/step - accuracy: 0.7649 - loss: 0.5722 493/1073 ━━━━━━━━━━━━━━━━━━━━ 23s 40ms/step - accuracy: 0.7649 - loss: 0.5722 495/1073 ━━━━━━━━━━━━━━━━━━━━ 23s 40ms/step - accuracy: 0.7649 - loss: 0.5722 497/1073 ━━━━━━━━━━━━━━━━━━━━ 22s 40ms/step - accuracy: 0.7649 - loss: 0.5722 499/1073 ━━━━━━━━━━━━━━━━━━━━ 22s 40ms/step - accuracy: 0.7649 - loss: 0.5722 501/1073 ━━━━━━━━━━━━━━━━━━━━ 22s 40ms/step - accuracy: 0.7649 - loss: 0.5722 503/1073 ━━━━━━━━━━━━━━━━━━━━ 22s 40ms/step - accuracy: 0.7649 - loss: 0.5722 505/1073 ━━━━━━━━━━━━━━━━━━━━ 22s 40ms/step - accuracy: 0.7649 - loss: 0.5722 507/1073 ━━━━━━━━━━━━━━━━━━━━ 22s 40ms/step - accuracy: 0.7649 - loss: 0.5722 509/1073 ━━━━━━━━━━━━━━━━━━━━ 22s 40ms/step - accuracy: 0.7649 - loss: 0.5722 511/1073 ━━━━━━━━━━━━━━━━━━━━ 22s 40ms/step - accuracy: 0.7649 - loss: 0.5722 513/1073 ━━━━━━━━━━━━━━━━━━━━ 22s 40ms/step - accuracy: 0.7649 - loss: 0.5722 515/1073 ━━━━━━━━━━━━━━━━━━━━ 22s 40ms/step - accuracy: 0.7649 - loss: 0.5722 517/1073 ━━━━━━━━━━━━━━━━━━━━ 22s 40ms/step - accuracy: 0.7649 - loss: 0.5723 519/1073 ━━━━━━━━━━━━━━━━━━━━ 22s 40ms/step - accuracy: 0.7649 - loss: 0.5723 521/1073 ━━━━━━━━━━━━━━━━━━━━ 21s 40ms/step - accuracy: 0.7649 - loss: 0.5723 523/1073 ━━━━━━━━━━━━━━━━━━━━ 21s 40ms/step - accuracy: 0.7649 - loss: 0.5723 525/1073 ━━━━━━━━━━━━━━━━━━━━ 21s 40ms/step - accuracy: 0.7649 - loss: 0.5723 527/1073 ━━━━━━━━━━━━━━━━━━━━ 21s 40ms/step - accuracy: 0.7649 - loss: 0.5723 529/1073 ━━━━━━━━━━━━━━━━━━━━ 21s 40ms/step - accuracy: 0.7649 - loss: 0.5723 531/1073 ━━━━━━━━━━━━━━━━━━━━ 21s 40ms/step - accuracy: 0.7649 - loss: 0.5723 533/1073 ━━━━━━━━━━━━━━━━━━━━ 21s 40ms/step - accuracy: 0.7649 - loss: 0.5723 535/1073 ━━━━━━━━━━━━━━━━━━━━ 21s 40ms/step - accuracy: 0.7649 - loss: 0.5723 537/1073 ━━━━━━━━━━━━━━━━━━━━ 21s 40ms/step - accuracy: 0.7649 - loss: 0.5723 539/1073 ━━━━━━━━━━━━━━━━━━━━ 21s 40ms/step - accuracy: 0.7649 - loss: 0.5723 541/1073 ━━━━━━━━━━━━━━━━━━━━ 21s 40ms/step - accuracy: 0.7649 - loss: 0.5723 543/1073 ━━━━━━━━━━━━━━━━━━━━ 21s 40ms/step - accuracy: 0.7649 - loss: 0.5723 545/1073 ━━━━━━━━━━━━━━━━━━━━ 21s 40ms/step - accuracy: 0.7649 - loss: 0.5723 547/1073 ━━━━━━━━━━━━━━━━━━━━ 20s 40ms/step - accuracy: 0.7649 - loss: 0.5724 549/1073 ━━━━━━━━━━━━━━━━━━━━ 20s 40ms/step - accuracy: 0.7649 - loss: 0.5724 551/1073 ━━━━━━━━━━━━━━━━━━━━ 20s 40ms/step - accuracy: 0.7649 - loss: 0.5724 553/1073 ━━━━━━━━━━━━━━━━━━━━ 20s 40ms/step - accuracy: 0.7649 - loss: 0.5724 555/1073 ━━━━━━━━━━━━━━━━━━━━ 20s 40ms/step - accuracy: 0.7649 - loss: 0.5724 557/1073 ━━━━━━━━━━━━━━━━━━━━ 20s 40ms/step - accuracy: 0.7649 - loss: 0.5724 559/1073 ━━━━━━━━━━━━━━━━━━━━ 20s 40ms/step - accuracy: 0.7649 - loss: 0.5724 561/1073 ━━━━━━━━━━━━━━━━━━━━ 20s 40ms/step - accuracy: 0.7649 - loss: 0.5724 563/1073 ━━━━━━━━━━━━━━━━━━━━ 20s 40ms/step - accuracy: 0.7649 - loss: 0.5724 565/1073 ━━━━━━━━━━━━━━━━━━━━ 20s 40ms/step - accuracy: 0.7649 - loss: 0.5724 567/1073 ━━━━━━━━━━━━━━━━━━━━ 20s 40ms/step - accuracy: 0.7649 - loss: 0.5724 569/1073 ━━━━━━━━━━━━━━━━━━━━ 20s 40ms/step - accuracy: 0.7648 - loss: 0.5724 571/1073 ━━━━━━━━━━━━━━━━━━━━ 20s 40ms/step - accuracy: 0.7648 - loss: 0.5724 573/1073 ━━━━━━━━━━━━━━━━━━━━ 19s 40ms/step - accuracy: 0.7648 - loss: 0.5724 575/1073 ━━━━━━━━━━━━━━━━━━━━ 19s 40ms/step - accuracy: 0.7648 - loss: 0.5724 577/1073 ━━━━━━━━━━━━━━━━━━━━ 19s 40ms/step - accuracy: 0.7648 - loss: 0.5725 579/1073 ━━━━━━━━━━━━━━━━━━━━ 19s 40ms/step - accuracy: 0.7648 - loss: 0.5725 581/1073 ━━━━━━━━━━━━━━━━━━━━ 19s 40ms/step - accuracy: 0.7648 - loss: 0.5725 583/1073 ━━━━━━━━━━━━━━━━━━━━ 19s 40ms/step - accuracy: 0.7648 - loss: 0.5725 585/1073 ━━━━━━━━━━━━━━━━━━━━ 19s 40ms/step - accuracy: 0.7648 - loss: 0.5725 587/1073 ━━━━━━━━━━━━━━━━━━━━ 19s 40ms/step - accuracy: 0.7648 - loss: 0.5725 589/1073 ━━━━━━━━━━━━━━━━━━━━ 19s 40ms/step - accuracy: 0.7648 - loss: 0.5725 591/1073 ━━━━━━━━━━━━━━━━━━━━ 19s 40ms/step - accuracy: 0.7648 - loss: 0.5725 593/1073 ━━━━━━━━━━━━━━━━━━━━ 19s 40ms/step - accuracy: 0.7648 - loss: 0.5725 595/1073 ━━━━━━━━━━━━━━━━━━━━ 19s 40ms/step - accuracy: 0.7648 - loss: 0.5725 597/1073 ━━━━━━━━━━━━━━━━━━━━ 18s 40ms/step - accuracy: 0.7648 - loss: 0.5725 599/1073 ━━━━━━━━━━━━━━━━━━━━ 18s 40ms/step - accuracy: 0.7648 - loss: 0.5725 601/1073 ━━━━━━━━━━━━━━━━━━━━ 18s 40ms/step - accuracy: 0.7648 - loss: 0.5725 603/1073 ━━━━━━━━━━━━━━━━━━━━ 18s 40ms/step - accuracy: 0.7648 - loss: 0.5725 605/1073 ━━━━━━━━━━━━━━━━━━━━ 18s 40ms/step - accuracy: 0.7648 - loss: 0.5725 607/1073 ━━━━━━━━━━━━━━━━━━━━ 18s 40ms/step - accuracy: 0.7648 - loss: 0.5725 609/1073 ━━━━━━━━━━━━━━━━━━━━ 18s 40ms/step - accuracy: 0.7648 - loss: 0.5725 611/1073 ━━━━━━━━━━━━━━━━━━━━ 18s 40ms/step - accuracy: 0.7648 - loss: 0.5725 613/1073 ━━━━━━━━━━━━━━━━━━━━ 18s 40ms/step - accuracy: 0.7648 - loss: 0.5725 615/1073 ━━━━━━━━━━━━━━━━━━━━ 18s 40ms/step - accuracy: 0.7648 - loss: 0.5726 617/1073 ━━━━━━━━━━━━━━━━━━━━ 18s 40ms/step - accuracy: 0.7648 - loss: 0.5726 619/1073 ━━━━━━━━━━━━━━━━━━━━ 18s 40ms/step - accuracy: 0.7648 - loss: 0.5726 621/1073 ━━━━━━━━━━━━━━━━━━━━ 18s 40ms/step - accuracy: 0.7648 - loss: 0.5726 623/1073 ━━━━━━━━━━━━━━━━━━━━ 17s 40ms/step - accuracy: 0.7648 - loss: 0.5726 625/1073 ━━━━━━━━━━━━━━━━━━━━ 17s 40ms/step - accuracy: 0.7648 - loss: 0.5726 627/1073 ━━━━━━━━━━━━━━━━━━━━ 17s 40ms/step - accuracy: 0.7648 - loss: 0.5726 629/1073 ━━━━━━━━━━━━━━━━━━━━ 17s 40ms/step - accuracy: 0.7648 - loss: 0.5726 631/1073 ━━━━━━━━━━━━━━━━━━━━ 17s 40ms/step - accuracy: 0.7648 - loss: 0.5726 633/1073 ━━━━━━━━━━━━━━━━━━━━ 17s 40ms/step - accuracy: 0.7648 - loss: 0.5726 635/1073 ━━━━━━━━━━━━━━━━━━━━ 17s 40ms/step - accuracy: 0.7648 - loss: 0.5726 637/1073 ━━━━━━━━━━━━━━━━━━━━ 17s 40ms/step - accuracy: 0.7648 - loss: 0.5726 639/1073 ━━━━━━━━━━━━━━━━━━━━ 17s 40ms/step - accuracy: 0.7648 - loss: 0.5726 641/1073 ━━━━━━━━━━━━━━━━━━━━ 17s 40ms/step - accuracy: 0.7648 - loss: 0.5726 643/1073 ━━━━━━━━━━━━━━━━━━━━ 17s 40ms/step - accuracy: 0.7648 - loss: 0.5726 645/1073 ━━━━━━━━━━━━━━━━━━━━ 17s 40ms/step - accuracy: 0.7648 - loss: 0.5726 647/1073 ━━━━━━━━━━━━━━━━━━━━ 17s 40ms/step - accuracy: 0.7648 - loss: 0.5726 649/1073 ━━━━━━━━━━━━━━━━━━━━ 16s 40ms/step - accuracy: 0.7648 - loss: 0.5726 651/1073 ━━━━━━━━━━━━━━━━━━━━ 16s 40ms/step - accuracy: 0.7648 - loss: 0.5726 653/1073 ━━━━━━━━━━━━━━━━━━━━ 16s 40ms/step - accuracy: 0.7648 - loss: 0.5726 655/1073 ━━━━━━━━━━━━━━━━━━━━ 16s 40ms/step - accuracy: 0.7648 - loss: 0.5726 657/1073 ━━━━━━━━━━━━━━━━━━━━ 16s 40ms/step - accuracy: 0.7648 - loss: 0.5726 659/1073 ━━━━━━━━━━━━━━━━━━━━ 16s 40ms/step - accuracy: 0.7648 - loss: 0.5726 661/1073 ━━━━━━━━━━━━━━━━━━━━ 16s 40ms/step - accuracy: 0.7648 - loss: 0.5727 663/1073 ━━━━━━━━━━━━━━━━━━━━ 16s 40ms/step - accuracy: 0.7648 - loss: 0.5727 665/1073 ━━━━━━━━━━━━━━━━━━━━ 16s 40ms/step - accuracy: 0.7648 - loss: 0.5727 667/1073 ━━━━━━━━━━━━━━━━━━━━ 16s 40ms/step - accuracy: 0.7648 - loss: 0.5727 669/1073 ━━━━━━━━━━━━━━━━━━━━ 16s 40ms/step - accuracy: 0.7648 - loss: 0.5727 671/1073 ━━━━━━━━━━━━━━━━━━━━ 16s 40ms/step - accuracy: 0.7648 - loss: 0.5727 673/1073 ━━━━━━━━━━━━━━━━━━━━ 15s 40ms/step - accuracy: 0.7648 - loss: 0.5727 675/1073 ━━━━━━━━━━━━━━━━━━━━ 15s 40ms/step - accuracy: 0.7648 - loss: 0.5727 677/1073 ━━━━━━━━━━━━━━━━━━━━ 15s 40ms/step - accuracy: 0.7648 - loss: 0.5727 679/1073 ━━━━━━━━━━━━━━━━━━━━ 15s 40ms/step - accuracy: 0.7648 - loss: 0.5727 681/1073 ━━━━━━━━━━━━━━━━━━━━ 15s 40ms/step - accuracy: 0.7648 - loss: 0.5727 683/1073 ━━━━━━━━━━━━━━━━━━━━ 15s 40ms/step - accuracy: 0.7648 - loss: 0.5727 685/1073 ━━━━━━━━━━━━━━━━━━━━ 15s 40ms/step - accuracy: 0.7648 - loss: 0.5727 687/1073 ━━━━━━━━━━━━━━━━━━━━ 15s 40ms/step - accuracy: 0.7648 - loss: 0.5727 689/1073 ━━━━━━━━━━━━━━━━━━━━ 15s 40ms/step - accuracy: 0.7648 - loss: 0.5727 691/1073 ━━━━━━━━━━━━━━━━━━━━ 15s 40ms/step - accuracy: 0.7648 - loss: 0.5727 693/1073 ━━━━━━━━━━━━━━━━━━━━ 15s 40ms/step - accuracy: 0.7648 - loss: 0.5727 695/1073 ━━━━━━━━━━━━━━━━━━━━ 15s 40ms/step - accuracy: 0.7648 - loss: 0.5727 697/1073 ━━━━━━━━━━━━━━━━━━━━ 15s 40ms/step - accuracy: 0.7648 - loss: 0.5727 699/1073 ━━━━━━━━━━━━━━━━━━━━ 14s 40ms/step - accuracy: 0.7648 - loss: 0.5727 701/1073 ━━━━━━━━━━━━━━━━━━━━ 14s 40ms/step - accuracy: 0.7648 - loss: 0.5727 703/1073 ━━━━━━━━━━━━━━━━━━━━ 14s 40ms/step - accuracy: 0.7648 - loss: 0.5727 705/1073 ━━━━━━━━━━━━━━━━━━━━ 14s 40ms/step - accuracy: 0.7648 - loss: 0.5727 707/1073 ━━━━━━━━━━━━━━━━━━━━ 14s 40ms/step - accuracy: 0.7648 - loss: 0.5727 709/1073 ━━━━━━━━━━━━━━━━━━━━ 14s 40ms/step - accuracy: 0.7648 - loss: 0.5727 711/1073 ━━━━━━━━━━━━━━━━━━━━ 14s 40ms/step - accuracy: 0.7648 - loss: 0.5727 713/1073 ━━━━━━━━━━━━━━━━━━━━ 14s 40ms/step - accuracy: 0.7648 - loss: 0.5727 715/1073 ━━━━━━━━━━━━━━━━━━━━ 14s 40ms/step - accuracy: 0.7648 - loss: 0.5727 717/1073 ━━━━━━━━━━━━━━━━━━━━ 14s 40ms/step - accuracy: 0.7648 - loss: 0.5727 719/1073 ━━━━━━━━━━━━━━━━━━━━ 14s 40ms/step - accuracy: 0.7648 - loss: 0.5727 721/1073 ━━━━━━━━━━━━━━━━━━━━ 14s 40ms/step - accuracy: 0.7648 - loss: 0.5727 723/1073 ━━━━━━━━━━━━━━━━━━━━ 13s 40ms/step - accuracy: 0.7648 - loss: 0.5727 725/1073 ━━━━━━━━━━━━━━━━━━━━ 13s 40ms/step - accuracy: 0.7648 - loss: 0.5727 727/1073 ━━━━━━━━━━━━━━━━━━━━ 13s 40ms/step - accuracy: 0.7648 - loss: 0.5727 729/1073 ━━━━━━━━━━━━━━━━━━━━ 13s 40ms/step - accuracy: 0.7648 - loss: 0.5727 731/1073 ━━━━━━━━━━━━━━━━━━━━ 13s 40ms/step - accuracy: 0.7648 - loss: 0.5727 733/1073 ━━━━━━━━━━━━━━━━━━━━ 13s 40ms/step - accuracy: 0.7648 - loss: 0.5727 735/1073 ━━━━━━━━━━━━━━━━━━━━ 13s 40ms/step - accuracy: 0.7648 - loss: 0.5727 737/1073 ━━━━━━━━━━━━━━━━━━━━ 13s 40ms/step - accuracy: 0.7648 - loss: 0.5727 739/1073 ━━━━━━━━━━━━━━━━━━━━ 13s 40ms/step - accuracy: 0.7648 - loss: 0.5727 741/1073 ━━━━━━━━━━━━━━━━━━━━ 13s 40ms/step - accuracy: 0.7648 - loss: 0.5727 743/1073 ━━━━━━━━━━━━━━━━━━━━ 13s 40ms/step - accuracy: 0.7648 - loss: 0.5727 745/1073 ━━━━━━━━━━━━━━━━━━━━ 13s 40ms/step - accuracy: 0.7648 - loss: 0.5727 747/1073 ━━━━━━━━━━━━━━━━━━━━ 13s 40ms/step - accuracy: 0.7648 - loss: 0.5727 749/1073 ━━━━━━━━━━━━━━━━━━━━ 12s 40ms/step - accuracy: 0.7648 - loss: 0.5728 751/1073 ━━━━━━━━━━━━━━━━━━━━ 12s 40ms/step - accuracy: 0.7648 - loss: 0.5728 753/1073 ━━━━━━━━━━━━━━━━━━━━ 12s 40ms/step - accuracy: 0.7648 - loss: 0.5728 755/1073 ━━━━━━━━━━━━━━━━━━━━ 12s 40ms/step - accuracy: 0.7648 - loss: 0.5728 757/1073 ━━━━━━━━━━━━━━━━━━━━ 12s 40ms/step - accuracy: 0.7648 - loss: 0.5728 759/1073 ━━━━━━━━━━━━━━━━━━━━ 12s 40ms/step - accuracy: 0.7648 - loss: 0.5728 761/1073 ━━━━━━━━━━━━━━━━━━━━ 12s 40ms/step - accuracy: 0.7649 - loss: 0.5728 763/1073 ━━━━━━━━━━━━━━━━━━━━ 12s 40ms/step - accuracy: 0.7649 - loss: 0.5728 765/1073 ━━━━━━━━━━━━━━━━━━━━ 12s 40ms/step - accuracy: 0.7649 - loss: 0.5728 767/1073 ━━━━━━━━━━━━━━━━━━━━ 12s 40ms/step - accuracy: 0.7649 - loss: 0.5728 769/1073 ━━━━━━━━━━━━━━━━━━━━ 12s 40ms/step - accuracy: 0.7649 - loss: 0.5728 771/1073 ━━━━━━━━━━━━━━━━━━━━ 12s 40ms/step - accuracy: 0.7649 - loss: 0.5728 773/1073 ━━━━━━━━━━━━━━━━━━━━ 11s 40ms/step - accuracy: 0.7649 - loss: 0.5728 775/1073 ━━━━━━━━━━━━━━━━━━━━ 11s 40ms/step - accuracy: 0.7649 - loss: 0.5728 777/1073 ━━━━━━━━━━━━━━━━━━━━ 11s 40ms/step - accuracy: 0.7649 - loss: 0.5728 779/1073 ━━━━━━━━━━━━━━━━━━━━ 11s 40ms/step - accuracy: 0.7649 - loss: 0.5728 781/1073 ━━━━━━━━━━━━━━━━━━━━ 11s 40ms/step - accuracy: 0.7649 - loss: 0.5728 783/1073 ━━━━━━━━━━━━━━━━━━━━ 11s 40ms/step - accuracy: 0.7649 - loss: 0.5728 785/1073 ━━━━━━━━━━━━━━━━━━━━ 11s 40ms/step - accuracy: 0.7649 - loss: 0.5728 787/1073 ━━━━━━━━━━━━━━━━━━━━ 11s 40ms/step - accuracy: 0.7649 - loss: 0.5728 789/1073 ━━━━━━━━━━━━━━━━━━━━ 11s 40ms/step - accuracy: 0.7649 - loss: 0.5728 791/1073 ━━━━━━━━━━━━━━━━━━━━ 11s 40ms/step - accuracy: 0.7649 - loss: 0.5728 793/1073 ━━━━━━━━━━━━━━━━━━━━ 11s 40ms/step - accuracy: 0.7649 - loss: 0.5728 795/1073 ━━━━━━━━━━━━━━━━━━━━ 11s 40ms/step - accuracy: 0.7649 - loss: 0.5728 797/1073 ━━━━━━━━━━━━━━━━━━━━ 11s 40ms/step - accuracy: 0.7649 - loss: 0.5728 799/1073 ━━━━━━━━━━━━━━━━━━━━ 10s 40ms/step - accuracy: 0.7649 - loss: 0.5728 801/1073 ━━━━━━━━━━━━━━━━━━━━ 10s 40ms/step - accuracy: 0.7649 - loss: 0.5728 803/1073 ━━━━━━━━━━━━━━━━━━━━ 10s 40ms/step - accuracy: 0.7649 - loss: 0.5728 805/1073 ━━━━━━━━━━━━━━━━━━━━ 10s 40ms/step - accuracy: 0.7649 - loss: 0.5728 807/1073 ━━━━━━━━━━━━━━━━━━━━ 10s 40ms/step - accuracy: 0.7649 - loss: 0.5728 809/1073 ━━━━━━━━━━━━━━━━━━━━ 10s 40ms/step - accuracy: 0.7649 - loss: 0.5728 811/1073 ━━━━━━━━━━━━━━━━━━━━ 10s 40ms/step - accuracy: 0.7649 - loss: 0.5728 813/1073 ━━━━━━━━━━━━━━━━━━━━ 10s 40ms/step - accuracy: 0.7649 - loss: 0.5728 815/1073 ━━━━━━━━━━━━━━━━━━━━ 10s 40ms/step - accuracy: 0.7649 - loss: 0.5728 817/1073 ━━━━━━━━━━━━━━━━━━━━ 10s 40ms/step - accuracy: 0.7649 - loss: 0.5728 819/1073 ━━━━━━━━━━━━━━━━━━━━ 10s 40ms/step - accuracy: 0.7649 - loss: 0.5728 821/1073 ━━━━━━━━━━━━━━━━━━━━ 10s 40ms/step - accuracy: 0.7649 - loss: 0.5728 823/1073 ━━━━━━━━━━━━━━━━━━━━ 9s 40ms/step - accuracy: 0.7649 - loss: 0.5728 825/1073 ━━━━━━━━━━━━━━━━━━━━ 9s 40ms/step - accuracy: 0.7649 - loss: 0.5728 827/1073 ━━━━━━━━━━━━━━━━━━━━ 9s 40ms/step - accuracy: 0.7649 - loss: 0.5728 829/1073 ━━━━━━━━━━━━━━━━━━━━ 9s 40ms/step - accuracy: 0.7649 - loss: 0.5728 831/1073 ━━━━━━━━━━━━━━━━━━━━ 9s 40ms/step - accuracy: 0.7649 - loss: 0.5728 833/1073 ━━━━━━━━━━━━━━━━━━━━ 9s 40ms/step - accuracy: 0.7649 - loss: 0.5728 835/1073 ━━━━━━━━━━━━━━━━━━━━ 9s 40ms/step - accuracy: 0.7649 - loss: 0.5728 837/1073 ━━━━━━━━━━━━━━━━━━━━ 9s 40ms/step - accuracy: 0.7649 - loss: 0.5728 839/1073 ━━━━━━━━━━━━━━━━━━━━ 9s 40ms/step - accuracy: 0.7649 - loss: 0.5728 841/1073 ━━━━━━━━━━━━━━━━━━━━ 9s 40ms/step - accuracy: 0.7649 - loss: 0.5728 843/1073 ━━━━━━━━━━━━━━━━━━━━ 9s 40ms/step - accuracy: 0.7649 - loss: 0.5728 845/1073 ━━━━━━━━━━━━━━━━━━━━ 9s 40ms/step - accuracy: 0.7649 - loss: 0.5728 847/1073 ━━━━━━━━━━━━━━━━━━━━ 9s 40ms/step - accuracy: 0.7649 - loss: 0.5728 849/1073 ━━━━━━━━━━━━━━━━━━━━ 8s 40ms/step - accuracy: 0.7649 - loss: 0.5728 851/1073 ━━━━━━━━━━━━━━━━━━━━ 8s 40ms/step - accuracy: 0.7649 - loss: 0.5728 853/1073 ━━━━━━━━━━━━━━━━━━━━ 8s 40ms/step - accuracy: 0.7649 - loss: 0.5728 855/1073 ━━━━━━━━━━━━━━━━━━━━ 8s 40ms/step - accuracy: 0.7649 - loss: 0.5728 857/1073 ━━━━━━━━━━━━━━━━━━━━ 8s 40ms/step - accuracy: 0.7649 - loss: 0.5728 859/1073 ━━━━━━━━━━━━━━━━━━━━ 8s 40ms/step - accuracy: 0.7649 - loss: 0.5728 861/1073 ━━━━━━━━━━━━━━━━━━━━ 8s 40ms/step - accuracy: 0.7649 - loss: 0.5728 863/1073 ━━━━━━━━━━━━━━━━━━━━ 8s 40ms/step - accuracy: 0.7649 - loss: 0.5728 865/1073 ━━━━━━━━━━━━━━━━━━━━ 8s 40ms/step - accuracy: 0.7649 - loss: 0.5728 867/1073 ━━━━━━━━━━━━━━━━━━━━ 8s 40ms/step - accuracy: 0.7649 - loss: 0.5728 869/1073 ━━━━━━━━━━━━━━━━━━━━ 8s 40ms/step - accuracy: 0.7649 - loss: 0.5728 871/1073 ━━━━━━━━━━━━━━━━━━━━ 8s 40ms/step - accuracy: 0.7649 - loss: 0.5728 873/1073 ━━━━━━━━━━━━━━━━━━━━ 8s 40ms/step - accuracy: 0.7649 - loss: 0.5728 875/1073 ━━━━━━━━━━━━━━━━━━━━ 7s 40ms/step - accuracy: 0.7649 - loss: 0.5728 877/1073 ━━━━━━━━━━━━━━━━━━━━ 7s 40ms/step - accuracy: 0.7649 - loss: 0.5728 879/1073 ━━━━━━━━━━━━━━━━━━━━ 7s 40ms/step - accuracy: 0.7649 - loss: 0.5728 881/1073 ━━━━━━━━━━━━━━━━━━━━ 7s 40ms/step - accuracy: 0.7649 - loss: 0.5728 883/1073 ━━━━━━━━━━━━━━━━━━━━ 7s 40ms/step - accuracy: 0.7649 - loss: 0.5728 885/1073 ━━━━━━━━━━━━━━━━━━━━ 7s 40ms/step - accuracy: 0.7649 - loss: 0.5728 887/1073 ━━━━━━━━━━━━━━━━━━━━ 7s 40ms/step - accuracy: 0.7649 - loss: 0.5728 889/1073 ━━━━━━━━━━━━━━━━━━━━ 7s 40ms/step - accuracy: 0.7649 - loss: 0.5728 891/1073 ━━━━━━━━━━━━━━━━━━━━ 7s 40ms/step - accuracy: 0.7649 - loss: 0.5728 893/1073 ━━━━━━━━━━━━━━━━━━━━ 7s 40ms/step - accuracy: 0.7649 - loss: 0.5728 895/1073 ━━━━━━━━━━━━━━━━━━━━ 7s 40ms/step - accuracy: 0.7649 - loss: 0.5728 897/1073 ━━━━━━━━━━━━━━━━━━━━ 7s 40ms/step - accuracy: 0.7649 - loss: 0.5728 899/1073 ━━━━━━━━━━━━━━━━━━━━ 6s 40ms/step - accuracy: 0.7649 - loss: 0.5728 901/1073 ━━━━━━━━━━━━━━━━━━━━ 6s 40ms/step - accuracy: 0.7649 - loss: 0.5728 903/1073 ━━━━━━━━━━━━━━━━━━━━ 6s 40ms/step - accuracy: 0.7649 - loss: 0.5728 905/1073 ━━━━━━━━━━━━━━━━━━━━ 6s 40ms/step - accuracy: 0.7649 - loss: 0.5728 907/1073 ━━━━━━━━━━━━━━━━━━━━ 6s 40ms/step - accuracy: 0.7649 - loss: 0.5728 909/1073 ━━━━━━━━━━━━━━━━━━━━ 6s 40ms/step - accuracy: 0.7649 - loss: 0.5728 911/1073 ━━━━━━━━━━━━━━━━━━━━ 6s 40ms/step - accuracy: 0.7649 - loss: 0.5728 913/1073 ━━━━━━━━━━━━━━━━━━━━ 6s 40ms/step - accuracy: 0.7649 - loss: 0.5728 915/1073 ━━━━━━━━━━━━━━━━━━━━ 6s 40ms/step - accuracy: 0.7649 - loss: 0.5728 917/1073 ━━━━━━━━━━━━━━━━━━━━ 6s 40ms/step - accuracy: 0.7649 - loss: 0.5728 919/1073 ━━━━━━━━━━━━━━━━━━━━ 6s 40ms/step - accuracy: 0.7649 - loss: 0.5728 921/1073 ━━━━━━━━━━━━━━━━━━━━ 6s 40ms/step - accuracy: 0.7649 - loss: 0.5728 923/1073 ━━━━━━━━━━━━━━━━━━━━ 6s 40ms/step - accuracy: 0.7649 - loss: 0.5728 925/1073 ━━━━━━━━━━━━━━━━━━━━ 5s 40ms/step - accuracy: 0.7649 - loss: 0.5728 927/1073 ━━━━━━━━━━━━━━━━━━━━ 5s 40ms/step - accuracy: 0.7649 - loss: 0.5728 929/1073 ━━━━━━━━━━━━━━━━━━━━ 5s 40ms/step - accuracy: 0.7649 - loss: 0.5728 931/1073 ━━━━━━━━━━━━━━━━━━━━ 5s 40ms/step - accuracy: 0.7649 - loss: 0.5728 933/1073 ━━━━━━━━━━━━━━━━━━━━ 5s 40ms/step - accuracy: 0.7649 - loss: 0.5728 935/1073 ━━━━━━━━━━━━━━━━━━━━ 5s 40ms/step - accuracy: 0.7649 - loss: 0.5728 937/1073 ━━━━━━━━━━━━━━━━━━━━ 5s 40ms/step - accuracy: 0.7649 - loss: 0.5728 939/1073 ━━━━━━━━━━━━━━━━━━━━ 5s 40ms/step - accuracy: 0.7649 - loss: 0.5728 941/1073 ━━━━━━━━━━━━━━━━━━━━ 5s 40ms/step - accuracy: 0.7649 - loss: 0.5728 943/1073 ━━━━━━━━━━━━━━━━━━━━ 5s 40ms/step - accuracy: 0.7649 - loss: 0.5728 945/1073 ━━━━━━━━━━━━━━━━━━━━ 5s 40ms/step - accuracy: 0.7649 - loss: 0.5728 947/1073 ━━━━━━━━━━━━━━━━━━━━ 5s 40ms/step - accuracy: 0.7649 - loss: 0.5728 949/1073 ━━━━━━━━━━━━━━━━━━━━ 4s 40ms/step - accuracy: 0.7649 - loss: 0.5728 951/1073 ━━━━━━━━━━━━━━━━━━━━ 4s 40ms/step - accuracy: 0.7649 - loss: 0.5728 953/1073 ━━━━━━━━━━━━━━━━━━━━ 4s 40ms/step - accuracy: 0.7649 - loss: 0.5728 955/1073 ━━━━━━━━━━━━━━━━━━━━ 4s 40ms/step - accuracy: 0.7649 - loss: 0.5728 957/1073 ━━━━━━━━━━━━━━━━━━━━ 4s 40ms/step - accuracy: 0.7649 - loss: 0.5728 959/1073 ━━━━━━━━━━━━━━━━━━━━ 4s 40ms/step - accuracy: 0.7650 - loss: 0.5728 961/1073 ━━━━━━━━━━━━━━━━━━━━ 4s 40ms/step - accuracy: 0.7650 - loss: 0.5728 963/1073 ━━━━━━━━━━━━━━━━━━━━ 4s 40ms/step - accuracy: 0.7650 - loss: 0.5728 965/1073 ━━━━━━━━━━━━━━━━━━━━ 4s 40ms/step - accuracy: 0.7650 - loss: 0.5728 967/1073 ━━━━━━━━━━━━━━━━━━━━ 4s 40ms/step - accuracy: 0.7650 - loss: 0.5728 969/1073 ━━━━━━━━━━━━━━━━━━━━ 4s 40ms/step - accuracy: 0.7650 - loss: 0.5728 971/1073 ━━━━━━━━━━━━━━━━━━━━ 4s 40ms/step - accuracy: 0.7650 - loss: 0.5728 973/1073 ━━━━━━━━━━━━━━━━━━━━ 4s 40ms/step - accuracy: 0.7650 - loss: 0.5728 975/1073 ━━━━━━━━━━━━━━━━━━━━ 3s 40ms/step - accuracy: 0.7650 - loss: 0.5728 977/1073 ━━━━━━━━━━━━━━━━━━━━ 3s 40ms/step - accuracy: 0.7650 - loss: 0.5728 979/1073 ━━━━━━━━━━━━━━━━━━━━ 3s 40ms/step - accuracy: 0.7650 - loss: 0.5728 981/1073 ━━━━━━━━━━━━━━━━━━━━ 3s 40ms/step - accuracy: 0.7650 - loss: 0.5728 983/1073 ━━━━━━━━━━━━━━━━━━━━ 3s 40ms/step - accuracy: 0.7650 - loss: 0.5728 985/1073 ━━━━━━━━━━━━━━━━━━━━ 3s 40ms/step - accuracy: 0.7650 - loss: 0.5728 987/1073 ━━━━━━━━━━━━━━━━━━━━ 3s 40ms/step - accuracy: 0.7650 - loss: 0.5728 989/1073 ━━━━━━━━━━━━━━━━━━━━ 3s 40ms/step - accuracy: 0.7650 - loss: 0.5728 991/1073 ━━━━━━━━━━━━━━━━━━━━ 3s 40ms/step - accuracy: 0.7650 - loss: 0.5728 993/1073 ━━━━━━━━━━━━━━━━━━━━ 3s 40ms/step - accuracy: 0.7650 - loss: 0.5728 995/1073 ━━━━━━━━━━━━━━━━━━━━ 3s 40ms/step - accuracy: 0.7650 - loss: 0.5728 997/1073 ━━━━━━━━━━━━━━━━━━━━ 3s 40ms/step - accuracy: 0.7650 - loss: 0.5728 999/1073 ━━━━━━━━━━━━━━━━━━━━ 2s 40ms/step - accuracy: 0.7650 - loss: 0.57281001/1073 ━━━━━━━━━━━━━━━━━━━━ 2s 40ms/step - accuracy: 0.7650 - loss: 0.57281003/1073 ━━━━━━━━━━━━━━━━━━━━ 2s 40ms/step - accuracy: 0.7650 - loss: 0.57281005/1073 ━━━━━━━━━━━━━━━━━━━━ 2s 40ms/step - accuracy: 0.7650 - loss: 0.57281007/1073 ━━━━━━━━━━━━━━━━━━━━ 2s 40ms/step - accuracy: 0.7650 - loss: 0.57281009/1073 ━━━━━━━━━━━━━━━━━━━━ 2s 40ms/step - accuracy: 0.7650 - loss: 0.57281011/1073 ━━━━━━━━━━━━━━━━━━━━ 2s 40ms/step - accuracy: 0.7650 - loss: 0.57281013/1073 ━━━━━━━━━━━━━━━━━━━━ 2s 40ms/step - accuracy: 0.7650 - loss: 0.57281015/1073 ━━━━━━━━━━━━━━━━━━━━ 2s 40ms/step - accuracy: 0.7650 - loss: 0.57281017/1073 ━━━━━━━━━━━━━━━━━━━━ 2s 40ms/step - accuracy: 0.7650 - loss: 0.57281019/1073 ━━━━━━━━━━━━━━━━━━━━ 2s 40ms/step - accuracy: 0.7650 - loss: 0.57281021/1073 ━━━━━━━━━━━━━━━━━━━━ 2s 40ms/step - accuracy: 0.7650 - loss: 0.57281023/1073 ━━━━━━━━━━━━━━━━━━━━ 2s 40ms/step - accuracy: 0.7650 - loss: 0.57281025/1073 ━━━━━━━━━━━━━━━━━━━━ 1s 40ms/step - accuracy: 0.7650 - loss: 0.57281027/1073 ━━━━━━━━━━━━━━━━━━━━ 1s 40ms/step - accuracy: 0.7650 - loss: 0.57281029/1073 ━━━━━━━━━━━━━━━━━━━━ 1s 40ms/step - accuracy: 0.7650 - loss: 0.57281031/1073 ━━━━━━━━━━━━━━━━━━━━ 1s 40ms/step - accuracy: 0.7650 - loss: 0.57281033/1073 ━━━━━━━━━━━━━━━━━━━━ 1s 40ms/step - accuracy: 0.7650 - loss: 0.57281035/1073 ━━━━━━━━━━━━━━━━━━━━ 1s 40ms/step - accuracy: 0.7650 - loss: 0.57281037/1073 ━━━━━━━━━━━━━━━━━━━━ 1s 40ms/step - accuracy: 0.7650 - loss: 0.57281039/1073 ━━━━━━━━━━━━━━━━━━━━ 1s 40ms/step - accuracy: 0.7650 - loss: 0.57281041/1073 ━━━━━━━━━━━━━━━━━━━━ 1s 40ms/step - accuracy: 0.7650 - loss: 0.57281043/1073 ━━━━━━━━━━━━━━━━━━━━ 1s 40ms/step - accuracy: 0.7650 - loss: 0.57281045/1073 ━━━━━━━━━━━━━━━━━━━━ 1s 40ms/step - accuracy: 0.7650 - loss: 0.57281047/1073 ━━━━━━━━━━━━━━━━━━━━ 1s 40ms/step - accuracy: 0.7650 - loss: 0.57281049/1073 ━━━━━━━━━━━━━━━━━━━━ 0s 40ms/step - accuracy: 0.7650 - loss: 0.57281051/1073 ━━━━━━━━━━━━━━━━━━━━ 0s 40ms/step - accuracy: 0.7650 - loss: 0.57281053/1073 ━━━━━━━━━━━━━━━━━━━━ 0s 40ms/step - accuracy: 0.7650 - loss: 0.57281055/1073 ━━━━━━━━━━━━━━━━━━━━ 0s 40ms/step - accuracy: 0.7650 - loss: 0.57281057/1073 ━━━━━━━━━━━━━━━━━━━━ 0s 40ms/step - accuracy: 0.7650 - loss: 0.57281059/1073 ━━━━━━━━━━━━━━━━━━━━ 0s 40ms/step - accuracy: 0.7650 - loss: 0.57281061/1073 ━━━━━━━━━━━━━━━━━━━━ 0s 40ms/step - accuracy: 0.7650 - loss: 0.57281063/1073 ━━━━━━━━━━━━━━━━━━━━ 0s 40ms/step - accuracy: 0.7650 - loss: 0.57271065/1073 ━━━━━━━━━━━━━━━━━━━━ 0s 40ms/step - accuracy: 0.7650 - loss: 0.57271067/1073 ━━━━━━━━━━━━━━━━━━━━ 0s 40ms/step - accuracy: 0.7650 - loss: 0.57271069/1073 ━━━━━━━━━━━━━━━━━━━━ 0s 40ms/step - accuracy: 0.7650 - loss: 0.57271071/1073 ━━━━━━━━━━━━━━━━━━━━ 0s 40ms/step - accuracy: 0.7650 - loss: 0.57271073/1073 ━━━━━━━━━━━━━━━━━━━━ 0s 40ms/step - accuracy: 0.7650 - loss: 0.57271073/1073 ━━━━━━━━━━━━━━━━━━━━ 44s 40ms/step - accuracy: 0.7657 - loss: 0.5721 - val_accuracy: 0.7704 - val_loss: 0.5641Epoch 4/5 1/1073 ━━━━━━━━━━━━━━━━━━━━ 18:39 1s/step - accuracy: 0.7852 - loss: 0.5116 3/1073 ━━━━━━━━━━━━━━━━━━━━ 45s 42ms/step - accuracy: 0.7925 - loss: 0.5004 5/1073 ━━━━━━━━━━━━━━━━━━━━ 44s 41ms/step - accuracy: 0.7956 - loss: 0.4984 7/1073 ━━━━━━━━━━━━━━━━━━━━ 43s 41ms/step - accuracy: 0.7954 - loss: 0.4990 9/1073 ━━━━━━━━━━━━━━━━━━━━ 43s 41ms/step - accuracy: 0.7956 - loss: 0.4993 11/1073 ━━━━━━━━━━━━━━━━━━━━ 42s 40ms/step - accuracy: 0.7964 - loss: 0.4991 13/1073 ━━━━━━━━━━━━━━━━━━━━ 42s 40ms/step - accuracy: 0.7969 - loss: 0.4989 15/1073 ━━━━━━━━━━━━━━━━━━━━ 42s 40ms/step - accuracy: 0.7972 - loss: 0.4987 17/1073 ━━━━━━━━━━━━━━━━━━━━ 42s 40ms/step - accuracy: 0.7976 - loss: 0.4983 19/1073 ━━━━━━━━━━━━━━━━━━━━ 42s 40ms/step - accuracy: 0.7981 - loss: 0.4980 21/1073 ━━━━━━━━━━━━━━━━━━━━ 42s 40ms/step - accuracy: 0.7986 - loss: 0.4975 23/1073 ━━━━━━━━━━━━━━━━━━━━ 42s 40ms/step - accuracy: 0.7989 - loss: 0.4972 25/1073 ━━━━━━━━━━━━━━━━━━━━ 42s 40ms/step - accuracy: 0.7991 - loss: 0.4972 27/1073 ━━━━━━━━━━━━━━━━━━━━ 42s 40ms/step - accuracy: 0.7992 - loss: 0.4974 29/1073 ━━━━━━━━━━━━━━━━━━━━ 42s 40ms/step - accuracy: 0.7993 - loss: 0.4975 31/1073 ━━━━━━━━━━━━━━━━━━━━ 42s 40ms/step - accuracy: 0.7992 - loss: 0.4979 33/1073 ━━━━━━━━━━━━━━━━━━━━ 41s 40ms/step - accuracy: 0.7990 - loss: 0.4985 35/1073 ━━━━━━━━━━━━━━━━━━━━ 41s 40ms/step - accuracy: 0.7988 - loss: 0.4991 37/1073 ━━━━━━━━━━━━━━━━━━━━ 41s 40ms/step - accuracy: 0.7986 - loss: 0.4997 39/1073 ━━━━━━━━━━━━━━━━━━━━ 41s 40ms/step - accuracy: 0.7985 - loss: 0.5003 41/1073 ━━━━━━━━━━━━━━━━━━━━ 41s 40ms/step - accuracy: 0.7983 - loss: 0.5007 43/1073 ━━━━━━━━━━━━━━━━━━━━ 41s 40ms/step - accuracy: 0.7982 - loss: 0.5012 45/1073 ━━━━━━━━━━━━━━━━━━━━ 41s 40ms/step - accuracy: 0.7980 - loss: 0.5016 47/1073 ━━━━━━━━━━━━━━━━━━━━ 41s 40ms/step - accuracy: 0.7979 - loss: 0.5021 49/1073 ━━━━━━━━━━━━━━━━━━━━ 41s 40ms/step - accuracy: 0.7978 - loss: 0.5025 51/1073 ━━━━━━━━━━━━━━━━━━━━ 41s 40ms/step - accuracy: 0.7977 - loss: 0.5029 53/1073 ━━━━━━━━━━━━━━━━━━━━ 41s 40ms/step - accuracy: 0.7976 - loss: 0.5033 55/1073 ━━━━━━━━━━━━━━━━━━━━ 41s 40ms/step - accuracy: 0.7974 - loss: 0.5037 57/1073 ━━━━━━━━━━━━━━━━━━━━ 40s 40ms/step - accuracy: 0.7973 - loss: 0.5041 59/1073 ━━━━━━━━━━━━━━━━━━━━ 40s 40ms/step - accuracy: 0.7972 - loss: 0.5045 61/1073 ━━━━━━━━━━━━━━━━━━━━ 40s 40ms/step - accuracy: 0.7971 - loss: 0.5048 63/1073 ━━━━━━━━━━━━━━━━━━━━ 40s 40ms/step - accuracy: 0.7971 - loss: 0.5052 65/1073 ━━━━━━━━━━━━━━━━━━━━ 40s 40ms/step - accuracy: 0.7970 - loss: 0.5055 67/1073 ━━━━━━━━━━━━━━━━━━━━ 40s 40ms/step - accuracy: 0.7969 - loss: 0.5058 69/1073 ━━━━━━━━━━━━━━━━━━━━ 40s 40ms/step - accuracy: 0.7968 - loss: 0.5061 71/1073 ━━━━━━━━━━━━━━━━━━━━ 40s 40ms/step - accuracy: 0.7967 - loss: 0.5065 73/1073 ━━━━━━━━━━━━━━━━━━━━ 40s 40ms/step - accuracy: 0.7966 - loss: 0.5068 75/1073 ━━━━━━━━━━━━━━━━━━━━ 40s 40ms/step - accuracy: 0.7965 - loss: 0.5070 77/1073 ━━━━━━━━━━━━━━━━━━━━ 40s 40ms/step - accuracy: 0.7964 - loss: 0.5073 79/1073 ━━━━━━━━━━━━━━━━━━━━ 39s 40ms/step - accuracy: 0.7963 - loss: 0.5076 81/1073 ━━━━━━━━━━━━━━━━━━━━ 39s 40ms/step - accuracy: 0.7962 - loss: 0.5079 83/1073 ━━━━━━━━━━━━━━━━━━━━ 39s 40ms/step - accuracy: 0.7961 - loss: 0.5082 85/1073 ━━━━━━━━━━━━━━━━━━━━ 39s 40ms/step - accuracy: 0.7960 - loss: 0.5084 87/1073 ━━━━━━━━━━━━━━━━━━━━ 39s 40ms/step - accuracy: 0.7959 - loss: 0.5086 89/1073 ━━━━━━━━━━━━━━━━━━━━ 39s 40ms/step - accuracy: 0.7958 - loss: 0.5088 91/1073 ━━━━━━━━━━━━━━━━━━━━ 39s 40ms/step - accuracy: 0.7957 - loss: 0.5090 93/1073 ━━━━━━━━━━━━━━━━━━━━ 39s 40ms/step - accuracy: 0.7957 - loss: 0.5092 95/1073 ━━━━━━━━━━━━━━━━━━━━ 39s 40ms/step - accuracy: 0.7956 - loss: 0.5094 97/1073 ━━━━━━━━━━━━━━━━━━━━ 39s 40ms/step - accuracy: 0.7955 - loss: 0.5095 99/1073 ━━━━━━━━━━━━━━━━━━━━ 39s 40ms/step - accuracy: 0.7955 - loss: 0.5097 101/1073 ━━━━━━━━━━━━━━━━━━━━ 38s 40ms/step - accuracy: 0.7954 - loss: 0.5099 103/1073 ━━━━━━━━━━━━━━━━━━━━ 38s 40ms/step - accuracy: 0.7953 - loss: 0.5100 105/1073 ━━━━━━━━━━━━━━━━━━━━ 38s 40ms/step - accuracy: 0.7953 - loss: 0.5102 107/1073 ━━━━━━━━━━━━━━━━━━━━ 38s 40ms/step - accuracy: 0.7952 - loss: 0.5103 109/1073 ━━━━━━━━━━━━━━━━━━━━ 38s 40ms/step - accuracy: 0.7951 - loss: 0.5105 111/1073 ━━━━━━━━━━━━━━━━━━━━ 38s 40ms/step - accuracy: 0.7950 - loss: 0.5106 113/1073 ━━━━━━━━━━━━━━━━━━━━ 38s 40ms/step - accuracy: 0.7950 - loss: 0.5108 115/1073 ━━━━━━━━━━━━━━━━━━━━ 38s 40ms/step - accuracy: 0.7949 - loss: 0.5109 117/1073 ━━━━━━━━━━━━━━━━━━━━ 38s 40ms/step - accuracy: 0.7949 - loss: 0.5110 119/1073 ━━━━━━━━━━━━━━━━━━━━ 38s 40ms/step - accuracy: 0.7948 - loss: 0.5112 121/1073 ━━━━━━━━━━━━━━━━━━━━ 38s 40ms/step - accuracy: 0.7948 - loss: 0.5113 123/1073 ━━━━━━━━━━━━━━━━━━━━ 38s 40ms/step - accuracy: 0.7947 - loss: 0.5114 125/1073 ━━━━━━━━━━━━━━━━━━━━ 38s 40ms/step - accuracy: 0.7947 - loss: 0.5115 127/1073 ━━━━━━━━━━━━━━━━━━━━ 37s 40ms/step - accuracy: 0.7946 - loss: 0.5116 129/1073 ━━━━━━━━━━━━━━━━━━━━ 37s 40ms/step - accuracy: 0.7946 - loss: 0.5116 131/1073 ━━━━━━━━━━━━━━━━━━━━ 37s 40ms/step - accuracy: 0.7946 - loss: 0.5117 133/1073 ━━━━━━━━━━━━━━━━━━━━ 37s 40ms/step - accuracy: 0.7946 - loss: 0.5118 135/1073 ━━━━━━━━━━━━━━━━━━━━ 37s 40ms/step - accuracy: 0.7945 - loss: 0.5119 137/1073 ━━━━━━━━━━━━━━━━━━━━ 37s 40ms/step - accuracy: 0.7945 - loss: 0.5119 139/1073 ━━━━━━━━━━━━━━━━━━━━ 37s 40ms/step - accuracy: 0.7945 - loss: 0.5120 141/1073 ━━━━━━━━━━━━━━━━━━━━ 37s 40ms/step - accuracy: 0.7945 - loss: 0.5121 143/1073 ━━━━━━━━━━━━━━━━━━━━ 37s 40ms/step - accuracy: 0.7944 - loss: 0.5122 145/1073 ━━━━━━━━━━━━━━━━━━━━ 37s 40ms/step - accuracy: 0.7944 - loss: 0.5122 147/1073 ━━━━━━━━━━━━━━━━━━━━ 37s 40ms/step - accuracy: 0.7944 - loss: 0.5123 149/1073 ━━━━━━━━━━━━━━━━━━━━ 37s 40ms/step - accuracy: 0.7944 - loss: 0.5124 151/1073 ━━━━━━━━━━━━━━━━━━━━ 37s 40ms/step - accuracy: 0.7943 - loss: 0.5124 153/1073 ━━━━━━━━━━━━━━━━━━━━ 36s 40ms/step - accuracy: 0.7943 - loss: 0.5125 155/1073 ━━━━━━━━━━━━━━━━━━━━ 36s 40ms/step - accuracy: 0.7943 - loss: 0.5126 157/1073 ━━━━━━━━━━━━━━━━━━━━ 36s 40ms/step - accuracy: 0.7943 - loss: 0.5126 159/1073 ━━━━━━━━━━━━━━━━━━━━ 36s 40ms/step - accuracy: 0.7942 - loss: 0.5127 161/1073 ━━━━━━━━━━━━━━━━━━━━ 36s 40ms/step - accuracy: 0.7942 - loss: 0.5127 163/1073 ━━━━━━━━━━━━━━━━━━━━ 36s 40ms/step - accuracy: 0.7942 - loss: 0.5128 165/1073 ━━━━━━━━━━━━━━━━━━━━ 36s 40ms/step - accuracy: 0.7942 - loss: 0.5128 167/1073 ━━━━━━━━━━━━━━━━━━━━ 36s 40ms/step - accuracy: 0.7941 - loss: 0.5129 169/1073 ━━━━━━━━━━━━━━━━━━━━ 36s 40ms/step - accuracy: 0.7941 - loss: 0.5129 171/1073 ━━━━━━━━━━━━━━━━━━━━ 36s 40ms/step - accuracy: 0.7941 - loss: 0.5130 173/1073 ━━━━━━━━━━━━━━━━━━━━ 36s 40ms/step - accuracy: 0.7941 - loss: 0.5130 175/1073 ━━━━━━━━━━━━━━━━━━━━ 36s 40ms/step - accuracy: 0.7941 - loss: 0.5131 177/1073 ━━━━━━━━━━━━━━━━━━━━ 35s 40ms/step - accuracy: 0.7941 - loss: 0.5131 179/1073 ━━━━━━━━━━━━━━━━━━━━ 35s 40ms/step - accuracy: 0.7940 - loss: 0.5132 181/1073 ━━━━━━━━━━━━━━━━━━━━ 35s 40ms/step - accuracy: 0.7940 - loss: 0.5132 183/1073 ━━━━━━━━━━━━━━━━━━━━ 35s 40ms/step - accuracy: 0.7940 - loss: 0.5132 185/1073 ━━━━━━━━━━━━━━━━━━━━ 35s 40ms/step - accuracy: 0.7940 - loss: 0.5133 187/1073 ━━━━━━━━━━━━━━━━━━━━ 35s 40ms/step - accuracy: 0.7940 - loss: 0.5133 189/1073 ━━━━━━━━━━━━━━━━━━━━ 35s 40ms/step - accuracy: 0.7940 - loss: 0.5134 191/1073 ━━━━━━━━━━━━━━━━━━━━ 35s 40ms/step - accuracy: 0.7939 - loss: 0.5134 193/1073 ━━━━━━━━━━━━━━━━━━━━ 35s 40ms/step - accuracy: 0.7939 - loss: 0.5134 195/1073 ━━━━━━━━━━━━━━━━━━━━ 35s 40ms/step - accuracy: 0.7939 - loss: 0.5135 197/1073 ━━━━━━━━━━━━━━━━━━━━ 35s 40ms/step - accuracy: 0.7939 - loss: 0.5135 199/1073 ━━━━━━━━━━━━━━━━━━━━ 35s 40ms/step - accuracy: 0.7939 - loss: 0.5135 201/1073 ━━━━━━━━━━━━━━━━━━━━ 35s 40ms/step - accuracy: 0.7939 - loss: 0.5136 203/1073 ━━━━━━━━━━━━━━━━━━━━ 34s 40ms/step - accuracy: 0.7938 - loss: 0.5136 205/1073 ━━━━━━━━━━━━━━━━━━━━ 34s 40ms/step - accuracy: 0.7938 - loss: 0.5137 207/1073 ━━━━━━━━━━━━━━━━━━━━ 34s 40ms/step - accuracy: 0.7938 - loss: 0.5137 209/1073 ━━━━━━━━━━━━━━━━━━━━ 34s 40ms/step - accuracy: 0.7938 - loss: 0.5138 211/1073 ━━━━━━━━━━━━━━━━━━━━ 34s 40ms/step - accuracy: 0.7937 - loss: 0.5138 213/1073 ━━━━━━━━━━━━━━━━━━━━ 34s 40ms/step - accuracy: 0.7937 - loss: 0.5139 215/1073 ━━━━━━━━━━━━━━━━━━━━ 34s 40ms/step - accuracy: 0.7937 - loss: 0.5139 217/1073 ━━━━━━━━━━━━━━━━━━━━ 34s 40ms/step - accuracy: 0.7937 - loss: 0.5139 219/1073 ━━━━━━━━━━━━━━━━━━━━ 34s 40ms/step - accuracy: 0.7936 - loss: 0.5140 221/1073 ━━━━━━━━━━━━━━━━━━━━ 34s 40ms/step - accuracy: 0.7936 - loss: 0.5140 223/1073 ━━━━━━━━━━━━━━━━━━━━ 34s 40ms/step - accuracy: 0.7936 - loss: 0.5141 225/1073 ━━━━━━━━━━━━━━━━━━━━ 34s 40ms/step - accuracy: 0.7936 - loss: 0.5141 227/1073 ━━━━━━━━━━━━━━━━━━━━ 33s 40ms/step - accuracy: 0.7935 - loss: 0.5142 229/1073 ━━━━━━━━━━━━━━━━━━━━ 33s 40ms/step - accuracy: 0.7935 - loss: 0.5142 231/1073 ━━━━━━━━━━━━━━━━━━━━ 33s 40ms/step - accuracy: 0.7935 - loss: 0.5143 233/1073 ━━━━━━━━━━━━━━━━━━━━ 33s 40ms/step - accuracy: 0.7935 - loss: 0.5143 235/1073 ━━━━━━━━━━━━━━━━━━━━ 33s 40ms/step - accuracy: 0.7934 - loss: 0.5144 237/1073 ━━━━━━━━━━━━━━━━━━━━ 33s 40ms/step - accuracy: 0.7934 - loss: 0.5144 239/1073 ━━━━━━━━━━━━━━━━━━━━ 33s 40ms/step - accuracy: 0.7934 - loss: 0.5145 241/1073 ━━━━━━━━━━━━━━━━━━━━ 33s 40ms/step - accuracy: 0.7934 - loss: 0.5145 243/1073 ━━━━━━━━━━━━━━━━━━━━ 33s 40ms/step - accuracy: 0.7934 - loss: 0.5145 245/1073 ━━━━━━━━━━━━━━━━━━━━ 33s 40ms/step - accuracy: 0.7933 - loss: 0.5146 247/1073 ━━━━━━━━━━━━━━━━━━━━ 33s 40ms/step - accuracy: 0.7933 - loss: 0.5146 249/1073 ━━━━━━━━━━━━━━━━━━━━ 33s 40ms/step - accuracy: 0.7933 - loss: 0.5147 251/1073 ━━━━━━━━━━━━━━━━━━━━ 33s 40ms/step - accuracy: 0.7933 - loss: 0.5147 253/1073 ━━━━━━━━━━━━━━━━━━━━ 32s 40ms/step - accuracy: 0.7933 - loss: 0.5147 255/1073 ━━━━━━━━━━━━━━━━━━━━ 32s 40ms/step - accuracy: 0.7933 - loss: 0.5148 257/1073 ━━━━━━━━━━━━━━━━━━━━ 32s 40ms/step - accuracy: 0.7932 - loss: 0.5148 259/1073 ━━━━━━━━━━━━━━━━━━━━ 32s 40ms/step - accuracy: 0.7932 - loss: 0.5148 261/1073 ━━━━━━━━━━━━━━━━━━━━ 32s 40ms/step - accuracy: 0.7932 - loss: 0.5149 263/1073 ━━━━━━━━━━━━━━━━━━━━ 32s 40ms/step - accuracy: 0.7932 - loss: 0.5149 265/1073 ━━━━━━━━━━━━━━━━━━━━ 32s 40ms/step - accuracy: 0.7932 - loss: 0.5150 267/1073 ━━━━━━━━━━━━━━━━━━━━ 32s 40ms/step - accuracy: 0.7931 - loss: 0.5150 269/1073 ━━━━━━━━━━━━━━━━━━━━ 32s 40ms/step - accuracy: 0.7931 - loss: 0.5150 271/1073 ━━━━━━━━━━━━━━━━━━━━ 32s 40ms/step - accuracy: 0.7931 - loss: 0.5151 273/1073 ━━━━━━━━━━━━━━━━━━━━ 32s 40ms/step - accuracy: 0.7931 - loss: 0.5151 275/1073 ━━━━━━━━━━━━━━━━━━━━ 32s 40ms/step - accuracy: 0.7931 - loss: 0.5151 277/1073 ━━━━━━━━━━━━━━━━━━━━ 32s 40ms/step - accuracy: 0.7931 - loss: 0.5152 279/1073 ━━━━━━━━━━━━━━━━━━━━ 31s 40ms/step - accuracy: 0.7930 - loss: 0.5152 281/1073 ━━━━━━━━━━━━━━━━━━━━ 31s 40ms/step - accuracy: 0.7930 - loss: 0.5152 283/1073 ━━━━━━━━━━━━━━━━━━━━ 31s 40ms/step - accuracy: 0.7930 - loss: 0.5152 285/1073 ━━━━━━━━━━━━━━━━━━━━ 31s 40ms/step - accuracy: 0.7930 - loss: 0.5153 287/1073 ━━━━━━━━━━━━━━━━━━━━ 31s 40ms/step - accuracy: 0.7930 - loss: 0.5153 289/1073 ━━━━━━━━━━━━━━━━━━━━ 31s 40ms/step - accuracy: 0.7930 - loss: 0.5153 291/1073 ━━━━━━━━━━━━━━━━━━━━ 31s 40ms/step - accuracy: 0.7930 - loss: 0.5153 293/1073 ━━━━━━━━━━━━━━━━━━━━ 31s 40ms/step - accuracy: 0.7930 - loss: 0.5154 295/1073 ━━━━━━━━━━━━━━━━━━━━ 31s 40ms/step - accuracy: 0.7929 - loss: 0.5154 297/1073 ━━━━━━━━━━━━━━━━━━━━ 31s 40ms/step - accuracy: 0.7929 - loss: 0.5154 299/1073 ━━━━━━━━━━━━━━━━━━━━ 31s 40ms/step - accuracy: 0.7929 - loss: 0.5155 301/1073 ━━━━━━━━━━━━━━━━━━━━ 31s 40ms/step - accuracy: 0.7929 - loss: 0.5155 303/1073 ━━━━━━━━━━━━━━━━━━━━ 30s 40ms/step - accuracy: 0.7929 - loss: 0.5155 305/1073 ━━━━━━━━━━━━━━━━━━━━ 30s 40ms/step - accuracy: 0.7929 - loss: 0.5155 307/1073 ━━━━━━━━━━━━━━━━━━━━ 30s 40ms/step - accuracy: 0.7929 - loss: 0.5155 309/1073 ━━━━━━━━━━━━━━━━━━━━ 30s 40ms/step - accuracy: 0.7929 - loss: 0.5156 311/1073 ━━━━━━━━━━━━━━━━━━━━ 30s 40ms/step - accuracy: 0.7928 - loss: 0.5156 313/1073 ━━━━━━━━━━━━━━━━━━━━ 30s 40ms/step - accuracy: 0.7928 - loss: 0.5156 314/1073 ━━━━━━━━━━━━━━━━━━━━ 30s 40ms/step - accuracy: 0.7928 - loss: 0.5156 316/1073 ━━━━━━━━━━━━━━━━━━━━ 30s 40ms/step - accuracy: 0.7928 - loss: 0.5156 318/1073 ━━━━━━━━━━━━━━━━━━━━ 30s 40ms/step - accuracy: 0.7928 - loss: 0.5157 319/1073 ━━━━━━━━━━━━━━━━━━━━ 30s 40ms/step - accuracy: 0.7928 - loss: 0.5157 321/1073 ━━━━━━━━━━━━━━━━━━━━ 30s 40ms/step - accuracy: 0.7928 - loss: 0.5157 323/1073 ━━━━━━━━━━━━━━━━━━━━ 30s 40ms/step - accuracy: 0.7928 - loss: 0.5157 325/1073 ━━━━━━━━━━━━━━━━━━━━ 30s 41ms/step - accuracy: 0.7928 - loss: 0.5157 327/1073 ━━━━━━━━━━━━━━━━━━━━ 30s 41ms/step - accuracy: 0.7928 - loss: 0.5158 329/1073 ━━━━━━━━━━━━━━━━━━━━ 30s 41ms/step - accuracy: 0.7928 - loss: 0.5158 331/1073 ━━━━━━━━━━━━━━━━━━━━ 30s 41ms/step - accuracy: 0.7927 - loss: 0.5158 333/1073 ━━━━━━━━━━━━━━━━━━━━ 30s 41ms/step - accuracy: 0.7927 - loss: 0.5158 335/1073 ━━━━━━━━━━━━━━━━━━━━ 29s 41ms/step - accuracy: 0.7927 - loss: 0.5158 337/1073 ━━━━━━━━━━━━━━━━━━━━ 29s 41ms/step - accuracy: 0.7927 - loss: 0.5159 339/1073 ━━━━━━━━━━━━━━━━━━━━ 29s 41ms/step - accuracy: 0.7927 - loss: 0.5159 341/1073 ━━━━━━━━━━━━━━━━━━━━ 29s 41ms/step - accuracy: 0.7927 - loss: 0.5159 343/1073 ━━━━━━━━━━━━━━━━━━━━ 29s 41ms/step - accuracy: 0.7927 - loss: 0.5159 345/1073 ━━━━━━━━━━━━━━━━━━━━ 29s 41ms/step - accuracy: 0.7927 - loss: 0.5159 347/1073 ━━━━━━━━━━━━━━━━━━━━ 29s 41ms/step - accuracy: 0.7927 - loss: 0.5159 349/1073 ━━━━━━━━━━━━━━━━━━━━ 29s 41ms/step - accuracy: 0.7927 - loss: 0.5160 351/1073 ━━━━━━━━━━━━━━━━━━━━ 29s 41ms/step - accuracy: 0.7927 - loss: 0.5160 353/1073 ━━━━━━━━━━━━━━━━━━━━ 29s 41ms/step - accuracy: 0.7927 - loss: 0.5160 355/1073 ━━━━━━━━━━━━━━━━━━━━ 29s 41ms/step - accuracy: 0.7926 - loss: 0.5160 357/1073 ━━━━━━━━━━━━━━━━━━━━ 29s 41ms/step - accuracy: 0.7926 - loss: 0.5160 359/1073 ━━━━━━━━━━━━━━━━━━━━ 28s 41ms/step - accuracy: 0.7926 - loss: 0.5160 361/1073 ━━━━━━━━━━━━━━━━━━━━ 28s 41ms/step - accuracy: 0.7926 - loss: 0.5161 363/1073 ━━━━━━━━━━━━━━━━━━━━ 28s 41ms/step - accuracy: 0.7926 - loss: 0.5161 365/1073 ━━━━━━━━━━━━━━━━━━━━ 28s 41ms/step - accuracy: 0.7926 - loss: 0.5161 367/1073 ━━━━━━━━━━━━━━━━━━━━ 28s 41ms/step - accuracy: 0.7926 - loss: 0.5161 369/1073 ━━━━━━━━━━━━━━━━━━━━ 28s 41ms/step - accuracy: 0.7926 - loss: 0.5161 371/1073 ━━━━━━━━━━━━━━━━━━━━ 28s 41ms/step - accuracy: 0.7926 - loss: 0.5162 373/1073 ━━━━━━━━━━━━━━━━━━━━ 28s 41ms/step - accuracy: 0.7926 - loss: 0.5162 375/1073 ━━━━━━━━━━━━━━━━━━━━ 28s 41ms/step - accuracy: 0.7926 - loss: 0.5162 377/1073 ━━━━━━━━━━━━━━━━━━━━ 28s 41ms/step - accuracy: 0.7926 - loss: 0.5162 379/1073 ━━━━━━━━━━━━━━━━━━━━ 28s 41ms/step - accuracy: 0.7925 - loss: 0.5162 381/1073 ━━━━━━━━━━━━━━━━━━━━ 28s 41ms/step - accuracy: 0.7925 - loss: 0.5163 383/1073 ━━━━━━━━━━━━━━━━━━━━ 27s 41ms/step - accuracy: 0.7925 - loss: 0.5163 385/1073 ━━━━━━━━━━━━━━━━━━━━ 27s 41ms/step - accuracy: 0.7925 - loss: 0.5163 387/1073 ━━━━━━━━━━━━━━━━━━━━ 27s 41ms/step - accuracy: 0.7925 - loss: 0.5163 389/1073 ━━━━━━━━━━━━━━━━━━━━ 27s 41ms/step - accuracy: 0.7925 - loss: 0.5164 391/1073 ━━━━━━━━━━━━━━━━━━━━ 27s 41ms/step - accuracy: 0.7925 - loss: 0.5164 392/1073 ━━━━━━━━━━━━━━━━━━━━ 27s 41ms/step - accuracy: 0.7925 - loss: 0.5164 394/1073 ━━━━━━━━━━━━━━━━━━━━ 27s 41ms/step - accuracy: 0.7925 - loss: 0.5164 396/1073 ━━━━━━━━━━━━━━━━━━━━ 27s 41ms/step - accuracy: 0.7924 - loss: 0.5165 398/1073 ━━━━━━━━━━━━━━━━━━━━ 27s 41ms/step - accuracy: 0.7924 - loss: 0.5165 400/1073 ━━━━━━━━━━━━━━━━━━━━ 27s 41ms/step - accuracy: 0.7924 - loss: 0.5165 402/1073 ━━━━━━━━━━━━━━━━━━━━ 27s 41ms/step - accuracy: 0.7924 - loss: 0.5165 404/1073 ━━━━━━━━━━━━━━━━━━━━ 27s 41ms/step - accuracy: 0.7924 - loss: 0.5165 405/1073 ━━━━━━━━━━━━━━━━━━━━ 27s 41ms/step - accuracy: 0.7924 - loss: 0.5166 407/1073 ━━━━━━━━━━━━━━━━━━━━ 27s 41ms/step - accuracy: 0.7924 - loss: 0.5166 408/1073 ━━━━━━━━━━━━━━━━━━━━ 27s 41ms/step - accuracy: 0.7924 - loss: 0.5166 410/1073 ━━━━━━━━━━━━━━━━━━━━ 27s 41ms/step - accuracy: 0.7924 - loss: 0.5166 411/1073 ━━━━━━━━━━━━━━━━━━━━ 27s 41ms/step - accuracy: 0.7924 - loss: 0.5166 413/1073 ━━━━━━━━━━━━━━━━━━━━ 27s 41ms/step - accuracy: 0.7924 - loss: 0.5167 415/1073 ━━━━━━━━━━━━━━━━━━━━ 26s 41ms/step - accuracy: 0.7923 - loss: 0.5167 417/1073 ━━━━━━━━━━━━━━━━━━━━ 26s 41ms/step - accuracy: 0.7923 - loss: 0.5167 419/1073 ━━━━━━━━━━━━━━━━━━━━ 26s 41ms/step - accuracy: 0.7923 - loss: 0.5167 421/1073 ━━━━━━━━━━━━━━━━━━━━ 26s 41ms/step - accuracy: 0.7923 - loss: 0.5167 423/1073 ━━━━━━━━━━━━━━━━━━━━ 26s 41ms/step - accuracy: 0.7923 - loss: 0.5168 425/1073 ━━━━━━━━━━━━━━━━━━━━ 26s 41ms/step - accuracy: 0.7923 - loss: 0.5168 427/1073 ━━━━━━━━━━━━━━━━━━━━ 26s 41ms/step - accuracy: 0.7923 - loss: 0.5168 429/1073 ━━━━━━━━━━━━━━━━━━━━ 26s 41ms/step - accuracy: 0.7923 - loss: 0.5168 430/1073 ━━━━━━━━━━━━━━━━━━━━ 26s 41ms/step - accuracy: 0.7923 - loss: 0.5169 432/1073 ━━━━━━━━━━━━━━━━━━━━ 26s 41ms/step - accuracy: 0.7923 - loss: 0.5169 434/1073 ━━━━━━━━━━━━━━━━━━━━ 26s 41ms/step - accuracy: 0.7923 - loss: 0.5169 436/1073 ━━━━━━━━━━━━━━━━━━━━ 26s 41ms/step - accuracy: 0.7922 - loss: 0.5169 438/1073 ━━━━━━━━━━━━━━━━━━━━ 26s 41ms/step - accuracy: 0.7922 - loss: 0.5170 440/1073 ━━━━━━━━━━━━━━━━━━━━ 26s 41ms/step - accuracy: 0.7922 - loss: 0.5170 442/1073 ━━━━━━━━━━━━━━━━━━━━ 26s 41ms/step - accuracy: 0.7922 - loss: 0.5170 444/1073 ━━━━━━━━━━━━━━━━━━━━ 26s 41ms/step - accuracy: 0.7922 - loss: 0.5170 446/1073 ━━━━━━━━━━━━━━━━━━━━ 25s 41ms/step - accuracy: 0.7922 - loss: 0.5170 448/1073 ━━━━━━━━━━━━━━━━━━━━ 25s 41ms/step - accuracy: 0.7922 - loss: 0.5171 450/1073 ━━━━━━━━━━━━━━━━━━━━ 25s 41ms/step - accuracy: 0.7922 - loss: 0.5171 452/1073 ━━━━━━━━━━━━━━━━━━━━ 25s 41ms/step - accuracy: 0.7922 - loss: 0.5171 453/1073 ━━━━━━━━━━━━━━━━━━━━ 25s 41ms/step - accuracy: 0.7922 - loss: 0.5171 455/1073 ━━━━━━━━━━━━━━━━━━━━ 25s 42ms/step - accuracy: 0.7922 - loss: 0.5172 456/1073 ━━━━━━━━━━━━━━━━━━━━ 25s 42ms/step - accuracy: 0.7921 - loss: 0.5172 458/1073 ━━━━━━━━━━━━━━━━━━━━ 25s 42ms/step - accuracy: 0.7921 - loss: 0.5172 459/1073 ━━━━━━━━━━━━━━━━━━━━ 25s 42ms/step - accuracy: 0.7921 - loss: 0.5172 461/1073 ━━━━━━━━━━━━━━━━━━━━ 25s 42ms/step - accuracy: 0.7921 - loss: 0.5172 463/1073 ━━━━━━━━━━━━━━━━━━━━ 25s 42ms/step - accuracy: 0.7921 - loss: 0.5172 465/1073 ━━━━━━━━━━━━━━━━━━━━ 25s 42ms/step - accuracy: 0.7921 - loss: 0.5173 467/1073 ━━━━━━━━━━━━━━━━━━━━ 25s 42ms/step - accuracy: 0.7921 - loss: 0.5173 469/1073 ━━━━━━━━━━━━━━━━━━━━ 25s 42ms/step - accuracy: 0.7921 - loss: 0.5173 471/1073 ━━━━━━━━━━━━━━━━━━━━ 25s 42ms/step - accuracy: 0.7921 - loss: 0.5173 473/1073 ━━━━━━━━━━━━━━━━━━━━ 25s 42ms/step - accuracy: 0.7921 - loss: 0.5174 475/1073 ━━━━━━━━━━━━━━━━━━━━ 24s 42ms/step - accuracy: 0.7921 - loss: 0.5174 477/1073 ━━━━━━━━━━━━━━━━━━━━ 24s 42ms/step - accuracy: 0.7921 - loss: 0.5174 479/1073 ━━━━━━━━━━━━━━━━━━━━ 24s 42ms/step - accuracy: 0.7920 - loss: 0.5174 480/1073 ━━━━━━━━━━━━━━━━━━━━ 24s 42ms/step - accuracy: 0.7920 - loss: 0.5174 482/1073 ━━━━━━━━━━━━━━━━━━━━ 24s 42ms/step - accuracy: 0.7920 - loss: 0.5174 483/1073 ━━━━━━━━━━━━━━━━━━━━ 24s 42ms/step - accuracy: 0.7920 - loss: 0.5175 485/1073 ━━━━━━━━━━━━━━━━━━━━ 24s 42ms/step - accuracy: 0.7920 - loss: 0.5175 486/1073 ━━━━━━━━━━━━━━━━━━━━ 24s 42ms/step - accuracy: 0.7920 - loss: 0.5175 488/1073 ━━━━━━━━━━━━━━━━━━━━ 24s 42ms/step - accuracy: 0.7920 - loss: 0.5175 490/1073 ━━━━━━━━━━━━━━━━━━━━ 24s 42ms/step - accuracy: 0.7920 - loss: 0.5175 492/1073 ━━━━━━━━━━━━━━━━━━━━ 24s 42ms/step - accuracy: 0.7920 - loss: 0.5175 493/1073 ━━━━━━━━━━━━━━━━━━━━ 24s 42ms/step - accuracy: 0.7920 - loss: 0.5176 495/1073 ━━━━━━━━━━━━━━━━━━━━ 24s 42ms/step - accuracy: 0.7920 - loss: 0.5176 496/1073 ━━━━━━━━━━━━━━━━━━━━ 24s 42ms/step - accuracy: 0.7920 - loss: 0.5176 498/1073 ━━━━━━━━━━━━━━━━━━━━ 24s 42ms/step - accuracy: 0.7920 - loss: 0.5176 500/1073 ━━━━━━━━━━━━━━━━━━━━ 24s 42ms/step - accuracy: 0.7920 - loss: 0.5176 502/1073 ━━━━━━━━━━━━━━━━━━━━ 24s 42ms/step - accuracy: 0.7920 - loss: 0.5176 504/1073 ━━━━━━━━━━━━━━━━━━━━ 23s 42ms/step - accuracy: 0.7919 - loss: 0.5177 506/1073 ━━━━━━━━━━━━━━━━━━━━ 23s 42ms/step - accuracy: 0.7919 - loss: 0.5177 508/1073 ━━━━━━━━━━━━━━━━━━━━ 23s 42ms/step - accuracy: 0.7919 - loss: 0.5177 510/1073 ━━━━━━━━━━━━━━━━━━━━ 23s 42ms/step - accuracy: 0.7919 - loss: 0.5177 512/1073 ━━━━━━━━━━━━━━━━━━━━ 23s 42ms/step - accuracy: 0.7919 - loss: 0.5177 514/1073 ━━━━━━━━━━━━━━━━━━━━ 23s 42ms/step - accuracy: 0.7919 - loss: 0.5178 515/1073 ━━━━━━━━━━━━━━━━━━━━ 23s 42ms/step - accuracy: 0.7919 - loss: 0.5178 517/1073 ━━━━━━━━━━━━━━━━━━━━ 23s 42ms/step - accuracy: 0.7919 - loss: 0.5178 519/1073 ━━━━━━━━━━━━━━━━━━━━ 23s 42ms/step - accuracy: 0.7919 - loss: 0.5178 521/1073 ━━━━━━━━━━━━━━━━━━━━ 23s 42ms/step - accuracy: 0.7919 - loss: 0.5178 523/1073 ━━━━━━━━━━━━━━━━━━━━ 23s 42ms/step - accuracy: 0.7919 - loss: 0.5178 525/1073 ━━━━━━━━━━━━━━━━━━━━ 23s 42ms/step - accuracy: 0.7919 - loss: 0.5179 527/1073 ━━━━━━━━━━━━━━━━━━━━ 23s 42ms/step - accuracy: 0.7919 - loss: 0.5179 529/1073 ━━━━━━━━━━━━━━━━━━━━ 23s 42ms/step - accuracy: 0.7918 - loss: 0.5179 531/1073 ━━━━━━━━━━━━━━━━━━━━ 22s 42ms/step - accuracy: 0.7918 - loss: 0.5179 533/1073 ━━━━━━━━━━━━━━━━━━━━ 22s 42ms/step - accuracy: 0.7918 - loss: 0.5179 535/1073 ━━━━━━━━━━━━━━━━━━━━ 22s 42ms/step - accuracy: 0.7918 - loss: 0.5180 537/1073 ━━━━━━━━━━━━━━━━━━━━ 22s 42ms/step - accuracy: 0.7918 - loss: 0.5180 539/1073 ━━━━━━━━━━━━━━━━━━━━ 22s 42ms/step - accuracy: 0.7918 - loss: 0.5180 541/1073 ━━━━━━━━━━━━━━━━━━━━ 22s 42ms/step - accuracy: 0.7918 - loss: 0.5180 542/1073 ━━━━━━━━━━━━━━━━━━━━ 22s 42ms/step - accuracy: 0.7918 - loss: 0.5180 544/1073 ━━━━━━━━━━━━━━━━━━━━ 22s 42ms/step - accuracy: 0.7918 - loss: 0.5180 545/1073 ━━━━━━━━━━━━━━━━━━━━ 22s 42ms/step - accuracy: 0.7918 - loss: 0.5180 547/1073 ━━━━━━━━━━━━━━━━━━━━ 22s 42ms/step - accuracy: 0.7918 - loss: 0.5181 548/1073 ━━━━━━━━━━━━━━━━━━━━ 22s 42ms/step - accuracy: 0.7918 - loss: 0.5181 550/1073 ━━━━━━━━━━━━━━━━━━━━ 22s 43ms/step - accuracy: 0.7918 - loss: 0.5181 552/1073 ━━━━━━━━━━━━━━━━━━━━ 22s 43ms/step - accuracy: 0.7918 - loss: 0.5181 554/1073 ━━━━━━━━━━━━━━━━━━━━ 22s 43ms/step - accuracy: 0.7918 - loss: 0.5181 556/1073 ━━━━━━━━━━━━━━━━━━━━ 21s 43ms/step - accuracy: 0.7918 - loss: 0.5181 558/1073 ━━━━━━━━━━━━━━━━━━━━ 21s 43ms/step - accuracy: 0.7917 - loss: 0.5182 560/1073 ━━━━━━━━━━━━━━━━━━━━ 21s 43ms/step - accuracy: 0.7917 - loss: 0.5182 562/1073 ━━━━━━━━━━━━━━━━━━━━ 21s 43ms/step - accuracy: 0.7917 - loss: 0.5182 563/1073 ━━━━━━━━━━━━━━━━━━━━ 21s 43ms/step - accuracy: 0.7917 - loss: 0.5182 565/1073 ━━━━━━━━━━━━━━━━━━━━ 21s 43ms/step - accuracy: 0.7917 - loss: 0.5182 566/1073 ━━━━━━━━━━━━━━━━━━━━ 21s 43ms/step - accuracy: 0.7917 - loss: 0.5182 568/1073 ━━━━━━━━━━━━━━━━━━━━ 21s 43ms/step - accuracy: 0.7917 - loss: 0.5182 569/1073 ━━━━━━━━━━━━━━━━━━━━ 21s 43ms/step - accuracy: 0.7917 - loss: 0.5182 571/1073 ━━━━━━━━━━━━━━━━━━━━ 21s 43ms/step - accuracy: 0.7917 - loss: 0.5183 573/1073 ━━━━━━━━━━━━━━━━━━━━ 21s 43ms/step - accuracy: 0.7917 - loss: 0.5183 575/1073 ━━━━━━━━━━━━━━━━━━━━ 21s 43ms/step - accuracy: 0.7917 - loss: 0.5183 577/1073 ━━━━━━━━━━━━━━━━━━━━ 21s 43ms/step - accuracy: 0.7917 - loss: 0.5183 579/1073 ━━━━━━━━━━━━━━━━━━━━ 21s 43ms/step - accuracy: 0.7917 - loss: 0.5183 581/1073 ━━━━━━━━━━━━━━━━━━━━ 21s 43ms/step - accuracy: 0.7917 - loss: 0.5183 583/1073 ━━━━━━━━━━━━━━━━━━━━ 20s 43ms/step - accuracy: 0.7917 - loss: 0.5184 584/1073 ━━━━━━━━━━━━━━━━━━━━ 20s 43ms/step - accuracy: 0.7917 - loss: 0.5184 586/1073 ━━━━━━━━━━━━━━━━━━━━ 20s 43ms/step - accuracy: 0.7917 - loss: 0.5184 587/1073 ━━━━━━━━━━━━━━━━━━━━ 20s 43ms/step - accuracy: 0.7917 - loss: 0.5184 589/1073 ━━━━━━━━━━━━━━━━━━━━ 20s 43ms/step - accuracy: 0.7916 - loss: 0.5184 590/1073 ━━━━━━━━━━━━━━━━━━━━ 20s 43ms/step - accuracy: 0.7916 - loss: 0.5184 592/1073 ━━━━━━━━━━━━━━━━━━━━ 20s 43ms/step - accuracy: 0.7916 - loss: 0.5184 594/1073 ━━━━━━━━━━━━━━━━━━━━ 20s 43ms/step - accuracy: 0.7916 - loss: 0.5184 596/1073 ━━━━━━━━━━━━━━━━━━━━ 20s 43ms/step - accuracy: 0.7916 - loss: 0.5185 598/1073 ━━━━━━━━━━━━━━━━━━━━ 20s 43ms/step - accuracy: 0.7916 - loss: 0.5185 600/1073 ━━━━━━━━━━━━━━━━━━━━ 20s 43ms/step - accuracy: 0.7916 - loss: 0.5185 602/1073 ━━━━━━━━━━━━━━━━━━━━ 20s 43ms/step - accuracy: 0.7916 - loss: 0.5185 603/1073 ━━━━━━━━━━━━━━━━━━━━ 20s 43ms/step - accuracy: 0.7916 - loss: 0.5185 605/1073 ━━━━━━━━━━━━━━━━━━━━ 20s 43ms/step - accuracy: 0.7916 - loss: 0.5185 607/1073 ━━━━━━━━━━━━━━━━━━━━ 20s 43ms/step - accuracy: 0.7916 - loss: 0.5185 609/1073 ━━━━━━━━━━━━━━━━━━━━ 19s 43ms/step - accuracy: 0.7916 - loss: 0.5185 611/1073 ━━━━━━━━━━━━━━━━━━━━ 19s 43ms/step - accuracy: 0.7916 - loss: 0.5185 612/1073 ━━━━━━━━━━━━━━━━━━━━ 19s 43ms/step - accuracy: 0.7916 - loss: 0.5186 614/1073 ━━━━━━━━━━━━━━━━━━━━ 19s 43ms/step - accuracy: 0.7916 - loss: 0.5186 615/1073 ━━━━━━━━━━━━━━━━━━━━ 19s 43ms/step - accuracy: 0.7916 - loss: 0.5186 617/1073 ━━━━━━━━━━━━━━━━━━━━ 19s 43ms/step - accuracy: 0.7916 - loss: 0.5186 618/1073 ━━━━━━━━━━━━━━━━━━━━ 19s 43ms/step - accuracy: 0.7916 - loss: 0.5186 620/1073 ━━━━━━━━━━━━━━━━━━━━ 19s 43ms/step - accuracy: 0.7916 - loss: 0.5186 621/1073 ━━━━━━━━━━━━━━━━━━━━ 19s 43ms/step - accuracy: 0.7916 - loss: 0.5186 623/1073 ━━━━━━━━━━━━━━━━━━━━ 19s 43ms/step - accuracy: 0.7915 - loss: 0.5186 624/1073 ━━━━━━━━━━━━━━━━━━━━ 19s 43ms/step - accuracy: 0.7915 - loss: 0.5186 626/1073 ━━━━━━━━━━━━━━━━━━━━ 19s 43ms/step - accuracy: 0.7915 - loss: 0.5186 627/1073 ━━━━━━━━━━━━━━━━━━━━ 19s 43ms/step - accuracy: 0.7915 - loss: 0.5187 629/1073 ━━━━━━━━━━━━━━━━━━━━ 19s 43ms/step - accuracy: 0.7915 - loss: 0.5187 631/1073 ━━━━━━━━━━━━━━━━━━━━ 19s 43ms/step - accuracy: 0.7915 - loss: 0.5187 633/1073 ━━━━━━━━━━━━━━━━━━━━ 18s 43ms/step - accuracy: 0.7915 - loss: 0.5187 635/1073 ━━━━━━━━━━━━━━━━━━━━ 18s 43ms/step - accuracy: 0.7915 - loss: 0.5187 637/1073 ━━━━━━━━━━━━━━━━━━━━ 18s 43ms/step - accuracy: 0.7915 - loss: 0.5187 639/1073 ━━━━━━━━━━━━━━━━━━━━ 18s 43ms/step - accuracy: 0.7915 - loss: 0.5187 641/1073 ━━━━━━━━━━━━━━━━━━━━ 18s 43ms/step - accuracy: 0.7915 - loss: 0.5187 642/1073 ━━━━━━━━━━━━━━━━━━━━ 18s 43ms/step - accuracy: 0.7915 - loss: 0.5188 644/1073 ━━━━━━━━━━━━━━━━━━━━ 18s 43ms/step - accuracy: 0.7915 - loss: 0.5188 645/1073 ━━━━━━━━━━━━━━━━━━━━ 18s 43ms/step - accuracy: 0.7915 - loss: 0.5188 647/1073 ━━━━━━━━━━━━━━━━━━━━ 18s 43ms/step - accuracy: 0.7915 - loss: 0.5188 649/1073 ━━━━━━━━━━━━━━━━━━━━ 18s 43ms/step - accuracy: 0.7915 - loss: 0.5188 651/1073 ━━━━━━━━━━━━━━━━━━━━ 18s 43ms/step - accuracy: 0.7915 - loss: 0.5188 652/1073 ━━━━━━━━━━━━━━━━━━━━ 18s 43ms/step - accuracy: 0.7915 - loss: 0.5188 654/1073 ━━━━━━━━━━━━━━━━━━━━ 18s 43ms/step - accuracy: 0.7915 - loss: 0.5188 655/1073 ━━━━━━━━━━━━━━━━━━━━ 18s 43ms/step - accuracy: 0.7915 - loss: 0.5188 657/1073 ━━━━━━━━━━━━━━━━━━━━ 18s 43ms/step - accuracy: 0.7915 - loss: 0.5188 658/1073 ━━━━━━━━━━━━━━━━━━━━ 17s 43ms/step - accuracy: 0.7914 - loss: 0.5189 660/1073 ━━━━━━━━━━━━━━━━━━━━ 17s 43ms/step - accuracy: 0.7914 - loss: 0.5189 662/1073 ━━━━━━━━━━━━━━━━━━━━ 17s 43ms/step - accuracy: 0.7914 - loss: 0.5189 664/1073 ━━━━━━━━━━━━━━━━━━━━ 17s 43ms/step - accuracy: 0.7914 - loss: 0.5189 666/1073 ━━━━━━━━━━━━━━━━━━━━ 17s 43ms/step - accuracy: 0.7914 - loss: 0.5189 668/1073 ━━━━━━━━━━━━━━━━━━━━ 17s 43ms/step - accuracy: 0.7914 - loss: 0.5189 669/1073 ━━━━━━━━━━━━━━━━━━━━ 17s 43ms/step - accuracy: 0.7914 - loss: 0.5189 671/1073 ━━━━━━━━━━━━━━━━━━━━ 17s 43ms/step - accuracy: 0.7914 - loss: 0.5189 673/1073 ━━━━━━━━━━━━━━━━━━━━ 17s 43ms/step - accuracy: 0.7914 - loss: 0.5189 675/1073 ━━━━━━━━━━━━━━━━━━━━ 17s 43ms/step - accuracy: 0.7914 - loss: 0.5190 676/1073 ━━━━━━━━━━━━━━━━━━━━ 17s 43ms/step - accuracy: 0.7914 - loss: 0.5190 678/1073 ━━━━━━━━━━━━━━━━━━━━ 17s 43ms/step - accuracy: 0.7914 - loss: 0.5190 680/1073 ━━━━━━━━━━━━━━━━━━━━ 17s 43ms/step - accuracy: 0.7914 - loss: 0.5190 682/1073 ━━━━━━━━━━━━━━━━━━━━ 16s 43ms/step - accuracy: 0.7914 - loss: 0.5190 684/1073 ━━━━━━━━━━━━━━━━━━━━ 16s 43ms/step - accuracy: 0.7914 - loss: 0.5190 686/1073 ━━━━━━━━━━━━━━━━━━━━ 16s 43ms/step - accuracy: 0.7914 - loss: 0.5190 688/1073 ━━━━━━━━━━━━━━━━━━━━ 16s 43ms/step - accuracy: 0.7914 - loss: 0.5190 690/1073 ━━━━━━━━━━━━━━━━━━━━ 16s 43ms/step - accuracy: 0.7914 - loss: 0.5190 692/1073 ━━━━━━━━━━━━━━━━━━━━ 16s 43ms/step - accuracy: 0.7914 - loss: 0.5191 694/1073 ━━━━━━━━━━━━━━━━━━━━ 16s 43ms/step - accuracy: 0.7914 - loss: 0.5191 695/1073 ━━━━━━━━━━━━━━━━━━━━ 16s 43ms/step - accuracy: 0.7914 - loss: 0.5191 697/1073 ━━━━━━━━━━━━━━━━━━━━ 16s 43ms/step - accuracy: 0.7913 - loss: 0.5191 698/1073 ━━━━━━━━━━━━━━━━━━━━ 16s 43ms/step - accuracy: 0.7913 - loss: 0.5191 700/1073 ━━━━━━━━━━━━━━━━━━━━ 16s 44ms/step - accuracy: 0.7913 - loss: 0.5191 702/1073 ━━━━━━━━━━━━━━━━━━━━ 16s 44ms/step - accuracy: 0.7913 - loss: 0.5191 704/1073 ━━━━━━━━━━━━━━━━━━━━ 16s 44ms/step - accuracy: 0.7913 - loss: 0.5191 706/1073 ━━━━━━━━━━━━━━━━━━━━ 15s 44ms/step - accuracy: 0.7913 - loss: 0.5191 708/1073 ━━━━━━━━━━━━━━━━━━━━ 15s 44ms/step - accuracy: 0.7913 - loss: 0.5192 710/1073 ━━━━━━━━━━━━━━━━━━━━ 15s 44ms/step - accuracy: 0.7913 - loss: 0.5192 712/1073 ━━━━━━━━━━━━━━━━━━━━ 15s 44ms/step - accuracy: 0.7913 - loss: 0.5192 714/1073 ━━━━━━━━━━━━━━━━━━━━ 15s 44ms/step - accuracy: 0.7913 - loss: 0.5192 716/1073 ━━━━━━━━━━━━━━━━━━━━ 15s 44ms/step - accuracy: 0.7913 - loss: 0.5192 718/1073 ━━━━━━━━━━━━━━━━━━━━ 15s 44ms/step - accuracy: 0.7913 - loss: 0.5192 720/1073 ━━━━━━━━━━━━━━━━━━━━ 15s 44ms/step - accuracy: 0.7913 - loss: 0.5192 722/1073 ━━━━━━━━━━━━━━━━━━━━ 15s 44ms/step - accuracy: 0.7913 - loss: 0.5192 724/1073 ━━━━━━━━━━━━━━━━━━━━ 15s 44ms/step - accuracy: 0.7913 - loss: 0.5193 726/1073 ━━━━━━━━━━━━━━━━━━━━ 15s 44ms/step - accuracy: 0.7913 - loss: 0.5193 728/1073 ━━━━━━━━━━━━━━━━━━━━ 15s 44ms/step - accuracy: 0.7913 - loss: 0.5193 730/1073 ━━━━━━━━━━━━━━━━━━━━ 14s 44ms/step - accuracy: 0.7913 - loss: 0.5193 732/1073 ━━━━━━━━━━━━━━━━━━━━ 14s 44ms/step - accuracy: 0.7913 - loss: 0.5193 733/1073 ━━━━━━━━━━━━━━━━━━━━ 14s 44ms/step - accuracy: 0.7913 - loss: 0.5193 735/1073 ━━━━━━━━━━━━━━━━━━━━ 14s 44ms/step - accuracy: 0.7912 - loss: 0.5193 736/1073 ━━━━━━━━━━━━━━━━━━━━ 14s 44ms/step - accuracy: 0.7912 - loss: 0.5193 738/1073 ━━━━━━━━━━━━━━━━━━━━ 14s 44ms/step - accuracy: 0.7912 - loss: 0.5193 740/1073 ━━━━━━━━━━━━━━━━━━━━ 14s 44ms/step - accuracy: 0.7912 - loss: 0.5193 742/1073 ━━━━━━━━━━━━━━━━━━━━ 14s 44ms/step - accuracy: 0.7912 - loss: 0.5193 744/1073 ━━━━━━━━━━━━━━━━━━━━ 14s 44ms/step - accuracy: 0.7912 - loss: 0.5194 746/1073 ━━━━━━━━━━━━━━━━━━━━ 14s 44ms/step - accuracy: 0.7912 - loss: 0.5194 748/1073 ━━━━━━━━━━━━━━━━━━━━ 14s 44ms/step - accuracy: 0.7912 - loss: 0.5194 750/1073 ━━━━━━━━━━━━━━━━━━━━ 14s 44ms/step - accuracy: 0.7912 - loss: 0.5194 752/1073 ━━━━━━━━━━━━━━━━━━━━ 14s 44ms/step - accuracy: 0.7912 - loss: 0.5194 754/1073 ━━━━━━━━━━━━━━━━━━━━ 13s 44ms/step - accuracy: 0.7912 - loss: 0.5194 756/1073 ━━━━━━━━━━━━━━━━━━━━ 13s 44ms/step - accuracy: 0.7912 - loss: 0.5194 757/1073 ━━━━━━━━━━━━━━━━━━━━ 13s 44ms/step - accuracy: 0.7912 - loss: 0.5194 759/1073 ━━━━━━━━━━━━━━━━━━━━ 13s 44ms/step - accuracy: 0.7912 - loss: 0.5194 761/1073 ━━━━━━━━━━━━━━━━━━━━ 13s 44ms/step - accuracy: 0.7912 - loss: 0.5194 763/1073 ━━━━━━━━━━━━━━━━━━━━ 13s 44ms/step - accuracy: 0.7912 - loss: 0.5194 765/1073 ━━━━━━━━━━━━━━━━━━━━ 13s 44ms/step - accuracy: 0.7912 - loss: 0.5195 766/1073 ━━━━━━━━━━━━━━━━━━━━ 13s 44ms/step - accuracy: 0.7912 - loss: 0.5195 768/1073 ━━━━━━━━━━━━━━━━━━━━ 13s 44ms/step - accuracy: 0.7912 - loss: 0.5195 769/1073 ━━━━━━━━━━━━━━━━━━━━ 13s 44ms/step - accuracy: 0.7912 - loss: 0.5195 771/1073 ━━━━━━━━━━━━━━━━━━━━ 13s 44ms/step - accuracy: 0.7912 - loss: 0.5195 773/1073 ━━━━━━━━━━━━━━━━━━━━ 13s 44ms/step - accuracy: 0.7912 - loss: 0.5195 775/1073 ━━━━━━━━━━━━━━━━━━━━ 13s 44ms/step - accuracy: 0.7912 - loss: 0.5195 777/1073 ━━━━━━━━━━━━━━━━━━━━ 12s 44ms/step - accuracy: 0.7912 - loss: 0.5195 778/1073 ━━━━━━━━━━━━━━━━━━━━ 12s 44ms/step - accuracy: 0.7912 - loss: 0.5195 780/1073 ━━━━━━━━━━━━━━━━━━━━ 12s 44ms/step - accuracy: 0.7912 - loss: 0.5195 782/1073 ━━━━━━━━━━━━━━━━━━━━ 12s 44ms/step - accuracy: 0.7912 - loss: 0.5195 784/1073 ━━━━━━━━━━━━━━━━━━━━ 12s 44ms/step - accuracy: 0.7911 - loss: 0.5195 786/1073 ━━━━━━━━━━━━━━━━━━━━ 12s 44ms/step - accuracy: 0.7911 - loss: 0.5195 787/1073 ━━━━━━━━━━━━━━━━━━━━ 12s 44ms/step - accuracy: 0.7911 - loss: 0.5196 789/1073 ━━━━━━━━━━━━━━━━━━━━ 12s 44ms/step - accuracy: 0.7911 - loss: 0.5196 790/1073 ━━━━━━━━━━━━━━━━━━━━ 12s 44ms/step - accuracy: 0.7911 - loss: 0.5196 792/1073 ━━━━━━━━━━━━━━━━━━━━ 12s 44ms/step - accuracy: 0.7911 - loss: 0.5196 793/1073 ━━━━━━━━━━━━━━━━━━━━ 12s 44ms/step - accuracy: 0.7911 - loss: 0.5196 795/1073 ━━━━━━━━━━━━━━━━━━━━ 12s 44ms/step - accuracy: 0.7911 - loss: 0.5196 797/1073 ━━━━━━━━━━━━━━━━━━━━ 12s 44ms/step - accuracy: 0.7911 - loss: 0.5196 799/1073 ━━━━━━━━━━━━━━━━━━━━ 12s 44ms/step - accuracy: 0.7911 - loss: 0.5196 801/1073 ━━━━━━━━━━━━━━━━━━━━ 11s 44ms/step - accuracy: 0.7911 - loss: 0.5196 803/1073 ━━━━━━━━━━━━━━━━━━━━ 11s 44ms/step - accuracy: 0.7911 - loss: 0.5196 805/1073 ━━━━━━━━━━━━━━━━━━━━ 11s 44ms/step - accuracy: 0.7911 - loss: 0.5196 807/1073 ━━━━━━━━━━━━━━━━━━━━ 11s 44ms/step - accuracy: 0.7911 - loss: 0.5196 809/1073 ━━━━━━━━━━━━━━━━━━━━ 11s 44ms/step - accuracy: 0.7911 - loss: 0.5196 811/1073 ━━━━━━━━━━━━━━━━━━━━ 11s 44ms/step - accuracy: 0.7911 - loss: 0.5196 813/1073 ━━━━━━━━━━━━━━━━━━━━ 11s 44ms/step - accuracy: 0.7911 - loss: 0.5197 815/1073 ━━━━━━━━━━━━━━━━━━━━ 11s 44ms/step - accuracy: 0.7911 - loss: 0.5197 817/1073 ━━━━━━━━━━━━━━━━━━━━ 11s 44ms/step - accuracy: 0.7911 - loss: 0.5197 818/1073 ━━━━━━━━━━━━━━━━━━━━ 11s 44ms/step - accuracy: 0.7911 - loss: 0.5197 820/1073 ━━━━━━━━━━━━━━━━━━━━ 11s 44ms/step - accuracy: 0.7911 - loss: 0.5197 821/1073 ━━━━━━━━━━━━━━━━━━━━ 11s 44ms/step - accuracy: 0.7911 - loss: 0.5197 823/1073 ━━━━━━━━━━━━━━━━━━━━ 11s 44ms/step - accuracy: 0.7911 - loss: 0.5197 825/1073 ━━━━━━━━━━━━━━━━━━━━ 10s 44ms/step - accuracy: 0.7911 - loss: 0.5197 827/1073 ━━━━━━━━━━━━━━━━━━━━ 10s 44ms/step - accuracy: 0.7911 - loss: 0.5197 829/1073 ━━━━━━━━━━━━━━━━━━━━ 10s 44ms/step - accuracy: 0.7911 - loss: 0.5197 831/1073 ━━━━━━━━━━━━━━━━━━━━ 10s 44ms/step - accuracy: 0.7911 - loss: 0.5197 832/1073 ━━━━━━━━━━━━━━━━━━━━ 10s 44ms/step - accuracy: 0.7911 - loss: 0.5197 834/1073 ━━━━━━━━━━━━━━━━━━━━ 10s 44ms/step - accuracy: 0.7911 - loss: 0.5197 835/1073 ━━━━━━━━━━━━━━━━━━━━ 10s 44ms/step - accuracy: 0.7911 - loss: 0.5197 837/1073 ━━━━━━━━━━━━━━━━━━━━ 10s 44ms/step - accuracy: 0.7911 - loss: 0.5197 838/1073 ━━━━━━━━━━━━━━━━━━━━ 10s 44ms/step - accuracy: 0.7911 - loss: 0.5197 840/1073 ━━━━━━━━━━━━━━━━━━━━ 10s 44ms/step - accuracy: 0.7911 - loss: 0.5198 842/1073 ━━━━━━━━━━━━━━━━━━━━ 10s 44ms/step - accuracy: 0.7910 - loss: 0.5198 844/1073 ━━━━━━━━━━━━━━━━━━━━ 10s 44ms/step - accuracy: 0.7910 - loss: 0.5198 846/1073 ━━━━━━━━━━━━━━━━━━━━ 10s 44ms/step - accuracy: 0.7910 - loss: 0.5198 848/1073 ━━━━━━━━━━━━━━━━━━━━ 9s 44ms/step - accuracy: 0.7910 - loss: 0.5198 850/1073 ━━━━━━━━━━━━━━━━━━━━ 9s 44ms/step - accuracy: 0.7910 - loss: 0.5198 852/1073 ━━━━━━━━━━━━━━━━━━━━ 9s 44ms/step - accuracy: 0.7910 - loss: 0.5198 854/1073 ━━━━━━━━━━━━━━━━━━━━ 9s 44ms/step - accuracy: 0.7910 - loss: 0.5198 856/1073 ━━━━━━━━━━━━━━━━━━━━ 9s 44ms/step - accuracy: 0.7910 - loss: 0.5198 858/1073 ━━━━━━━━━━━━━━━━━━━━ 9s 44ms/step - accuracy: 0.7910 - loss: 0.5198 860/1073 ━━━━━━━━━━━━━━━━━━━━ 9s 44ms/step - accuracy: 0.7910 - loss: 0.5198 862/1073 ━━━━━━━━━━━━━━━━━━━━ 9s 44ms/step - accuracy: 0.7910 - loss: 0.5198 863/1073 ━━━━━━━━━━━━━━━━━━━━ 9s 44ms/step - accuracy: 0.7910 - loss: 0.5198 865/1073 ━━━━━━━━━━━━━━━━━━━━ 9s 44ms/step - accuracy: 0.7910 - loss: 0.5198 867/1073 ━━━━━━━━━━━━━━━━━━━━ 9s 44ms/step - accuracy: 0.7910 - loss: 0.5199 869/1073 ━━━━━━━━━━━━━━━━━━━━ 9s 44ms/step - accuracy: 0.7910 - loss: 0.5199 871/1073 ━━━━━━━━━━━━━━━━━━━━ 8s 44ms/step - accuracy: 0.7910 - loss: 0.5199 872/1073 ━━━━━━━━━━━━━━━━━━━━ 8s 44ms/step - accuracy: 0.7910 - loss: 0.5199 874/1073 ━━━━━━━━━━━━━━━━━━━━ 8s 44ms/step - accuracy: 0.7910 - loss: 0.5199 875/1073 ━━━━━━━━━━━━━━━━━━━━ 8s 44ms/step - accuracy: 0.7910 - loss: 0.5199 877/1073 ━━━━━━━━━━━━━━━━━━━━ 8s 44ms/step - accuracy: 0.7910 - loss: 0.5199 878/1073 ━━━━━━━━━━━━━━━━━━━━ 8s 44ms/step - accuracy: 0.7910 - loss: 0.5199 880/1073 ━━━━━━━━━━━━━━━━━━━━ 8s 44ms/step - accuracy: 0.7910 - loss: 0.5199 882/1073 ━━━━━━━━━━━━━━━━━━━━ 8s 44ms/step - accuracy: 0.7910 - loss: 0.5199 884/1073 ━━━━━━━━━━━━━━━━━━━━ 8s 44ms/step - accuracy: 0.7910 - loss: 0.5199 886/1073 ━━━━━━━━━━━━━━━━━━━━ 8s 44ms/step - accuracy: 0.7910 - loss: 0.5199 888/1073 ━━━━━━━━━━━━━━━━━━━━ 8s 44ms/step - accuracy: 0.7910 - loss: 0.5199 890/1073 ━━━━━━━━━━━━━━━━━━━━ 8s 44ms/step - accuracy: 0.7910 - loss: 0.5199 892/1073 ━━━━━━━━━━━━━━━━━━━━ 8s 44ms/step - accuracy: 0.7910 - loss: 0.5199 894/1073 ━━━━━━━━━━━━━━━━━━━━ 7s 44ms/step - accuracy: 0.7910 - loss: 0.5199 896/1073 ━━━━━━━━━━━━━━━━━━━━ 7s 44ms/step - accuracy: 0.7910 - loss: 0.5199 898/1073 ━━━━━━━━━━━━━━━━━━━━ 7s 44ms/step - accuracy: 0.7910 - loss: 0.5200 900/1073 ━━━━━━━━━━━━━━━━━━━━ 7s 44ms/step - accuracy: 0.7910 - loss: 0.5200 902/1073 ━━━━━━━━━━━━━━━━━━━━ 7s 44ms/step - accuracy: 0.7909 - loss: 0.5200 904/1073 ━━━━━━━━━━━━━━━━━━━━ 7s 44ms/step - accuracy: 0.7909 - loss: 0.5200 905/1073 ━━━━━━━━━━━━━━━━━━━━ 7s 44ms/step - accuracy: 0.7909 - loss: 0.5200 907/1073 ━━━━━━━━━━━━━━━━━━━━ 7s 44ms/step - accuracy: 0.7909 - loss: 0.5200 908/1073 ━━━━━━━━━━━━━━━━━━━━ 7s 44ms/step - accuracy: 0.7909 - loss: 0.5200 910/1073 ━━━━━━━━━━━━━━━━━━━━ 7s 44ms/step - accuracy: 0.7909 - loss: 0.5200 912/1073 ━━━━━━━━━━━━━━━━━━━━ 7s 44ms/step - accuracy: 0.7909 - loss: 0.5200 914/1073 ━━━━━━━━━━━━━━━━━━━━ 7s 44ms/step - accuracy: 0.7909 - loss: 0.5200 916/1073 ━━━━━━━━━━━━━━━━━━━━ 6s 44ms/step - accuracy: 0.7909 - loss: 0.5200 918/1073 ━━━━━━━━━━━━━━━━━━━━ 6s 44ms/step - accuracy: 0.7909 - loss: 0.5200 920/1073 ━━━━━━━━━━━━━━━━━━━━ 6s 44ms/step - accuracy: 0.7909 - loss: 0.5200 921/1073 ━━━━━━━━━━━━━━━━━━━━ 6s 44ms/step - accuracy: 0.7909 - loss: 0.5200 923/1073 ━━━━━━━━━━━━━━━━━━━━ 6s 44ms/step - accuracy: 0.7909 - loss: 0.5200 924/1073 ━━━━━━━━━━━━━━━━━━━━ 6s 44ms/step - accuracy: 0.7909 - loss: 0.5200 926/1073 ━━━━━━━━━━━━━━━━━━━━ 6s 44ms/step - accuracy: 0.7909 - loss: 0.5200 927/1073 ━━━━━━━━━━━━━━━━━━━━ 6s 44ms/step - accuracy: 0.7909 - loss: 0.5200 929/1073 ━━━━━━━━━━━━━━━━━━━━ 6s 44ms/step - accuracy: 0.7909 - loss: 0.5200 930/1073 ━━━━━━━━━━━━━━━━━━━━ 6s 44ms/step - accuracy: 0.7909 - loss: 0.5200 932/1073 ━━━━━━━━━━━━━━━━━━━━ 6s 44ms/step - accuracy: 0.7909 - loss: 0.5201 934/1073 ━━━━━━━━━━━━━━━━━━━━ 6s 44ms/step - accuracy: 0.7909 - loss: 0.5201 936/1073 ━━━━━━━━━━━━━━━━━━━━ 6s 44ms/step - accuracy: 0.7909 - loss: 0.5201 938/1073 ━━━━━━━━━━━━━━━━━━━━ 5s 44ms/step - accuracy: 0.7909 - loss: 0.5201 940/1073 ━━━━━━━━━━━━━━━━━━━━ 5s 44ms/step - accuracy: 0.7909 - loss: 0.5201 942/1073 ━━━━━━━━━━━━━━━━━━━━ 5s 44ms/step - accuracy: 0.7909 - loss: 0.5201 944/1073 ━━━━━━━━━━━━━━━━━━━━ 5s 44ms/step - accuracy: 0.7909 - loss: 0.5201 945/1073 ━━━━━━━━━━━━━━━━━━━━ 5s 44ms/step - accuracy: 0.7909 - loss: 0.5201 947/1073 ━━━━━━━━━━━━━━━━━━━━ 5s 44ms/step - accuracy: 0.7909 - loss: 0.5201 949/1073 ━━━━━━━━━━━━━━━━━━━━ 5s 44ms/step - accuracy: 0.7909 - loss: 0.5201 951/1073 ━━━━━━━━━━━━━━━━━━━━ 5s 44ms/step - accuracy: 0.7909 - loss: 0.5201 953/1073 ━━━━━━━━━━━━━━━━━━━━ 5s 44ms/step - accuracy: 0.7909 - loss: 0.5201 955/1073 ━━━━━━━━━━━━━━━━━━━━ 5s 44ms/step - accuracy: 0.7909 - loss: 0.5201 957/1073 ━━━━━━━━━━━━━━━━━━━━ 5s 44ms/step - accuracy: 0.7909 - loss: 0.5201 958/1073 ━━━━━━━━━━━━━━━━━━━━ 5s 44ms/step - accuracy: 0.7909 - loss: 0.5201 960/1073 ━━━━━━━━━━━━━━━━━━━━ 5s 44ms/step - accuracy: 0.7909 - loss: 0.5201 961/1073 ━━━━━━━━━━━━━━━━━━━━ 4s 44ms/step - accuracy: 0.7909 - loss: 0.5201 963/1073 ━━━━━━━━━━━━━━━━━━━━ 4s 44ms/step - accuracy: 0.7909 - loss: 0.5201 965/1073 ━━━━━━━━━━━━━━━━━━━━ 4s 44ms/step - accuracy: 0.7909 - loss: 0.5201 967/1073 ━━━━━━━━━━━━━━━━━━━━ 4s 44ms/step - accuracy: 0.7909 - loss: 0.5201 969/1073 ━━━━━━━━━━━━━━━━━━━━ 4s 44ms/step - accuracy: 0.7909 - loss: 0.5201 971/1073 ━━━━━━━━━━━━━━━━━━━━ 4s 44ms/step - accuracy: 0.7909 - loss: 0.5201 973/1073 ━━━━━━━━━━━━━━━━━━━━ 4s 44ms/step - accuracy: 0.7909 - loss: 0.5202 975/1073 ━━━━━━━━━━━━━━━━━━━━ 4s 44ms/step - accuracy: 0.7909 - loss: 0.5202 977/1073 ━━━━━━━━━━━━━━━━━━━━ 4s 45ms/step - accuracy: 0.7908 - loss: 0.5202 979/1073 ━━━━━━━━━━━━━━━━━━━━ 4s 45ms/step - accuracy: 0.7908 - loss: 0.5202 980/1073 ━━━━━━━━━━━━━━━━━━━━ 4s 45ms/step - accuracy: 0.7908 - loss: 0.5202 982/1073 ━━━━━━━━━━━━━━━━━━━━ 4s 45ms/step - accuracy: 0.7908 - loss: 0.5202 984/1073 ━━━━━━━━━━━━━━━━━━━━ 3s 45ms/step - accuracy: 0.7908 - loss: 0.5202 986/1073 ━━━━━━━━━━━━━━━━━━━━ 3s 45ms/step - accuracy: 0.7908 - loss: 0.5202 988/1073 ━━━━━━━━━━━━━━━━━━━━ 3s 45ms/step - accuracy: 0.7908 - loss: 0.5202 989/1073 ━━━━━━━━━━━━━━━━━━━━ 3s 45ms/step - accuracy: 0.7908 - loss: 0.5202 991/1073 ━━━━━━━━━━━━━━━━━━━━ 3s 45ms/step - accuracy: 0.7908 - loss: 0.5202 993/1073 ━━━━━━━━━━━━━━━━━━━━ 3s 45ms/step - accuracy: 0.7908 - loss: 0.5202 995/1073 ━━━━━━━━━━━━━━━━━━━━ 3s 45ms/step - accuracy: 0.7908 - loss: 0.5202 997/1073 ━━━━━━━━━━━━━━━━━━━━ 3s 45ms/step - accuracy: 0.7908 - loss: 0.5202 999/1073 ━━━━━━━━━━━━━━━━━━━━ 3s 45ms/step - accuracy: 0.7908 - loss: 0.52021001/1073 ━━━━━━━━━━━━━━━━━━━━ 3s 45ms/step - accuracy: 0.7908 - loss: 0.52021003/1073 ━━━━━━━━━━━━━━━━━━━━ 3s 45ms/step - accuracy: 0.7908 - loss: 0.52021005/1073 ━━━━━━━━━━━━━━━━━━━━ 3s 45ms/step - accuracy: 0.7908 - loss: 0.52021007/1073 ━━━━━━━━━━━━━━━━━━━━ 2s 45ms/step - accuracy: 0.7908 - loss: 0.52021009/1073 ━━━━━━━━━━━━━━━━━━━━ 2s 45ms/step - accuracy: 0.7908 - loss: 0.52021011/1073 ━━━━━━━━━━━━━━━━━━━━ 2s 45ms/step - accuracy: 0.7908 - loss: 0.52021013/1073 ━━━━━━━━━━━━━━━━━━━━ 2s 45ms/step - accuracy: 0.7908 - loss: 0.52021015/1073 ━━━━━━━━━━━━━━━━━━━━ 2s 45ms/step - accuracy: 0.7908 - loss: 0.52031016/1073 ━━━━━━━━━━━━━━━━━━━━ 2s 45ms/step - accuracy: 0.7908 - loss: 0.52031018/1073 ━━━━━━━━━━━━━━━━━━━━ 2s 45ms/step - accuracy: 0.7908 - loss: 0.52031020/1073 ━━━━━━━━━━━━━━━━━━━━ 2s 45ms/step - accuracy: 0.7908 - loss: 0.52031022/1073 ━━━━━━━━━━━━━━━━━━━━ 2s 45ms/step - accuracy: 0.7908 - loss: 0.52031024/1073 ━━━━━━━━━━━━━━━━━━━━ 2s 45ms/step - accuracy: 0.7908 - loss: 0.52031026/1073 ━━━━━━━━━━━━━━━━━━━━ 2s 45ms/step - accuracy: 0.7908 - loss: 0.52031028/1073 ━━━━━━━━━━━━━━━━━━━━ 2s 45ms/step - accuracy: 0.7908 - loss: 0.52031030/1073 ━━━━━━━━━━━━━━━━━━━━ 1s 45ms/step - accuracy: 0.7908 - loss: 0.52031031/1073 ━━━━━━━━━━━━━━━━━━━━ 1s 45ms/step - accuracy: 0.7908 - loss: 0.52031033/1073 ━━━━━━━━━━━━━━━━━━━━ 1s 45ms/step - accuracy: 0.7908 - loss: 0.52031034/1073 ━━━━━━━━━━━━━━━━━━━━ 1s 45ms/step - accuracy: 0.7908 - loss: 0.52031036/1073 ━━━━━━━━━━━━━━━━━━━━ 1s 45ms/step - accuracy: 0.7908 - loss: 0.52031037/1073 ━━━━━━━━━━━━━━━━━━━━ 1s 45ms/step - accuracy: 0.7908 - loss: 0.52031039/1073 ━━━━━━━━━━━━━━━━━━━━ 1s 45ms/step - accuracy: 0.7908 - loss: 0.52031040/1073 ━━━━━━━━━━━━━━━━━━━━ 1s 45ms/step - accuracy: 0.7908 - loss: 0.52031042/1073 ━━━━━━━━━━━━━━━━━━━━ 1s 45ms/step - accuracy: 0.7908 - loss: 0.52031044/1073 ━━━━━━━━━━━━━━━━━━━━ 1s 45ms/step - accuracy: 0.7908 - loss: 0.52031046/1073 ━━━━━━━━━━━━━━━━━━━━ 1s 45ms/step - accuracy: 0.7908 - loss: 0.52031048/1073 ━━━━━━━━━━━━━━━━━━━━ 1s 45ms/step - accuracy: 0.7908 - loss: 0.52031050/1073 ━━━━━━━━━━━━━━━━━━━━ 1s 45ms/step - accuracy: 0.7908 - loss: 0.52031052/1073 ━━━━━━━━━━━━━━━━━━━━ 0s 45ms/step - accuracy: 0.7908 - loss: 0.52031054/1073 ━━━━━━━━━━━━━━━━━━━━ 0s 45ms/step - accuracy: 0.7908 - loss: 0.52031055/1073 ━━━━━━━━━━━━━━━━━━━━ 0s 45ms/step - accuracy: 0.7908 - loss: 0.52031057/1073 ━━━━━━━━━━━━━━━━━━━━ 0s 45ms/step - accuracy: 0.7908 - loss: 0.52031058/1073 ━━━━━━━━━━━━━━━━━━━━ 0s 45ms/step - accuracy: 0.7908 - loss: 0.52031060/1073 ━━━━━━━━━━━━━━━━━━━━ 0s 45ms/step - accuracy: 0.7908 - loss: 0.52031061/1073 ━━━━━━━━━━━━━━━━━━━━ 0s 45ms/step - accuracy: 0.7908 - loss: 0.52031063/1073 ━━━━━━━━━━━━━━━━━━━━ 0s 45ms/step - accuracy: 0.7908 - loss: 0.52031065/1073 ━━━━━━━━━━━━━━━━━━━━ 0s 45ms/step - accuracy: 0.7908 - loss: 0.52041067/1073 ━━━━━━━━━━━━━━━━━━━━ 0s 45ms/step - accuracy: 0.7908 - loss: 0.52041069/1073 ━━━━━━━━━━━━━━━━━━━━ 0s 45ms/step - accuracy: 0.7908 - loss: 0.52041071/1073 ━━━━━━━━━━━━━━━━━━━━ 0s 45ms/step - accuracy: 0.7908 - loss: 0.52041073/1073 ━━━━━━━━━━━━━━━━━━━━ 0s 45ms/step - accuracy: 0.7908 - loss: 0.52041073/1073 ━━━━━━━━━━━━━━━━━━━━ 49s 45ms/step - accuracy: 0.7899 - loss: 0.5223 - val_accuracy: 0.7750 - val_loss: 0.5572Epoch 5/5 1/1073 ━━━━━━━━━━━━━━━━━━━━ 22:43 1s/step - accuracy: 0.8027 - loss: 0.4734 3/1073 ━━━━━━━━━━━━━━━━━━━━ 50s 48ms/step - accuracy: 0.8075 - loss: 0.4693 5/1073 ━━━━━━━━━━━━━━━━━━━━ 50s 48ms/step - accuracy: 0.8120 - loss: 0.4661 7/1073 ━━━━━━━━━━━━━━━━━━━━ 50s 48ms/step - accuracy: 0.8134 - loss: 0.4658 8/1073 ━━━━━━━━━━━━━━━━━━━━ 51s 48ms/step - accuracy: 0.8139 - loss: 0.4654 10/1073 ━━━━━━━━━━━━━━━━━━━━ 50s 48ms/step - accuracy: 0.8147 - loss: 0.4649 11/1073 ━━━━━━━━━━━━━━━━━━━━ 51s 48ms/step - accuracy: 0.8147 - loss: 0.4651 13/1073 ━━━━━━━━━━━━━━━━━━━━ 50s 48ms/step - accuracy: 0.8148 - loss: 0.4650 15/1073 ━━━━━━━━━━━━━━━━━━━━ 50s 48ms/step - accuracy: 0.8145 - loss: 0.4652 17/1073 ━━━━━━━━━━━━━━━━━━━━ 50s 48ms/step - accuracy: 0.8143 - loss: 0.4653 19/1073 ━━━━━━━━━━━━━━━━━━━━ 50s 48ms/step - accuracy: 0.8141 - loss: 0.4655 20/1073 ━━━━━━━━━━━━━━━━━━━━ 50s 48ms/step - accuracy: 0.8140 - loss: 0.4655 22/1073 ━━━━━━━━━━━━━━━━━━━━ 50s 48ms/step - accuracy: 0.8140 - loss: 0.4655 24/1073 ━━━━━━━━━━━━━━━━━━━━ 50s 48ms/step - accuracy: 0.8139 - loss: 0.4655 26/1073 ━━━━━━━━━━━━━━━━━━━━ 49s 47ms/step - accuracy: 0.8139 - loss: 0.4656 28/1073 ━━━━━━━━━━━━━━━━━━━━ 48s 47ms/step - accuracy: 0.8139 - loss: 0.4659 30/1073 ━━━━━━━━━━━━━━━━━━━━ 48s 46ms/step - accuracy: 0.8139 - loss: 0.4661 32/1073 ━━━━━━━━━━━━━━━━━━━━ 47s 46ms/step - accuracy: 0.8139 - loss: 0.4663 34/1073 ━━━━━━━━━━━━━━━━━━━━ 47s 46ms/step - accuracy: 0.8139 - loss: 0.4664 36/1073 ━━━━━━━━━━━━━━━━━━━━ 47s 46ms/step - accuracy: 0.8138 - loss: 0.4666 38/1073 ━━━━━━━━━━━━━━━━━━━━ 47s 46ms/step - accuracy: 0.8137 - loss: 0.4669 40/1073 ━━━━━━━━━━━━━━━━━━━━ 47s 46ms/step - accuracy: 0.8136 - loss: 0.4673 42/1073 ━━━━━━━━━━━━━━━━━━━━ 47s 46ms/step - accuracy: 0.8135 - loss: 0.4676 44/1073 ━━━━━━━━━━━━━━━━━━━━ 46s 45ms/step - accuracy: 0.8134 - loss: 0.4679 46/1073 ━━━━━━━━━━━━━━━━━━━━ 46s 45ms/step - accuracy: 0.8133 - loss: 0.4682 48/1073 ━━━━━━━━━━━━━━━━━━━━ 46s 45ms/step - accuracy: 0.8132 - loss: 0.4685 50/1073 ━━━━━━━━━━━━━━━━━━━━ 45s 45ms/step - accuracy: 0.8132 - loss: 0.4687 52/1073 ━━━━━━━━━━━━━━━━━━━━ 45s 45ms/step - accuracy: 0.8131 - loss: 0.4689 54/1073 ━━━━━━━━━━━━━━━━━━━━ 45s 44ms/step - accuracy: 0.8130 - loss: 0.4691 56/1073 ━━━━━━━━━━━━━━━━━━━━ 45s 44ms/step - accuracy: 0.8130 - loss: 0.4692 58/1073 ━━━━━━━━━━━━━━━━━━━━ 44s 44ms/step - accuracy: 0.8129 - loss: 0.4694 60/1073 ━━━━━━━━━━━━━━━━━━━━ 44s 44ms/step - accuracy: 0.8128 - loss: 0.4695 62/1073 ━━━━━━━━━━━━━━━━━━━━ 44s 44ms/step - accuracy: 0.8128 - loss: 0.4696 64/1073 ━━━━━━━━━━━━━━━━━━━━ 44s 44ms/step - accuracy: 0.8127 - loss: 0.4698 66/1073 ━━━━━━━━━━━━━━━━━━━━ 43s 44ms/step - accuracy: 0.8126 - loss: 0.4699 68/1073 ━━━━━━━━━━━━━━━━━━━━ 43s 44ms/step - accuracy: 0.8126 - loss: 0.4700 70/1073 ━━━━━━━━━━━━━━━━━━━━ 43s 44ms/step - accuracy: 0.8126 - loss: 0.4700 72/1073 ━━━━━━━━━━━━━━━━━━━━ 43s 44ms/step - accuracy: 0.8125 - loss: 0.4701 74/1073 ━━━━━━━━━━━━━━━━━━━━ 43s 44ms/step - accuracy: 0.8125 - loss: 0.4702 76/1073 ━━━━━━━━━━━━━━━━━━━━ 43s 44ms/step - accuracy: 0.8124 - loss: 0.4703 78/1073 ━━━━━━━━━━━━━━━━━━━━ 43s 44ms/step - accuracy: 0.8124 - loss: 0.4704 80/1073 ━━━━━━━━━━━━━━━━━━━━ 43s 44ms/step - accuracy: 0.8123 - loss: 0.4704 82/1073 ━━━━━━━━━━━━━━━━━━━━ 43s 44ms/step - accuracy: 0.8123 - loss: 0.4705 84/1073 ━━━━━━━━━━━━━━━━━━━━ 43s 44ms/step - accuracy: 0.8122 - loss: 0.4706 86/1073 ━━━━━━━━━━━━━━━━━━━━ 43s 44ms/step - accuracy: 0.8122 - loss: 0.4707 88/1073 ━━━━━━━━━━━━━━━━━━━━ 43s 44ms/step - accuracy: 0.8121 - loss: 0.4707 90/1073 ━━━━━━━━━━━━━━━━━━━━ 43s 44ms/step - accuracy: 0.8121 - loss: 0.4708 92/1073 ━━━━━━━━━━━━━━━━━━━━ 42s 44ms/step - accuracy: 0.8121 - loss: 0.4709 94/1073 ━━━━━━━━━━━━━━━━━━━━ 42s 44ms/step - accuracy: 0.8120 - loss: 0.4710 96/1073 ━━━━━━━━━━━━━━━━━━━━ 42s 44ms/step - accuracy: 0.8120 - loss: 0.4710 98/1073 ━━━━━━━━━━━━━━━━━━━━ 42s 44ms/step - accuracy: 0.8119 - loss: 0.4711 100/1073 ━━━━━━━━━━━━━━━━━━━━ 42s 43ms/step - accuracy: 0.8119 - loss: 0.4712 102/1073 ━━━━━━━━━━━━━━━━━━━━ 42s 43ms/step - accuracy: 0.8119 - loss: 0.4712 104/1073 ━━━━━━━━━━━━━━━━━━━━ 41s 43ms/step - accuracy: 0.8119 - loss: 0.4713 106/1073 ━━━━━━━━━━━━━━━━━━━━ 41s 43ms/step - accuracy: 0.8119 - loss: 0.4713 108/1073 ━━━━━━━━━━━━━━━━━━━━ 41s 43ms/step - accuracy: 0.8118 - loss: 0.4714 110/1073 ━━━━━━━━━━━━━━━━━━━━ 41s 43ms/step - accuracy: 0.8118 - loss: 0.4714 112/1073 ━━━━━━━━━━━━━━━━━━━━ 41s 43ms/step - accuracy: 0.8118 - loss: 0.4715 114/1073 ━━━━━━━━━━━━━━━━━━━━ 41s 43ms/step - accuracy: 0.8118 - loss: 0.4716 116/1073 ━━━━━━━━━━━━━━━━━━━━ 41s 43ms/step - accuracy: 0.8118 - loss: 0.4716 118/1073 ━━━━━━━━━━━━━━━━━━━━ 41s 43ms/step - accuracy: 0.8117 - loss: 0.4717 120/1073 ━━━━━━━━━━━━━━━━━━━━ 40s 43ms/step - accuracy: 0.8117 - loss: 0.4718 122/1073 ━━━━━━━━━━━━━━━━━━━━ 40s 43ms/step - accuracy: 0.8117 - loss: 0.4718 124/1073 ━━━━━━━━━━━━━━━━━━━━ 40s 43ms/step - accuracy: 0.8117 - loss: 0.4719 126/1073 ━━━━━━━━━━━━━━━━━━━━ 40s 43ms/step - accuracy: 0.8116 - loss: 0.4720 128/1073 ━━━━━━━━━━━━━━━━━━━━ 40s 43ms/step - accuracy: 0.8116 - loss: 0.4720 130/1073 ━━━━━━━━━━━━━━━━━━━━ 40s 43ms/step - accuracy: 0.8116 - loss: 0.4721 132/1073 ━━━━━━━━━━━━━━━━━━━━ 40s 43ms/step - accuracy: 0.8116 - loss: 0.4722 134/1073 ━━━━━━━━━━━━━━━━━━━━ 39s 43ms/step - accuracy: 0.8115 - loss: 0.4722 136/1073 ━━━━━━━━━━━━━━━━━━━━ 39s 43ms/step - accuracy: 0.8115 - loss: 0.4723 138/1073 ━━━━━━━━━━━━━━━━━━━━ 39s 42ms/step - accuracy: 0.8115 - loss: 0.4724 140/1073 ━━━━━━━━━━━━━━━━━━━━ 39s 42ms/step - accuracy: 0.8115 - loss: 0.4725 142/1073 ━━━━━━━━━━━━━━━━━━━━ 39s 42ms/step - accuracy: 0.8114 - loss: 0.4725 144/1073 ━━━━━━━━━━━━━━━━━━━━ 39s 42ms/step - accuracy: 0.8114 - loss: 0.4726 146/1073 ━━━━━━━━━━━━━━━━━━━━ 39s 42ms/step - accuracy: 0.8114 - loss: 0.4726 148/1073 ━━━━━━━━━━━━━━━━━━━━ 39s 42ms/step - accuracy: 0.8114 - loss: 0.4727 150/1073 ━━━━━━━━━━━━━━━━━━━━ 39s 42ms/step - accuracy: 0.8114 - loss: 0.4727 152/1073 ━━━━━━━━━━━━━━━━━━━━ 39s 42ms/step - accuracy: 0.8114 - loss: 0.4728 154/1073 ━━━━━━━━━━━━━━━━━━━━ 39s 43ms/step - accuracy: 0.8114 - loss: 0.4728 156/1073 ━━━━━━━━━━━━━━━━━━━━ 39s 43ms/step - accuracy: 0.8114 - loss: 0.4728 158/1073 ━━━━━━━━━━━━━━━━━━━━ 39s 43ms/step - accuracy: 0.8114 - loss: 0.4729 160/1073 ━━━━━━━━━━━━━━━━━━━━ 38s 43ms/step - accuracy: 0.8114 - loss: 0.4729 162/1073 ━━━━━━━━━━━━━━━━━━━━ 38s 43ms/step - accuracy: 0.8114 - loss: 0.4730 164/1073 ━━━━━━━━━━━━━━━━━━━━ 38s 43ms/step - accuracy: 0.8113 - loss: 0.4730 166/1073 ━━━━━━━━━━━━━━━━━━━━ 38s 43ms/step - accuracy: 0.8113 - loss: 0.4731 168/1073 ━━━━━━━━━━━━━━━━━━━━ 38s 43ms/step - accuracy: 0.8113 - loss: 0.4731 170/1073 ━━━━━━━━━━━━━━━━━━━━ 38s 43ms/step - accuracy: 0.8113 - loss: 0.4731 172/1073 ━━━━━━━━━━━━━━━━━━━━ 38s 43ms/step - accuracy: 0.8113 - loss: 0.4732 174/1073 ━━━━━━━━━━━━━━━━━━━━ 38s 43ms/step - accuracy: 0.8113 - loss: 0.4732 176/1073 ━━━━━━━━━━━━━━━━━━━━ 38s 43ms/step - accuracy: 0.8113 - loss: 0.4733 178/1073 ━━━━━━━━━━━━━━━━━━━━ 38s 43ms/step - accuracy: 0.8113 - loss: 0.4733 180/1073 ━━━━━━━━━━━━━━━━━━━━ 38s 43ms/step - accuracy: 0.8113 - loss: 0.4734 182/1073 ━━━━━━━━━━━━━━━━━━━━ 38s 43ms/step - accuracy: 0.8113 - loss: 0.4734 184/1073 ━━━━━━━━━━━━━━━━━━━━ 38s 43ms/step - accuracy: 0.8113 - loss: 0.4734 186/1073 ━━━━━━━━━━━━━━━━━━━━ 38s 43ms/step - accuracy: 0.8112 - loss: 0.4735 188/1073 ━━━━━━━━━━━━━━━━━━━━ 38s 43ms/step - accuracy: 0.8112 - loss: 0.4735 190/1073 ━━━━━━━━━━━━━━━━━━━━ 38s 43ms/step - accuracy: 0.8112 - loss: 0.4736 192/1073 ━━━━━━━━━━━━━━━━━━━━ 38s 43ms/step - accuracy: 0.8112 - loss: 0.4736 194/1073 ━━━━━━━━━━━━━━━━━━━━ 38s 43ms/step - accuracy: 0.8112 - loss: 0.4737 196/1073 ━━━━━━━━━━━━━━━━━━━━ 37s 43ms/step - accuracy: 0.8112 - loss: 0.4737 198/1073 ━━━━━━━━━━━━━━━━━━━━ 37s 43ms/step - accuracy: 0.8112 - loss: 0.4738 200/1073 ━━━━━━━━━━━━━━━━━━━━ 37s 43ms/step - accuracy: 0.8112 - loss: 0.4738 202/1073 ━━━━━━━━━━━━━━━━━━━━ 37s 43ms/step - accuracy: 0.8111 - loss: 0.4738 204/1073 ━━━━━━━━━━━━━━━━━━━━ 37s 43ms/step - accuracy: 0.8111 - loss: 0.4739 206/1073 ━━━━━━━━━━━━━━━━━━━━ 37s 43ms/step - accuracy: 0.8111 - loss: 0.4739 208/1073 ━━━━━━━━━━━━━━━━━━━━ 37s 43ms/step - accuracy: 0.8111 - loss: 0.4740 210/1073 ━━━━━━━━━━━━━━━━━━━━ 37s 43ms/step - accuracy: 0.8111 - loss: 0.4740 212/1073 ━━━━━━━━━━━━━━━━━━━━ 37s 43ms/step - accuracy: 0.8111 - loss: 0.4740 214/1073 ━━━━━━━━━━━━━━━━━━━━ 36s 43ms/step - accuracy: 0.8111 - loss: 0.4741 216/1073 ━━━━━━━━━━━━━━━━━━━━ 36s 43ms/step - accuracy: 0.8111 - loss: 0.4741 218/1073 ━━━━━━━━━━━━━━━━━━━━ 36s 43ms/step - accuracy: 0.8111 - loss: 0.4741 220/1073 ━━━━━━━━━━━━━━━━━━━━ 36s 43ms/step - accuracy: 0.8111 - loss: 0.4742 222/1073 ━━━━━━━━━━━━━━━━━━━━ 36s 43ms/step - accuracy: 0.8111 - loss: 0.4742 224/1073 ━━━━━━━━━━━━━━━━━━━━ 36s 43ms/step - accuracy: 0.8111 - loss: 0.4742 226/1073 ━━━━━━━━━━━━━━━━━━━━ 36s 43ms/step - accuracy: 0.8111 - loss: 0.4743 228/1073 ━━━━━━━━━━━━━━━━━━━━ 36s 43ms/step - accuracy: 0.8110 - loss: 0.4743 230/1073 ━━━━━━━━━━━━━━━━━━━━ 36s 43ms/step - accuracy: 0.8110 - loss: 0.4743 232/1073 ━━━━━━━━━━━━━━━━━━━━ 36s 43ms/step - accuracy: 0.8110 - loss: 0.4744 234/1073 ━━━━━━━━━━━━━━━━━━━━ 35s 43ms/step - accuracy: 0.8110 - loss: 0.4744 236/1073 ━━━━━━━━━━━━━━━━━━━━ 35s 43ms/step - accuracy: 0.8110 - loss: 0.4744 238/1073 ━━━━━━━━━━━━━━━━━━━━ 35s 43ms/step - accuracy: 0.8110 - loss: 0.4745 240/1073 ━━━━━━━━━━━━━━━━━━━━ 35s 43ms/step - accuracy: 0.8110 - loss: 0.4745 242/1073 ━━━━━━━━━━━━━━━━━━━━ 35s 43ms/step - accuracy: 0.8110 - loss: 0.4745 244/1073 ━━━━━━━━━━━━━━━━━━━━ 35s 43ms/step - accuracy: 0.8110 - loss: 0.4746 246/1073 ━━━━━━━━━━━━━━━━━━━━ 35s 43ms/step - accuracy: 0.8110 - loss: 0.4746 248/1073 ━━━━━━━━━━━━━━━━━━━━ 35s 43ms/step - accuracy: 0.8110 - loss: 0.4746 250/1073 ━━━━━━━━━━━━━━━━━━━━ 35s 43ms/step - accuracy: 0.8110 - loss: 0.4746 252/1073 ━━━━━━━━━━━━━━━━━━━━ 35s 43ms/step - accuracy: 0.8110 - loss: 0.4747 254/1073 ━━━━━━━━━━━━━━━━━━━━ 34s 43ms/step - accuracy: 0.8109 - loss: 0.4747 256/1073 ━━━━━━━━━━━━━━━━━━━━ 34s 43ms/step - accuracy: 0.8109 - loss: 0.4747 258/1073 ━━━━━━━━━━━━━━━━━━━━ 34s 43ms/step - accuracy: 0.8109 - loss: 0.4748 260/1073 ━━━━━━━━━━━━━━━━━━━━ 34s 43ms/step - accuracy: 0.8109 - loss: 0.4748 262/1073 ━━━━━━━━━━━━━━━━━━━━ 34s 43ms/step - accuracy: 0.8109 - loss: 0.4748 264/1073 ━━━━━━━━━━━━━━━━━━━━ 34s 43ms/step - accuracy: 0.8109 - loss: 0.4748 266/1073 ━━━━━━━━━━━━━━━━━━━━ 34s 43ms/step - accuracy: 0.8109 - loss: 0.4749 268/1073 ━━━━━━━━━━━━━━━━━━━━ 34s 42ms/step - accuracy: 0.8109 - loss: 0.4749 270/1073 ━━━━━━━━━━━━━━━━━━━━ 34s 42ms/step - accuracy: 0.8109 - loss: 0.4749 272/1073 ━━━━━━━━━━━━━━━━━━━━ 34s 42ms/step - accuracy: 0.8109 - loss: 0.4750 274/1073 ━━━━━━━━━━━━━━━━━━━━ 33s 42ms/step - accuracy: 0.8109 - loss: 0.4750 276/1073 ━━━━━━━━━━━━━━━━━━━━ 33s 42ms/step - accuracy: 0.8108 - loss: 0.4750 278/1073 ━━━━━━━━━━━━━━━━━━━━ 33s 42ms/step - accuracy: 0.8108 - loss: 0.4751 280/1073 ━━━━━━━━━━━━━━━━━━━━ 33s 42ms/step - accuracy: 0.8108 - loss: 0.4751 282/1073 ━━━━━━━━━━━━━━━━━━━━ 33s 42ms/step - accuracy: 0.8108 - loss: 0.4751 284/1073 ━━━━━━━━━━━━━━━━━━━━ 33s 42ms/step - accuracy: 0.8108 - loss: 0.4752 286/1073 ━━━━━━━━━━━━━━━━━━━━ 33s 42ms/step - accuracy: 0.8108 - loss: 0.4752 288/1073 ━━━━━━━━━━━━━━━━━━━━ 33s 42ms/step - accuracy: 0.8108 - loss: 0.4752 290/1073 ━━━━━━━━━━━━━━━━━━━━ 33s 42ms/step - accuracy: 0.8108 - loss: 0.4753 292/1073 ━━━━━━━━━━━━━━━━━━━━ 33s 42ms/step - accuracy: 0.8107 - loss: 0.4753 294/1073 ━━━━━━━━━━━━━━━━━━━━ 32s 42ms/step - accuracy: 0.8107 - loss: 0.4753 296/1073 ━━━━━━━━━━━━━━━━━━━━ 32s 42ms/step - accuracy: 0.8107 - loss: 0.4754 298/1073 ━━━━━━━━━━━━━━━━━━━━ 32s 42ms/step - accuracy: 0.8107 - loss: 0.4754 300/1073 ━━━━━━━━━━━━━━━━━━━━ 32s 42ms/step - accuracy: 0.8107 - loss: 0.4754 302/1073 ━━━━━━━━━━━━━━━━━━━━ 32s 42ms/step - accuracy: 0.8107 - loss: 0.4755 304/1073 ━━━━━━━━━━━━━━━━━━━━ 32s 42ms/step - accuracy: 0.8107 - loss: 0.4755 306/1073 ━━━━━━━━━━━━━━━━━━━━ 32s 42ms/step - accuracy: 0.8107 - loss: 0.4755 308/1073 ━━━━━━━━━━━━━━━━━━━━ 32s 42ms/step - accuracy: 0.8107 - loss: 0.4755 310/1073 ━━━━━━━━━━━━━━━━━━━━ 32s 42ms/step - accuracy: 0.8106 - loss: 0.4756 312/1073 ━━━━━━━━━━━━━━━━━━━━ 32s 42ms/step - accuracy: 0.8106 - loss: 0.4756 314/1073 ━━━━━━━━━━━━━━━━━━━━ 31s 42ms/step - accuracy: 0.8106 - loss: 0.4756 316/1073 ━━━━━━━━━━━━━━━━━━━━ 31s 42ms/step - accuracy: 0.8106 - loss: 0.4757 318/1073 ━━━━━━━━━━━━━━━━━━━━ 31s 42ms/step - accuracy: 0.8106 - loss: 0.4757 320/1073 ━━━━━━━━━━━━━━━━━━━━ 31s 42ms/step - accuracy: 0.8106 - loss: 0.4757 322/1073 ━━━━━━━━━━━━━━━━━━━━ 31s 42ms/step - accuracy: 0.8106 - loss: 0.4757 324/1073 ━━━━━━━━━━━━━━━━━━━━ 31s 42ms/step - accuracy: 0.8106 - loss: 0.4758 326/1073 ━━━━━━━━━━━━━━━━━━━━ 31s 42ms/step - accuracy: 0.8106 - loss: 0.4758 328/1073 ━━━━━━━━━━━━━━━━━━━━ 31s 42ms/step - accuracy: 0.8106 - loss: 0.4758 330/1073 ━━━━━━━━━━━━━━━━━━━━ 31s 42ms/step - accuracy: 0.8105 - loss: 0.4758 332/1073 ━━━━━━━━━━━━━━━━━━━━ 31s 42ms/step - accuracy: 0.8105 - loss: 0.4759 334/1073 ━━━━━━━━━━━━━━━━━━━━ 31s 42ms/step - accuracy: 0.8105 - loss: 0.4759 336/1073 ━━━━━━━━━━━━━━━━━━━━ 30s 42ms/step - accuracy: 0.8105 - loss: 0.4759 338/1073 ━━━━━━━━━━━━━━━━━━━━ 30s 42ms/step - accuracy: 0.8105 - loss: 0.4759 340/1073 ━━━━━━━━━━━━━━━━━━━━ 30s 42ms/step - accuracy: 0.8105 - loss: 0.4760 342/1073 ━━━━━━━━━━━━━━━━━━━━ 30s 42ms/step - accuracy: 0.8105 - loss: 0.4760 344/1073 ━━━━━━━━━━━━━━━━━━━━ 30s 42ms/step - accuracy: 0.8105 - loss: 0.4760 346/1073 ━━━━━━━━━━━━━━━━━━━━ 30s 42ms/step - accuracy: 0.8105 - loss: 0.4760 348/1073 ━━━━━━━━━━━━━━━━━━━━ 30s 42ms/step - accuracy: 0.8104 - loss: 0.4761 350/1073 ━━━━━━━━━━━━━━━━━━━━ 30s 42ms/step - accuracy: 0.8104 - loss: 0.4761 352/1073 ━━━━━━━━━━━━━━━━━━━━ 30s 42ms/step - accuracy: 0.8104 - loss: 0.4761 354/1073 ━━━━━━━━━━━━━━━━━━━━ 30s 42ms/step - accuracy: 0.8104 - loss: 0.4761 356/1073 ━━━━━━━━━━━━━━━━━━━━ 30s 42ms/step - accuracy: 0.8104 - loss: 0.4762 358/1073 ━━━━━━━━━━━━━━━━━━━━ 29s 42ms/step - accuracy: 0.8104 - loss: 0.4762 360/1073 ━━━━━━━━━━━━━━━━━━━━ 29s 42ms/step - accuracy: 0.8104 - loss: 0.4762 362/1073 ━━━━━━━━━━━━━━━━━━━━ 29s 42ms/step - accuracy: 0.8104 - loss: 0.4762 364/1073 ━━━━━━━━━━━━━━━━━━━━ 29s 42ms/step - accuracy: 0.8104 - loss: 0.4763 366/1073 ━━━━━━━━━━━━━━━━━━━━ 29s 42ms/step - accuracy: 0.8104 - loss: 0.4763 368/1073 ━━━━━━━━━━━━━━━━━━━━ 29s 42ms/step - accuracy: 0.8103 - loss: 0.4763 370/1073 ━━━━━━━━━━━━━━━━━━━━ 29s 42ms/step - accuracy: 0.8103 - loss: 0.4763 372/1073 ━━━━━━━━━━━━━━━━━━━━ 29s 42ms/step - accuracy: 0.8103 - loss: 0.4763 374/1073 ━━━━━━━━━━━━━━━━━━━━ 29s 42ms/step - accuracy: 0.8103 - loss: 0.4764 376/1073 ━━━━━━━━━━━━━━━━━━━━ 29s 42ms/step - accuracy: 0.8103 - loss: 0.4764 378/1073 ━━━━━━━━━━━━━━━━━━━━ 29s 42ms/step - accuracy: 0.8103 - loss: 0.4764 380/1073 ━━━━━━━━━━━━━━━━━━━━ 28s 42ms/step - accuracy: 0.8103 - loss: 0.4764 382/1073 ━━━━━━━━━━━━━━━━━━━━ 28s 42ms/step - accuracy: 0.8103 - loss: 0.4764 384/1073 ━━━━━━━━━━━━━━━━━━━━ 28s 42ms/step - accuracy: 0.8103 - loss: 0.4765 386/1073 ━━━━━━━━━━━━━━━━━━━━ 28s 42ms/step - accuracy: 0.8103 - loss: 0.4765 388/1073 ━━━━━━━━━━━━━━━━━━━━ 28s 42ms/step - accuracy: 0.8103 - loss: 0.4765 390/1073 ━━━━━━━━━━━━━━━━━━━━ 28s 42ms/step - accuracy: 0.8102 - loss: 0.4765 392/1073 ━━━━━━━━━━━━━━━━━━━━ 28s 42ms/step - accuracy: 0.8102 - loss: 0.4765 394/1073 ━━━━━━━━━━━━━━━━━━━━ 28s 42ms/step - accuracy: 0.8102 - loss: 0.4766 396/1073 ━━━━━━━━━━━━━━━━━━━━ 28s 42ms/step - accuracy: 0.8102 - loss: 0.4766 398/1073 ━━━━━━━━━━━━━━━━━━━━ 28s 42ms/step - accuracy: 0.8102 - loss: 0.4766 400/1073 ━━━━━━━━━━━━━━━━━━━━ 28s 42ms/step - accuracy: 0.8102 - loss: 0.4766 402/1073 ━━━━━━━━━━━━━━━━━━━━ 27s 42ms/step - accuracy: 0.8102 - loss: 0.4766 404/1073 ━━━━━━━━━━━━━━━━━━━━ 27s 42ms/step - accuracy: 0.8102 - loss: 0.4767 406/1073 ━━━━━━━━━━━━━━━━━━━━ 27s 42ms/step - accuracy: 0.8102 - loss: 0.4767 408/1073 ━━━━━━━━━━━━━━━━━━━━ 27s 42ms/step - accuracy: 0.8102 - loss: 0.4767 410/1073 ━━━━━━━━━━━━━━━━━━━━ 27s 42ms/step - accuracy: 0.8102 - loss: 0.4767 412/1073 ━━━━━━━━━━━━━━━━━━━━ 27s 42ms/step - accuracy: 0.8101 - loss: 0.4767 414/1073 ━━━━━━━━━━━━━━━━━━━━ 27s 42ms/step - accuracy: 0.8101 - loss: 0.4767 416/1073 ━━━━━━━━━━━━━━━━━━━━ 27s 42ms/step - accuracy: 0.8101 - loss: 0.4768 418/1073 ━━━━━━━━━━━━━━━━━━━━ 27s 42ms/step - accuracy: 0.8101 - loss: 0.4768 420/1073 ━━━━━━━━━━━━━━━━━━━━ 27s 42ms/step - accuracy: 0.8101 - loss: 0.4768 422/1073 ━━━━━━━━━━━━━━━━━━━━ 27s 42ms/step - accuracy: 0.8101 - loss: 0.4768 424/1073 ━━━━━━━━━━━━━━━━━━━━ 27s 42ms/step - accuracy: 0.8101 - loss: 0.4768 426/1073 ━━━━━━━━━━━━━━━━━━━━ 26s 42ms/step - accuracy: 0.8101 - loss: 0.4768 428/1073 ━━━━━━━━━━━━━━━━━━━━ 26s 42ms/step - accuracy: 0.8101 - loss: 0.4769 430/1073 ━━━━━━━━━━━━━━━━━━━━ 26s 42ms/step - accuracy: 0.8101 - loss: 0.4769 432/1073 ━━━━━━━━━━━━━━━━━━━━ 26s 42ms/step - accuracy: 0.8101 - loss: 0.4769 434/1073 ━━━━━━━━━━━━━━━━━━━━ 26s 42ms/step - accuracy: 0.8101 - loss: 0.4769 436/1073 ━━━━━━━━━━━━━━━━━━━━ 26s 42ms/step - accuracy: 0.8101 - loss: 0.4769 438/1073 ━━━━━━━━━━━━━━━━━━━━ 26s 42ms/step - accuracy: 0.8100 - loss: 0.4769 440/1073 ━━━━━━━━━━━━━━━━━━━━ 26s 42ms/step - accuracy: 0.8100 - loss: 0.4770 442/1073 ━━━━━━━━━━━━━━━━━━━━ 26s 42ms/step - accuracy: 0.8100 - loss: 0.4770 444/1073 ━━━━━━━━━━━━━━━━━━━━ 26s 42ms/step - accuracy: 0.8100 - loss: 0.4770 446/1073 ━━━━━━━━━━━━━━━━━━━━ 26s 42ms/step - accuracy: 0.8100 - loss: 0.4770 448/1073 ━━━━━━━━━━━━━━━━━━━━ 25s 42ms/step - accuracy: 0.8100 - loss: 0.4770 450/1073 ━━━━━━━━━━━━━━━━━━━━ 25s 42ms/step - accuracy: 0.8100 - loss: 0.4770 452/1073 ━━━━━━━━━━━━━━━━━━━━ 25s 42ms/step - accuracy: 0.8100 - loss: 0.4771 454/1073 ━━━━━━━━━━━━━━━━━━━━ 25s 42ms/step - accuracy: 0.8100 - loss: 0.4771 456/1073 ━━━━━━━━━━━━━━━━━━━━ 25s 42ms/step - accuracy: 0.8100 - loss: 0.4771 458/1073 ━━━━━━━━━━━━━━━━━━━━ 25s 42ms/step - accuracy: 0.8100 - loss: 0.4771 460/1073 ━━━━━━━━━━━━━━━━━━━━ 25s 42ms/step - accuracy: 0.8100 - loss: 0.4771 462/1073 ━━━━━━━━━━━━━━━━━━━━ 25s 42ms/step - accuracy: 0.8100 - loss: 0.4771 464/1073 ━━━━━━━━━━━━━━━━━━━━ 25s 42ms/step - accuracy: 0.8100 - loss: 0.4772 466/1073 ━━━━━━━━━━━━━━━━━━━━ 25s 42ms/step - accuracy: 0.8099 - loss: 0.4772 468/1073 ━━━━━━━━━━━━━━━━━━━━ 25s 42ms/step - accuracy: 0.8099 - loss: 0.4772 470/1073 ━━━━━━━━━━━━━━━━━━━━ 25s 42ms/step - accuracy: 0.8099 - loss: 0.4772 472/1073 ━━━━━━━━━━━━━━━━━━━━ 24s 42ms/step - accuracy: 0.8099 - loss: 0.4772 474/1073 ━━━━━━━━━━━━━━━━━━━━ 24s 42ms/step - accuracy: 0.8099 - loss: 0.4772 476/1073 ━━━━━━━━━━━━━━━━━━━━ 24s 41ms/step - accuracy: 0.8099 - loss: 0.4772 478/1073 ━━━━━━━━━━━━━━━━━━━━ 24s 41ms/step - accuracy: 0.8099 - loss: 0.4773 480/1073 ━━━━━━━━━━━━━━━━━━━━ 24s 41ms/step - accuracy: 0.8099 - loss: 0.4773 482/1073 ━━━━━━━━━━━━━━━━━━━━ 24s 41ms/step - accuracy: 0.8099 - loss: 0.4773 484/1073 ━━━━━━━━━━━━━━━━━━━━ 24s 41ms/step - accuracy: 0.8099 - loss: 0.4773 486/1073 ━━━━━━━━━━━━━━━━━━━━ 24s 41ms/step - accuracy: 0.8099 - loss: 0.4773 488/1073 ━━━━━━━━━━━━━━━━━━━━ 24s 41ms/step - accuracy: 0.8099 - loss: 0.4773 490/1073 ━━━━━━━━━━━━━━━━━━━━ 24s 41ms/step - accuracy: 0.8099 - loss: 0.4773 492/1073 ━━━━━━━━━━━━━━━━━━━━ 24s 41ms/step - accuracy: 0.8099 - loss: 0.4774 494/1073 ━━━━━━━━━━━━━━━━━━━━ 24s 41ms/step - accuracy: 0.8099 - loss: 0.4774 496/1073 ━━━━━━━━━━━━━━━━━━━━ 23s 41ms/step - accuracy: 0.8098 - loss: 0.4774 498/1073 ━━━━━━━━━━━━━━━━━━━━ 23s 41ms/step - accuracy: 0.8098 - loss: 0.4774 500/1073 ━━━━━━━━━━━━━━━━━━━━ 23s 41ms/step - accuracy: 0.8098 - loss: 0.4774 502/1073 ━━━━━━━━━━━━━━━━━━━━ 23s 41ms/step - accuracy: 0.8098 - loss: 0.4774 504/1073 ━━━━━━━━━━━━━━━━━━━━ 23s 41ms/step - accuracy: 0.8098 - loss: 0.4774 506/1073 ━━━━━━━━━━━━━━━━━━━━ 23s 41ms/step - accuracy: 0.8098 - loss: 0.4775 508/1073 ━━━━━━━━━━━━━━━━━━━━ 23s 41ms/step - accuracy: 0.8098 - loss: 0.4775 510/1073 ━━━━━━━━━━━━━━━━━━━━ 23s 41ms/step - accuracy: 0.8098 - loss: 0.4775 512/1073 ━━━━━━━━━━━━━━━━━━━━ 23s 41ms/step - accuracy: 0.8098 - loss: 0.4775 514/1073 ━━━━━━━━━━━━━━━━━━━━ 23s 41ms/step - accuracy: 0.8098 - loss: 0.4775 516/1073 ━━━━━━━━━━━━━━━━━━━━ 23s 41ms/step - accuracy: 0.8098 - loss: 0.4775 518/1073 ━━━━━━━━━━━━━━━━━━━━ 22s 41ms/step - accuracy: 0.8098 - loss: 0.4775 520/1073 ━━━━━━━━━━━━━━━━━━━━ 22s 41ms/step - accuracy: 0.8098 - loss: 0.4775 522/1073 ━━━━━━━━━━━━━━━━━━━━ 22s 41ms/step - accuracy: 0.8098 - loss: 0.4776 524/1073 ━━━━━━━━━━━━━━━━━━━━ 22s 41ms/step - accuracy: 0.8098 - loss: 0.4776 526/1073 ━━━━━━━━━━━━━━━━━━━━ 22s 41ms/step - accuracy: 0.8098 - loss: 0.4776 528/1073 ━━━━━━━━━━━━━━━━━━━━ 22s 41ms/step - accuracy: 0.8098 - loss: 0.4776 530/1073 ━━━━━━━━━━━━━━━━━━━━ 22s 41ms/step - accuracy: 0.8098 - loss: 0.4776 532/1073 ━━━━━━━━━━━━━━━━━━━━ 22s 41ms/step - accuracy: 0.8097 - loss: 0.4776 534/1073 ━━━━━━━━━━━━━━━━━━━━ 22s 41ms/step - accuracy: 0.8097 - loss: 0.4776 536/1073 ━━━━━━━━━━━━━━━━━━━━ 22s 41ms/step - accuracy: 0.8097 - loss: 0.4777 538/1073 ━━━━━━━━━━━━━━━━━━━━ 22s 41ms/step - accuracy: 0.8097 - loss: 0.4777 540/1073 ━━━━━━━━━━━━━━━━━━━━ 22s 41ms/step - accuracy: 0.8097 - loss: 0.4777 542/1073 ━━━━━━━━━━━━━━━━━━━━ 21s 41ms/step - accuracy: 0.8097 - loss: 0.4777 544/1073 ━━━━━━━━━━━━━━━━━━━━ 21s 41ms/step - accuracy: 0.8097 - loss: 0.4777 546/1073 ━━━━━━━━━━━━━━━━━━━━ 21s 41ms/step - accuracy: 0.8097 - loss: 0.4777 548/1073 ━━━━━━━━━━━━━━━━━━━━ 21s 41ms/step - accuracy: 0.8097 - loss: 0.4777 550/1073 ━━━━━━━━━━━━━━━━━━━━ 21s 41ms/step - accuracy: 0.8097 - loss: 0.4777 552/1073 ━━━━━━━━━━━━━━━━━━━━ 21s 41ms/step - accuracy: 0.8097 - loss: 0.4778 554/1073 ━━━━━━━━━━━━━━━━━━━━ 21s 41ms/step - accuracy: 0.8097 - loss: 0.4778 556/1073 ━━━━━━━━━━━━━━━━━━━━ 21s 41ms/step - accuracy: 0.8097 - loss: 0.4778 558/1073 ━━━━━━━━━━━━━━━━━━━━ 21s 41ms/step - accuracy: 0.8097 - loss: 0.4778 560/1073 ━━━━━━━━━━━━━━━━━━━━ 21s 41ms/step - accuracy: 0.8097 - loss: 0.4778 562/1073 ━━━━━━━━━━━━━━━━━━━━ 21s 41ms/step - accuracy: 0.8097 - loss: 0.4778 564/1073 ━━━━━━━━━━━━━━━━━━━━ 21s 41ms/step - accuracy: 0.8097 - loss: 0.4778 566/1073 ━━━━━━━━━━━━━━━━━━━━ 20s 41ms/step - accuracy: 0.8097 - loss: 0.4778 568/1073 ━━━━━━━━━━━━━━━━━━━━ 20s 41ms/step - accuracy: 0.8097 - loss: 0.4779 570/1073 ━━━━━━━━━━━━━━━━━━━━ 20s 41ms/step - accuracy: 0.8096 - loss: 0.4779 572/1073 ━━━━━━━━━━━━━━━━━━━━ 20s 41ms/step - accuracy: 0.8096 - loss: 0.4779 574/1073 ━━━━━━━━━━━━━━━━━━━━ 20s 41ms/step - accuracy: 0.8096 - loss: 0.4779 576/1073 ━━━━━━━━━━━━━━━━━━━━ 20s 41ms/step - accuracy: 0.8096 - loss: 0.4779 578/1073 ━━━━━━━━━━━━━━━━━━━━ 20s 41ms/step - accuracy: 0.8096 - loss: 0.4779 580/1073 ━━━━━━━━━━━━━━━━━━━━ 20s 41ms/step - accuracy: 0.8096 - loss: 0.4779 582/1073 ━━━━━━━━━━━━━━━━━━━━ 20s 41ms/step - accuracy: 0.8096 - loss: 0.4779 584/1073 ━━━━━━━━━━━━━━━━━━━━ 20s 41ms/step - accuracy: 0.8096 - loss: 0.4779 586/1073 ━━━━━━━━━━━━━━━━━━━━ 20s 41ms/step - accuracy: 0.8096 - loss: 0.4780 588/1073 ━━━━━━━━━━━━━━━━━━━━ 20s 41ms/step - accuracy: 0.8096 - loss: 0.4780 590/1073 ━━━━━━━━━━━━━━━━━━━━ 19s 41ms/step - accuracy: 0.8096 - loss: 0.4780 592/1073 ━━━━━━━━━━━━━━━━━━━━ 19s 41ms/step - accuracy: 0.8096 - loss: 0.4780 594/1073 ━━━━━━━━━━━━━━━━━━━━ 19s 41ms/step - accuracy: 0.8096 - loss: 0.4780 596/1073 ━━━━━━━━━━━━━━━━━━━━ 19s 41ms/step - accuracy: 0.8096 - loss: 0.4780 598/1073 ━━━━━━━━━━━━━━━━━━━━ 19s 41ms/step - accuracy: 0.8096 - loss: 0.4780 600/1073 ━━━━━━━━━━━━━━━━━━━━ 19s 41ms/step - accuracy: 0.8096 - loss: 0.4780 602/1073 ━━━━━━━━━━━━━━━━━━━━ 19s 41ms/step - accuracy: 0.8096 - loss: 0.4780 604/1073 ━━━━━━━━━━━━━━━━━━━━ 19s 41ms/step - accuracy: 0.8096 - loss: 0.4781 606/1073 ━━━━━━━━━━━━━━━━━━━━ 19s 41ms/step - accuracy: 0.8096 - loss: 0.4781 608/1073 ━━━━━━━━━━━━━━━━━━━━ 19s 41ms/step - accuracy: 0.8096 - loss: 0.4781 610/1073 ━━━━━━━━━━━━━━━━━━━━ 19s 41ms/step - accuracy: 0.8096 - loss: 0.4781 612/1073 ━━━━━━━━━━━━━━━━━━━━ 19s 41ms/step - accuracy: 0.8095 - loss: 0.4781 614/1073 ━━━━━━━━━━━━━━━━━━━━ 18s 41ms/step - accuracy: 0.8095 - loss: 0.4781 616/1073 ━━━━━━━━━━━━━━━━━━━━ 18s 41ms/step - accuracy: 0.8095 - loss: 0.4781 618/1073 ━━━━━━━━━━━━━━━━━━━━ 18s 41ms/step - accuracy: 0.8095 - loss: 0.4781 620/1073 ━━━━━━━━━━━━━━━━━━━━ 18s 41ms/step - accuracy: 0.8095 - loss: 0.4782 622/1073 ━━━━━━━━━━━━━━━━━━━━ 18s 41ms/step - accuracy: 0.8095 - loss: 0.4782 624/1073 ━━━━━━━━━━━━━━━━━━━━ 18s 41ms/step - accuracy: 0.8095 - loss: 0.4782 626/1073 ━━━━━━━━━━━━━━━━━━━━ 18s 41ms/step - accuracy: 0.8095 - loss: 0.4782 628/1073 ━━━━━━━━━━━━━━━━━━━━ 18s 41ms/step - accuracy: 0.8095 - loss: 0.4782 630/1073 ━━━━━━━━━━━━━━━━━━━━ 18s 41ms/step - accuracy: 0.8095 - loss: 0.4782 632/1073 ━━━━━━━━━━━━━━━━━━━━ 18s 41ms/step - accuracy: 0.8095 - loss: 0.4782 634/1073 ━━━━━━━━━━━━━━━━━━━━ 18s 41ms/step - accuracy: 0.8095 - loss: 0.4782 636/1073 ━━━━━━━━━━━━━━━━━━━━ 18s 41ms/step - accuracy: 0.8095 - loss: 0.4783 638/1073 ━━━━━━━━━━━━━━━━━━━━ 17s 41ms/step - accuracy: 0.8095 - loss: 0.4783 640/1073 ━━━━━━━━━━━━━━━━━━━━ 17s 41ms/step - accuracy: 0.8095 - loss: 0.4783 642/1073 ━━━━━━━━━━━━━━━━━━━━ 17s 41ms/step - accuracy: 0.8095 - loss: 0.4783 644/1073 ━━━━━━━━━━━━━━━━━━━━ 17s 41ms/step - accuracy: 0.8095 - loss: 0.4783 646/1073 ━━━━━━━━━━━━━━━━━━━━ 17s 41ms/step - accuracy: 0.8095 - loss: 0.4783 648/1073 ━━━━━━━━━━━━━━━━━━━━ 17s 41ms/step - accuracy: 0.8095 - loss: 0.4783 650/1073 ━━━━━━━━━━━━━━━━━━━━ 17s 41ms/step - accuracy: 0.8094 - loss: 0.4783 652/1073 ━━━━━━━━━━━━━━━━━━━━ 17s 41ms/step - accuracy: 0.8094 - loss: 0.4784 654/1073 ━━━━━━━━━━━━━━━━━━━━ 17s 41ms/step - accuracy: 0.8094 - loss: 0.4784 656/1073 ━━━━━━━━━━━━━━━━━━━━ 17s 41ms/step - accuracy: 0.8094 - loss: 0.4784 658/1073 ━━━━━━━━━━━━━━━━━━━━ 17s 41ms/step - accuracy: 0.8094 - loss: 0.4784 660/1073 ━━━━━━━━━━━━━━━━━━━━ 17s 41ms/step - accuracy: 0.8094 - loss: 0.4784 662/1073 ━━━━━━━━━━━━━━━━━━━━ 16s 41ms/step - accuracy: 0.8094 - loss: 0.4784 664/1073 ━━━━━━━━━━━━━━━━━━━━ 16s 41ms/step - accuracy: 0.8094 - loss: 0.4784 666/1073 ━━━━━━━━━━━━━━━━━━━━ 16s 41ms/step - accuracy: 0.8094 - loss: 0.4784 668/1073 ━━━━━━━━━━━━━━━━━━━━ 16s 41ms/step - accuracy: 0.8094 - loss: 0.4785 670/1073 ━━━━━━━━━━━━━━━━━━━━ 16s 41ms/step - accuracy: 0.8094 - loss: 0.4785 672/1073 ━━━━━━━━━━━━━━━━━━━━ 16s 41ms/step - accuracy: 0.8094 - loss: 0.4785 674/1073 ━━━━━━━━━━━━━━━━━━━━ 16s 41ms/step - accuracy: 0.8094 - loss: 0.4785 676/1073 ━━━━━━━━━━━━━━━━━━━━ 16s 41ms/step - accuracy: 0.8094 - loss: 0.4785 678/1073 ━━━━━━━━━━━━━━━━━━━━ 16s 41ms/step - accuracy: 0.8094 - loss: 0.4785 680/1073 ━━━━━━━━━━━━━━━━━━━━ 16s 41ms/step - accuracy: 0.8094 - loss: 0.4785 682/1073 ━━━━━━━━━━━━━━━━━━━━ 16s 41ms/step - accuracy: 0.8094 - loss: 0.4785 684/1073 ━━━━━━━━━━━━━━━━━━━━ 16s 41ms/step - accuracy: 0.8094 - loss: 0.4785 686/1073 ━━━━━━━━━━━━━━━━━━━━ 15s 41ms/step - accuracy: 0.8094 - loss: 0.4786 688/1073 ━━━━━━━━━━━━━━━━━━━━ 15s 41ms/step - accuracy: 0.8094 - loss: 0.4786 690/1073 ━━━━━━━━━━━━━━━━━━━━ 15s 41ms/step - accuracy: 0.8094 - loss: 0.4786 692/1073 ━━━━━━━━━━━━━━━━━━━━ 15s 41ms/step - accuracy: 0.8093 - loss: 0.4786 694/1073 ━━━━━━━━━━━━━━━━━━━━ 15s 41ms/step - accuracy: 0.8093 - loss: 0.4786 696/1073 ━━━━━━━━━━━━━━━━━━━━ 15s 41ms/step - accuracy: 0.8093 - loss: 0.4786 698/1073 ━━━━━━━━━━━━━━━━━━━━ 15s 41ms/step - accuracy: 0.8093 - loss: 0.4786 700/1073 ━━━━━━━━━━━━━━━━━━━━ 15s 41ms/step - accuracy: 0.8093 - loss: 0.4786 702/1073 ━━━━━━━━━━━━━━━━━━━━ 15s 41ms/step - accuracy: 0.8093 - loss: 0.4787 704/1073 ━━━━━━━━━━━━━━━━━━━━ 15s 41ms/step - accuracy: 0.8093 - loss: 0.4787 706/1073 ━━━━━━━━━━━━━━━━━━━━ 15s 41ms/step - accuracy: 0.8093 - loss: 0.4787 708/1073 ━━━━━━━━━━━━━━━━━━━━ 15s 41ms/step - accuracy: 0.8093 - loss: 0.4787 710/1073 ━━━━━━━━━━━━━━━━━━━━ 14s 41ms/step - accuracy: 0.8093 - loss: 0.4787 712/1073 ━━━━━━━━━━━━━━━━━━━━ 14s 41ms/step - accuracy: 0.8093 - loss: 0.4787 714/1073 ━━━━━━━━━━━━━━━━━━━━ 14s 41ms/step - accuracy: 0.8093 - loss: 0.4787 716/1073 ━━━━━━━━━━━━━━━━━━━━ 14s 41ms/step - accuracy: 0.8093 - loss: 0.4787 718/1073 ━━━━━━━━━━━━━━━━━━━━ 14s 41ms/step - accuracy: 0.8093 - loss: 0.4787 720/1073 ━━━━━━━━━━━━━━━━━━━━ 14s 41ms/step - accuracy: 0.8093 - loss: 0.4788 722/1073 ━━━━━━━━━━━━━━━━━━━━ 14s 41ms/step - accuracy: 0.8093 - loss: 0.4788 724/1073 ━━━━━━━━━━━━━━━━━━━━ 14s 41ms/step - accuracy: 0.8093 - loss: 0.4788 726/1073 ━━━━━━━━━━━━━━━━━━━━ 14s 41ms/step - accuracy: 0.8093 - loss: 0.4788 728/1073 ━━━━━━━━━━━━━━━━━━━━ 14s 41ms/step - accuracy: 0.8093 - loss: 0.4788 730/1073 ━━━━━━━━━━━━━━━━━━━━ 14s 41ms/step - accuracy: 0.8093 - loss: 0.4788 732/1073 ━━━━━━━━━━━━━━━━━━━━ 14s 41ms/step - accuracy: 0.8093 - loss: 0.4788 734/1073 ━━━━━━━━━━━━━━━━━━━━ 13s 41ms/step - accuracy: 0.8092 - loss: 0.4788 736/1073 ━━━━━━━━━━━━━━━━━━━━ 13s 41ms/step - accuracy: 0.8092 - loss: 0.4788 738/1073 ━━━━━━━━━━━━━━━━━━━━ 13s 41ms/step - accuracy: 0.8092 - loss: 0.4789 740/1073 ━━━━━━━━━━━━━━━━━━━━ 13s 41ms/step - accuracy: 0.8092 - loss: 0.4789 742/1073 ━━━━━━━━━━━━━━━━━━━━ 13s 41ms/step - accuracy: 0.8092 - loss: 0.4789 744/1073 ━━━━━━━━━━━━━━━━━━━━ 13s 41ms/step - accuracy: 0.8092 - loss: 0.4789 746/1073 ━━━━━━━━━━━━━━━━━━━━ 13s 41ms/step - accuracy: 0.8092 - loss: 0.4789 748/1073 ━━━━━━━━━━━━━━━━━━━━ 13s 41ms/step - accuracy: 0.8092 - loss: 0.4789 750/1073 ━━━━━━━━━━━━━━━━━━━━ 13s 41ms/step - accuracy: 0.8092 - loss: 0.4789 752/1073 ━━━━━━━━━━━━━━━━━━━━ 13s 41ms/step - accuracy: 0.8092 - loss: 0.4789 754/1073 ━━━━━━━━━━━━━━━━━━━━ 13s 41ms/step - accuracy: 0.8092 - loss: 0.4789 756/1073 ━━━━━━━━━━━━━━━━━━━━ 13s 41ms/step - accuracy: 0.8092 - loss: 0.4790 758/1073 ━━━━━━━━━━━━━━━━━━━━ 12s 41ms/step - accuracy: 0.8092 - loss: 0.4790 760/1073 ━━━━━━━━━━━━━━━━━━━━ 12s 41ms/step - accuracy: 0.8092 - loss: 0.4790 762/1073 ━━━━━━━━━━━━━━━━━━━━ 12s 41ms/step - accuracy: 0.8092 - loss: 0.4790 764/1073 ━━━━━━━━━━━━━━━━━━━━ 12s 41ms/step - accuracy: 0.8092 - loss: 0.4790 766/1073 ━━━━━━━━━━━━━━━━━━━━ 12s 41ms/step - accuracy: 0.8092 - loss: 0.4790 768/1073 ━━━━━━━━━━━━━━━━━━━━ 12s 41ms/step - accuracy: 0.8092 - loss: 0.4790 770/1073 ━━━━━━━━━━━━━━━━━━━━ 12s 41ms/step - accuracy: 0.8092 - loss: 0.4790 772/1073 ━━━━━━━━━━━━━━━━━━━━ 12s 41ms/step - accuracy: 0.8092 - loss: 0.4790 774/1073 ━━━━━━━━━━━━━━━━━━━━ 12s 41ms/step - accuracy: 0.8092 - loss: 0.4791 776/1073 ━━━━━━━━━━━━━━━━━━━━ 12s 41ms/step - accuracy: 0.8092 - loss: 0.4791 778/1073 ━━━━━━━━━━━━━━━━━━━━ 12s 41ms/step - accuracy: 0.8092 - loss: 0.4791 780/1073 ━━━━━━━━━━━━━━━━━━━━ 12s 41ms/step - accuracy: 0.8092 - loss: 0.4791 782/1073 ━━━━━━━━━━━━━━━━━━━━ 11s 41ms/step - accuracy: 0.8091 - loss: 0.4791 784/1073 ━━━━━━━━━━━━━━━━━━━━ 11s 41ms/step - accuracy: 0.8091 - loss: 0.4791 786/1073 ━━━━━━━━━━━━━━━━━━━━ 11s 41ms/step - accuracy: 0.8091 - loss: 0.4791 788/1073 ━━━━━━━━━━━━━━━━━━━━ 11s 41ms/step - accuracy: 0.8091 - loss: 0.4791 790/1073 ━━━━━━━━━━━━━━━━━━━━ 11s 41ms/step - accuracy: 0.8091 - loss: 0.4791 792/1073 ━━━━━━━━━━━━━━━━━━━━ 11s 41ms/step - accuracy: 0.8091 - loss: 0.4792 794/1073 ━━━━━━━━━━━━━━━━━━━━ 11s 41ms/step - accuracy: 0.8091 - loss: 0.4792 796/1073 ━━━━━━━━━━━━━━━━━━━━ 11s 41ms/step - accuracy: 0.8091 - loss: 0.4792 798/1073 ━━━━━━━━━━━━━━━━━━━━ 11s 41ms/step - accuracy: 0.8091 - loss: 0.4792 800/1073 ━━━━━━━━━━━━━━━━━━━━ 11s 41ms/step - accuracy: 0.8091 - loss: 0.4792 802/1073 ━━━━━━━━━━━━━━━━━━━━ 11s 41ms/step - accuracy: 0.8091 - loss: 0.4792 804/1073 ━━━━━━━━━━━━━━━━━━━━ 11s 41ms/step - accuracy: 0.8091 - loss: 0.4792 806/1073 ━━━━━━━━━━━━━━━━━━━━ 10s 41ms/step - accuracy: 0.8091 - loss: 0.4792 808/1073 ━━━━━━━━━━━━━━━━━━━━ 10s 41ms/step - accuracy: 0.8091 - loss: 0.4792 810/1073 ━━━━━━━━━━━━━━━━━━━━ 10s 41ms/step - accuracy: 0.8091 - loss: 0.4793 812/1073 ━━━━━━━━━━━━━━━━━━━━ 10s 41ms/step - accuracy: 0.8091 - loss: 0.4793 814/1073 ━━━━━━━━━━━━━━━━━━━━ 10s 41ms/step - accuracy: 0.8091 - loss: 0.4793 816/1073 ━━━━━━━━━━━━━━━━━━━━ 10s 41ms/step - accuracy: 0.8091 - loss: 0.4793 818/1073 ━━━━━━━━━━━━━━━━━━━━ 10s 41ms/step - accuracy: 0.8091 - loss: 0.4793 820/1073 ━━━━━━━━━━━━━━━━━━━━ 10s 41ms/step - accuracy: 0.8091 - loss: 0.4793 822/1073 ━━━━━━━━━━━━━━━━━━━━ 10s 41ms/step - accuracy: 0.8091 - loss: 0.4793 824/1073 ━━━━━━━━━━━━━━━━━━━━ 10s 41ms/step - accuracy: 0.8091 - loss: 0.4793 826/1073 ━━━━━━━━━━━━━━━━━━━━ 10s 41ms/step - accuracy: 0.8091 - loss: 0.4793 828/1073 ━━━━━━━━━━━━━━━━━━━━ 10s 41ms/step - accuracy: 0.8091 - loss: 0.4793 830/1073 ━━━━━━━━━━━━━━━━━━━━ 9s 41ms/step - accuracy: 0.8091 - loss: 0.4793 832/1073 ━━━━━━━━━━━━━━━━━━━━ 9s 41ms/step - accuracy: 0.8090 - loss: 0.4794 834/1073 ━━━━━━━━━━━━━━━━━━━━ 9s 41ms/step - accuracy: 0.8090 - loss: 0.4794 836/1073 ━━━━━━━━━━━━━━━━━━━━ 9s 41ms/step - accuracy: 0.8090 - loss: 0.4794 838/1073 ━━━━━━━━━━━━━━━━━━━━ 9s 41ms/step - accuracy: 0.8090 - loss: 0.4794 840/1073 ━━━━━━━━━━━━━━━━━━━━ 9s 41ms/step - accuracy: 0.8090 - loss: 0.4794 842/1073 ━━━━━━━━━━━━━━━━━━━━ 9s 41ms/step - accuracy: 0.8090 - loss: 0.4794 844/1073 ━━━━━━━━━━━━━━━━━━━━ 9s 41ms/step - accuracy: 0.8090 - loss: 0.4794 846/1073 ━━━━━━━━━━━━━━━━━━━━ 9s 41ms/step - accuracy: 0.8090 - loss: 0.4794 848/1073 ━━━━━━━━━━━━━━━━━━━━ 9s 41ms/step - accuracy: 0.8090 - loss: 0.4794 850/1073 ━━━━━━━━━━━━━━━━━━━━ 9s 41ms/step - accuracy: 0.8090 - loss: 0.4794 852/1073 ━━━━━━━━━━━━━━━━━━━━ 9s 41ms/step - accuracy: 0.8090 - loss: 0.4794 854/1073 ━━━━━━━━━━━━━━━━━━━━ 9s 41ms/step - accuracy: 0.8090 - loss: 0.4795 856/1073 ━━━━━━━━━━━━━━━━━━━━ 8s 41ms/step - accuracy: 0.8090 - loss: 0.4795 858/1073 ━━━━━━━━━━━━━━━━━━━━ 8s 41ms/step - accuracy: 0.8090 - loss: 0.4795 860/1073 ━━━━━━━━━━━━━━━━━━━━ 8s 41ms/step - accuracy: 0.8090 - loss: 0.4795 862/1073 ━━━━━━━━━━━━━━━━━━━━ 8s 41ms/step - accuracy: 0.8090 - loss: 0.4795 864/1073 ━━━━━━━━━━━━━━━━━━━━ 8s 41ms/step - accuracy: 0.8090 - loss: 0.4795 866/1073 ━━━━━━━━━━━━━━━━━━━━ 8s 41ms/step - accuracy: 0.8090 - loss: 0.4795 868/1073 ━━━━━━━━━━━━━━━━━━━━ 8s 41ms/step - accuracy: 0.8090 - loss: 0.4795 870/1073 ━━━━━━━━━━━━━━━━━━━━ 8s 41ms/step - accuracy: 0.8090 - loss: 0.4795 872/1073 ━━━━━━━━━━━━━━━━━━━━ 8s 41ms/step - accuracy: 0.8090 - loss: 0.4795 874/1073 ━━━━━━━━━━━━━━━━━━━━ 8s 41ms/step - accuracy: 0.8090 - loss: 0.4795 876/1073 ━━━━━━━━━━━━━━━━━━━━ 8s 41ms/step - accuracy: 0.8090 - loss: 0.4795 878/1073 ━━━━━━━━━━━━━━━━━━━━ 8s 41ms/step - accuracy: 0.8090 - loss: 0.4796 880/1073 ━━━━━━━━━━━━━━━━━━━━ 7s 41ms/step - accuracy: 0.8090 - loss: 0.4796 882/1073 ━━━━━━━━━━━━━━━━━━━━ 7s 41ms/step - accuracy: 0.8090 - loss: 0.4796 884/1073 ━━━━━━━━━━━━━━━━━━━━ 7s 41ms/step - accuracy: 0.8090 - loss: 0.4796 886/1073 ━━━━━━━━━━━━━━━━━━━━ 7s 41ms/step - accuracy: 0.8090 - loss: 0.4796 888/1073 ━━━━━━━━━━━━━━━━━━━━ 7s 41ms/step - accuracy: 0.8089 - loss: 0.4796 890/1073 ━━━━━━━━━━━━━━━━━━━━ 7s 41ms/step - accuracy: 0.8089 - loss: 0.4796 892/1073 ━━━━━━━━━━━━━━━━━━━━ 7s 41ms/step - accuracy: 0.8089 - loss: 0.4796 894/1073 ━━━━━━━━━━━━━━━━━━━━ 7s 41ms/step - accuracy: 0.8089 - loss: 0.4796 896/1073 ━━━━━━━━━━━━━━━━━━━━ 7s 41ms/step - accuracy: 0.8089 - loss: 0.4796 898/1073 ━━━━━━━━━━━━━━━━━━━━ 7s 41ms/step - accuracy: 0.8089 - loss: 0.4796 900/1073 ━━━━━━━━━━━━━━━━━━━━ 7s 41ms/step - accuracy: 0.8089 - loss: 0.4796 902/1073 ━━━━━━━━━━━━━━━━━━━━ 7s 41ms/step - accuracy: 0.8089 - loss: 0.4797 904/1073 ━━━━━━━━━━━━━━━━━━━━ 6s 41ms/step - accuracy: 0.8089 - loss: 0.4797 906/1073 ━━━━━━━━━━━━━━━━━━━━ 6s 41ms/step - accuracy: 0.8089 - loss: 0.4797 908/1073 ━━━━━━━━━━━━━━━━━━━━ 6s 41ms/step - accuracy: 0.8089 - loss: 0.4797 910/1073 ━━━━━━━━━━━━━━━━━━━━ 6s 41ms/step - accuracy: 0.8089 - loss: 0.4797 912/1073 ━━━━━━━━━━━━━━━━━━━━ 6s 41ms/step - accuracy: 0.8089 - loss: 0.4797 914/1073 ━━━━━━━━━━━━━━━━━━━━ 6s 41ms/step - accuracy: 0.8089 - loss: 0.4797 916/1073 ━━━━━━━━━━━━━━━━━━━━ 6s 41ms/step - accuracy: 0.8089 - loss: 0.4797 918/1073 ━━━━━━━━━━━━━━━━━━━━ 6s 41ms/step - accuracy: 0.8089 - loss: 0.4797 920/1073 ━━━━━━━━━━━━━━━━━━━━ 6s 41ms/step - accuracy: 0.8089 - loss: 0.4797 922/1073 ━━━━━━━━━━━━━━━━━━━━ 6s 41ms/step - accuracy: 0.8089 - loss: 0.4797 924/1073 ━━━━━━━━━━━━━━━━━━━━ 6s 41ms/step - accuracy: 0.8089 - loss: 0.4797 926/1073 ━━━━━━━━━━━━━━━━━━━━ 6s 41ms/step - accuracy: 0.8089 - loss: 0.4798 928/1073 ━━━━━━━━━━━━━━━━━━━━ 5s 41ms/step - accuracy: 0.8089 - loss: 0.4798 930/1073 ━━━━━━━━━━━━━━━━━━━━ 5s 41ms/step - accuracy: 0.8089 - loss: 0.4798 932/1073 ━━━━━━━━━━━━━━━━━━━━ 5s 41ms/step - accuracy: 0.8089 - loss: 0.4798 934/1073 ━━━━━━━━━━━━━━━━━━━━ 5s 41ms/step - accuracy: 0.8089 - loss: 0.4798 936/1073 ━━━━━━━━━━━━━━━━━━━━ 5s 41ms/step - accuracy: 0.8089 - loss: 0.4798 938/1073 ━━━━━━━━━━━━━━━━━━━━ 5s 41ms/step - accuracy: 0.8089 - loss: 0.4798 940/1073 ━━━━━━━━━━━━━━━━━━━━ 5s 41ms/step - accuracy: 0.8089 - loss: 0.4798 942/1073 ━━━━━━━━━━━━━━━━━━━━ 5s 41ms/step - accuracy: 0.8089 - loss: 0.4798 944/1073 ━━━━━━━━━━━━━━━━━━━━ 5s 41ms/step - accuracy: 0.8089 - loss: 0.4798 946/1073 ━━━━━━━━━━━━━━━━━━━━ 5s 41ms/step - accuracy: 0.8088 - loss: 0.4798 948/1073 ━━━━━━━━━━━━━━━━━━━━ 5s 41ms/step - accuracy: 0.8088 - loss: 0.4798 950/1073 ━━━━━━━━━━━━━━━━━━━━ 5s 41ms/step - accuracy: 0.8088 - loss: 0.4799 952/1073 ━━━━━━━━━━━━━━━━━━━━ 4s 41ms/step - accuracy: 0.8088 - loss: 0.4799 954/1073 ━━━━━━━━━━━━━━━━━━━━ 4s 41ms/step - accuracy: 0.8088 - loss: 0.4799 956/1073 ━━━━━━━━━━━━━━━━━━━━ 4s 41ms/step - accuracy: 0.8088 - loss: 0.4799 958/1073 ━━━━━━━━━━━━━━━━━━━━ 4s 41ms/step - accuracy: 0.8088 - loss: 0.4799 960/1073 ━━━━━━━━━━━━━━━━━━━━ 4s 41ms/step - accuracy: 0.8088 - loss: 0.4799 962/1073 ━━━━━━━━━━━━━━━━━━━━ 4s 41ms/step - accuracy: 0.8088 - loss: 0.4799 964/1073 ━━━━━━━━━━━━━━━━━━━━ 4s 41ms/step - accuracy: 0.8088 - loss: 0.4799 966/1073 ━━━━━━━━━━━━━━━━━━━━ 4s 41ms/step - accuracy: 0.8088 - loss: 0.4799 968/1073 ━━━━━━━━━━━━━━━━━━━━ 4s 41ms/step - accuracy: 0.8088 - loss: 0.4799 970/1073 ━━━━━━━━━━━━━━━━━━━━ 4s 41ms/step - accuracy: 0.8088 - loss: 0.4799 972/1073 ━━━━━━━━━━━━━━━━━━━━ 4s 41ms/step - accuracy: 0.8088 - loss: 0.4799 974/1073 ━━━━━━━━━━━━━━━━━━━━ 4s 41ms/step - accuracy: 0.8088 - loss: 0.4799 976/1073 ━━━━━━━━━━━━━━━━━━━━ 3s 41ms/step - accuracy: 0.8088 - loss: 0.4799 978/1073 ━━━━━━━━━━━━━━━━━━━━ 3s 41ms/step - accuracy: 0.8088 - loss: 0.4800 980/1073 ━━━━━━━━━━━━━━━━━━━━ 3s 41ms/step - accuracy: 0.8088 - loss: 0.4800 982/1073 ━━━━━━━━━━━━━━━━━━━━ 3s 41ms/step - accuracy: 0.8088 - loss: 0.4800 984/1073 ━━━━━━━━━━━━━━━━━━━━ 3s 41ms/step - accuracy: 0.8088 - loss: 0.4800 986/1073 ━━━━━━━━━━━━━━━━━━━━ 3s 41ms/step - accuracy: 0.8088 - loss: 0.4800 988/1073 ━━━━━━━━━━━━━━━━━━━━ 3s 41ms/step - accuracy: 0.8088 - loss: 0.4800 990/1073 ━━━━━━━━━━━━━━━━━━━━ 3s 41ms/step - accuracy: 0.8088 - loss: 0.4800 992/1073 ━━━━━━━━━━━━━━━━━━━━ 3s 41ms/step - accuracy: 0.8088 - loss: 0.4800 994/1073 ━━━━━━━━━━━━━━━━━━━━ 3s 41ms/step - accuracy: 0.8088 - loss: 0.4800 995/1073 ━━━━━━━━━━━━━━━━━━━━ 3s 41ms/step - accuracy: 0.8088 - loss: 0.4800 997/1073 ━━━━━━━━━━━━━━━━━━━━ 3s 41ms/step - accuracy: 0.8088 - loss: 0.4800 999/1073 ━━━━━━━━━━━━━━━━━━━━ 3s 41ms/step - accuracy: 0.8088 - loss: 0.48001001/1073 ━━━━━━━━━━━━━━━━━━━━ 2s 41ms/step - accuracy: 0.8088 - loss: 0.48001003/1073 ━━━━━━━━━━━━━━━━━━━━ 2s 41ms/step - accuracy: 0.8088 - loss: 0.48001005/1073 ━━━━━━━━━━━━━━━━━━━━ 2s 41ms/step - accuracy: 0.8088 - loss: 0.48011007/1073 ━━━━━━━━━━━━━━━━━━━━ 2s 41ms/step - accuracy: 0.8088 - loss: 0.48011009/1073 ━━━━━━━━━━━━━━━━━━━━ 2s 41ms/step - accuracy: 0.8088 - loss: 0.48011011/1073 ━━━━━━━━━━━━━━━━━━━━ 2s 41ms/step - accuracy: 0.8087 - loss: 0.48011013/1073 ━━━━━━━━━━━━━━━━━━━━ 2s 41ms/step - accuracy: 0.8087 - loss: 0.48011015/1073 ━━━━━━━━━━━━━━━━━━━━ 2s 41ms/step - accuracy: 0.8087 - loss: 0.48011017/1073 ━━━━━━━━━━━━━━━━━━━━ 2s 41ms/step - accuracy: 0.8087 - loss: 0.48011019/1073 ━━━━━━━━━━━━━━━━━━━━ 2s 41ms/step - accuracy: 0.8087 - loss: 0.48011021/1073 ━━━━━━━━━━━━━━━━━━━━ 2s 41ms/step - accuracy: 0.8087 - loss: 0.48011023/1073 ━━━━━━━━━━━━━━━━━━━━ 2s 41ms/step - accuracy: 0.8087 - loss: 0.48011025/1073 ━━━━━━━━━━━━━━━━━━━━ 1s 41ms/step - accuracy: 0.8087 - loss: 0.48011027/1073 ━━━━━━━━━━━━━━━━━━━━ 1s 41ms/step - accuracy: 0.8087 - loss: 0.48011029/1073 ━━━━━━━━━━━━━━━━━━━━ 1s 41ms/step - accuracy: 0.8087 - loss: 0.48011031/1073 ━━━━━━━━━━━━━━━━━━━━ 1s 41ms/step - accuracy: 0.8087 - loss: 0.48011033/1073 ━━━━━━━━━━━━━━━━━━━━ 1s 41ms/step - accuracy: 0.8087 - loss: 0.48021035/1073 ━━━━━━━━━━━━━━━━━━━━ 1s 41ms/step - accuracy: 0.8087 - loss: 0.48021037/1073 ━━━━━━━━━━━━━━━━━━━━ 1s 41ms/step - accuracy: 0.8087 - loss: 0.48021039/1073 ━━━━━━━━━━━━━━━━━━━━ 1s 41ms/step - accuracy: 0.8087 - loss: 0.48021041/1073 ━━━━━━━━━━━━━━━━━━━━ 1s 41ms/step - accuracy: 0.8087 - loss: 0.48021043/1073 ━━━━━━━━━━━━━━━━━━━━ 1s 41ms/step - accuracy: 0.8087 - loss: 0.48021045/1073 ━━━━━━━━━━━━━━━━━━━━ 1s 41ms/step - accuracy: 0.8087 - loss: 0.48021047/1073 ━━━━━━━━━━━━━━━━━━━━ 1s 41ms/step - accuracy: 0.8087 - loss: 0.48021049/1073 ━━━━━━━━━━━━━━━━━━━━ 0s 41ms/step - accuracy: 0.8087 - loss: 0.48021051/1073 ━━━━━━━━━━━━━━━━━━━━ 0s 41ms/step - accuracy: 0.8087 - loss: 0.48021053/1073 ━━━━━━━━━━━━━━━━━━━━ 0s 41ms/step - accuracy: 0.8087 - loss: 0.48021055/1073 ━━━━━━━━━━━━━━━━━━━━ 0s 41ms/step - accuracy: 0.8087 - loss: 0.48021057/1073 ━━━━━━━━━━━━━━━━━━━━ 0s 41ms/step - accuracy: 0.8087 - loss: 0.48021059/1073 ━━━━━━━━━━━━━━━━━━━━ 0s 41ms/step - accuracy: 0.8087 - loss: 0.48031061/1073 ━━━━━━━━━━━━━━━━━━━━ 0s 41ms/step - accuracy: 0.8087 - loss: 0.48031063/1073 ━━━━━━━━━━━━━━━━━━━━ 0s 41ms/step - accuracy: 0.8087 - loss: 0.48031065/1073 ━━━━━━━━━━━━━━━━━━━━ 0s 41ms/step - accuracy: 0.8087 - loss: 0.48031067/1073 ━━━━━━━━━━━━━━━━━━━━ 0s 41ms/step - accuracy: 0.8087 - loss: 0.48031069/1073 ━━━━━━━━━━━━━━━━━━━━ 0s 41ms/step - accuracy: 0.8087 - loss: 0.48031071/1073 ━━━━━━━━━━━━━━━━━━━━ 0s 41ms/step - accuracy: 0.8087 - loss: 0.48031073/1073 ━━━━━━━━━━━━━━━━━━━━ 0s 41ms/step - accuracy: 0.8086 - loss: 0.48031073/1073 ━━━━━━━━━━━━━━━━━━━━ 46s 41ms/step - accuracy: 0.8069 - loss: 0.4844 - val_accuracy: 0.7857 - val_loss: 0.5478<keras.src.callbacks.history.History at 0x76bd75f2d730>lr, num_epochs = 1e-4, 5
optimizer = nnx.Optimizer(net, optax.adam(lr), wrt=nnx.Param)
@nnx.jit
def train_step(net, optimizer, tokens_X, segments_X, valid_lens_x, labels):
def loss_fn(model):
logits = model(tokens_X, segments_X, valid_lens_x)
return optax.softmax_cross_entropy_with_integer_labels(
logits, labels).mean()
loss, grads = nnx.value_and_grad(loss_fn)(net)
optimizer.update(net, grads)
return loss
@nnx.jit
def eval_step(net, tokens_X, segments_X, valid_lens_x, labels):
logits = nnx.view(net, deterministic=True)(
tokens_X, segments_X, valid_lens_x)
return (logits.argmax(axis=-1) == labels).sum()
for epoch in range(num_epochs):
train_loss, n_train = jnp.array(0.0), 0
for batch in train_iter:
tokens_X, segments_X, valid_lens_x, labels = (
batch[0], batch[1], batch[2], batch[3])
loss = train_step(net, optimizer, tokens_X, segments_X,
valid_lens_x, labels)
train_loss += loss * len(labels)
n_train += len(labels)
# Evaluate on test set
n_correct, n_test = jnp.array(0), 0
for batch in test_iter:
tokens_X, segments_X, valid_lens_x, labels = (
batch[0], batch[1], batch[2], batch[3])
n_correct += eval_step(
net, tokens_X, segments_X, valid_lens_x, labels)
n_test += len(labels)
train_loss, n_correct = float(train_loss), int(n_correct)
print(f'epoch {epoch + 1}, loss {train_loss / n_train:.4f}, '
f'test acc {n_correct / n_test:.4f}')epoch 1, loss 0.7752, test acc 0.7356epoch 2, loss 0.6329, test acc 0.7565epoch 3, loss 0.5652, test acc 0.7741epoch 4, loss 0.5165, test acc 0.7827epoch 5, loss 0.4798, test acc 0.7856lr, num_epochs = 1e-4, 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,
d2l.split_batch_multi_inputs)loss 0.478, train acc 0.810, test acc 0.785
1539.4 examples/sec on [gpu(0)]
18.7.4 Summary
- We can fine-tune the pretrained BERT model for downstream applications, such as natural language inference on the SNLI dataset.
- During fine-tuning, the BERT model becomes part of the model for the downstream application. Parameters that are only related to pretraining loss will not be updated during fine-tuning.
18.7.5 Exercises
- Fine-tune a much larger pretrained BERT model that is about as big as the original BERT base model if your computational resource allows. Set arguments in the
load_pretrained_modelfunction as: replacing ‘bert.small’ with ‘bert.base’, increasing values ofnum_hiddens=256,ffn_num_hiddens=512,num_heads=4, andnum_blks=2to 768, 3072, 12, and 12, respectively. By increasing fine-tuning epochs (and possibly tuning other hyperparameters), can you get a testing accuracy higher than 0.86? - How to truncate a pair of sequences according to their ratio of length? Compare this pair truncation method and the one used in the
SNLIBERTDatasetclass. What are their pros and cons?