TFBertForSequenceClassification for multi label classification - tensorflow2.0

Question

I am trying to fine-tune a bert model for multi-label classification.
here is how my data looks like. I have put the entire code on this colab notebook
({'input_ids': <tf.Tensor: shape=(128,), dtype=int32, numpy=
array([ 2, 8318, 1379, 7892, 2791, 20630, 1, 4, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0], dtype=int32)>,
'attention_mask': <tf.Tensor: shape=(128,), dtype=int32, numpy=
array([1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0], dtype=int32)>},
<tf.Tensor: shape=(7,), dtype=int64, numpy=array([1, 0, 0, 0, 0, 0, 0])>)
The first element is the id,
The second element corresponds to the attention_masks
the third one are the labels - here I have 7 lables.
First effort:
MODEL_NAME_OR_PATH = 'HooshvareLab/bert-fa-base-uncased'
NUM_LABELS = 7
from transformers import TFBertForSequenceClassification, BertConfig
model = TFBertForSequenceClassification.from_pretrained(
MODEL_NAME_OR_PATH,
config=BertConfig.from_pretrained(MODEL_NAME_OR_PATH, num_labels=NUM_LABELS, problem_type="multi_label_classification")
)
loss = tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True)
model.compile(optimizer='adam', loss=loss, metrics=['accuracy'])
history = model.fit(train_dataset, epochs=1, steps_per_epoch=115, validation_data=valid_dataset, validation_steps=7)
which ends up with the following error
InvalidArgumentError Traceback (most recent call last)
<ipython-input-48-4408a1f17fbe> in <module>()
10 loss = tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True)
11 model.compile(optimizer='adam', loss=loss, metrics=['accuracy'])
---> 12 history = model.fit(train_dataset, epochs=1, steps_per_epoch=115, validation_data=valid_dataset, validation_steps=7)
13
14
1 frames
/usr/local/lib/python3.7/dist-packages/tensorflow/python/eager/execute.py in quick_execute(op_name, num_outputs, inputs, attrs, ctx, name)
53 ctx.ensure_initialized()
54 tensors = pywrap_tfe.TFE_Py_Execute(ctx._handle, device_name, op_name,
---> 55 inputs, attrs, num_outputs)
56 except core._NotOkStatusException as e:
57 if name is not None:
InvalidArgumentError: Graph execution error:
Detected at node 'Equal' defined at (most recent call last):
File "/usr/lib/python3.7/runpy.py", line 193, in _run_module_as_main
"__main__", mod_spec)
File "/usr/lib/python3.7/runpy.py", line 85, in _run_code
exec(code, run_globals)
File "/usr/local/lib/python3.7/dist-packages/ipykernel_launcher.py", line 16, in <module>
app.launch_new_instance()
File "/usr/local/lib/python3.7/dist-packages/traitlets/config/application.py", line 846, in launch_instance
app.start()
File "/usr/local/lib/python3.7/dist-packages/ipykernel/kernelapp.py", line 499, in start
self.io_loop.start()
File "/usr/local/lib/python3.7/dist-packages/tornado/platform/asyncio.py", line 132, in start
self.asyncio_loop.run_forever()
File "/usr/lib/python3.7/asyncio/base_events.py", line 541, in run_forever
self._run_once()
File "/usr/lib/python3.7/asyncio/base_events.py", line 1786, in _run_once
handle._run()
File "/usr/lib/python3.7/asyncio/events.py", line 88, in _run
self._context.run(self._callback, *self._args)
File "/usr/local/lib/python3.7/dist-packages/tornado/platform/asyncio.py", line 122, in _handle_events
handler_func(fileobj, events)
File "/usr/local/lib/python3.7/dist-packages/tornado/stack_context.py", line 300, in null_wrapper
return fn(*args, **kwargs)
File "/usr/local/lib/python3.7/dist-packages/zmq/eventloop/zmqstream.py", line 577, in _handle_events
self._handle_recv()
File "/usr/local/lib/python3.7/dist-packages/zmq/eventloop/zmqstream.py", line 606, in _handle_recv
self._run_callback(callback, msg)
File "/usr/local/lib/python3.7/dist-packages/zmq/eventloop/zmqstream.py", line 556, in _run_callback
callback(*args, **kwargs)
File "/usr/local/lib/python3.7/dist-packages/tornado/stack_context.py", line 300, in null_wrapper
return fn(*args, **kwargs)
File "/usr/local/lib/python3.7/dist-packages/ipykernel/kernelbase.py", line 283, in dispatcher
return self.dispatch_shell(stream, msg)
File "/usr/local/lib/python3.7/dist-packages/ipykernel/kernelbase.py", line 233, in dispatch_shell
handler(stream, idents, msg)
File "/usr/local/lib/python3.7/dist-packages/ipykernel/kernelbase.py", line 399, in execute_request
user_expressions, allow_stdin)
File "/usr/local/lib/python3.7/dist-packages/ipykernel/ipkernel.py", line 208, in do_execute
res = shell.run_cell(code, store_history=store_history, silent=silent)
File "/usr/local/lib/python3.7/dist-packages/ipykernel/zmqshell.py", line 537, in run_cell
return super(ZMQInteractiveShell, self).run_cell(*args, **kwargs)
File "/usr/local/lib/python3.7/dist-packages/IPython/core/interactiveshell.py", line 2718, in run_cell
interactivity=interactivity, compiler=compiler, result=result)
File "/usr/local/lib/python3.7/dist-packages/IPython/core/interactiveshell.py", line 2822, in run_ast_nodes
if self.run_code(code, result):
File "/usr/local/lib/python3.7/dist-packages/IPython/core/interactiveshell.py", line 2882, in run_code
exec(code_obj, self.user_global_ns, self.user_ns)
File "<ipython-input-48-4408a1f17fbe>", line 12, in <module>
history = model.fit(train_dataset, epochs=1, steps_per_epoch=115, validation_data=valid_dataset, validation_steps=7)
File "/usr/local/lib/python3.7/dist-packages/keras/utils/traceback_utils.py", line 64, in error_handler
return fn(*args, **kwargs)
File "/usr/local/lib/python3.7/dist-packages/keras/engine/training.py", line 1384, in fit
tmp_logs = self.train_function(iterator)
File "/usr/local/lib/python3.7/dist-packages/keras/engine/training.py", line 1021, in train_function
return step_function(self, iterator)
File "/usr/local/lib/python3.7/dist-packages/keras/engine/training.py", line 1010, in step_function
outputs = model.distribute_strategy.run(run_step, args=(data,))
File "/usr/local/lib/python3.7/dist-packages/keras/engine/training.py", line 1000, in run_step
outputs = model.train_step(data)
File "/usr/local/lib/python3.7/dist-packages/transformers/modeling_tf_utils.py", line 1156, in train_step
self.compiled_metrics.update_state(y, y_pred, sample_weight)
File "/usr/local/lib/python3.7/dist-packages/keras/engine/compile_utils.py", line 459, in update_state
metric_obj.update_state(y_t, y_p, sample_weight=mask)
File "/usr/local/lib/python3.7/dist-packages/keras/utils/metrics_utils.py", line 70, in decorated
update_op = update_state_fn(*args, **kwargs)
File "/usr/local/lib/python3.7/dist-packages/keras/metrics.py", line 178, in update_state_fn
return ag_update_state(*args, **kwargs)
File "/usr/local/lib/python3.7/dist-packages/keras/metrics.py", line 729, in update_state
matches = ag_fn(y_true, y_pred, **self._fn_kwargs)
File "/usr/local/lib/python3.7/dist-packages/keras/metrics.py", line 4086, in sparse_categorical_accuracy
return tf.cast(tf.equal(y_true, y_pred), backend.floatx())
Node: 'Equal'
required broadcastable shapes
[[{{node Equal}}]] [Op:__inference_train_function_187978]
Second Effort inspired by this piece of code
from transformers import TFBertPreTrainedModel
from transformers import TFBertMainLayer
class TFBertForMultilabelClassification(TFBertPreTrainedModel):
def __init__(self, config, *inputs, **kwargs):
super(TFBertForMultilabelClassification, self).__init__(config, *inputs, **kwargs)
self.num_labels = config.num_labels
self.bert = TFBertMainLayer(config, name='bert')
self.dropout = tf.keras.layers.Dropout(config.hidden_dropout_prob)
self.classifier = tf.keras.layers.Dense(config.num_labels,
kernel_initializer='random_normal', #get_initializer(config.initializer_range),
name='classifier',
activation='sigmoid')
def call(self, inputs, **kwargs):
outputs = self.bert(inputs, **kwargs)
pooled_output = outputs[1]
pooled_output = self.dropout(pooled_output, training=kwargs.get('training', False))
logits = self.classifier(pooled_output)
outputs = (logits,) + outputs[2:] # add hidden states and attention if they are here
return outputs # logits, (hidden_states), (attentions)
MODEL_NAME_OR_PATH = 'HooshvareLab/bert-fa-base-uncased'
NUM_LABELS = len(y_train[0])
model = TFBertForMultilabelClassification.from_pretrained(MODEL_NAME_OR_PATH, num_labels=NUM_LABELS)
optimizer = tf.keras.optimizers.Adam(learning_rate=0.001,epsilon=1e-08, clipnorm=1)
# we do not have one-hot vectors, we can use sparce categorical cross entropy and accuracy
loss = tf.keras.losses.BinaryCrossentropy()
metric = tf.keras.metrics.CategoricalAccuracy()
model.compile(optimizer=optimizer, loss=loss, metrics=['accuracy'])
history = model.fit(train_dataset, epochs=1, validation_data=valid_dataset)
returns the following error
InvalidArgumentError Traceback (most recent call last)
<ipython-input-49-8aa1173bef76> in <module>()
4 metric = tf.keras.metrics.CategoricalAccuracy()
5 model.compile(optimizer=optimizer, loss=loss, metrics=['accuracy'])
----> 6 history = model.fit(train_dataset, epochs=1, validation_data=valid_dataset)
1 frames
/usr/local/lib/python3.7/dist-packages/tensorflow/python/eager/execute.py in quick_execute(op_name, num_outputs, inputs, attrs, ctx, name)
53 ctx.ensure_initialized()
54 tensors = pywrap_tfe.TFE_Py_Execute(ctx._handle, device_name, op_name,
---> 55 inputs, attrs, num_outputs)
56 except core._NotOkStatusException as e:
57 if name is not None:
InvalidArgumentError: Graph execution error:
Detected at node 'Equal' defined at (most recent call last):
File "/usr/lib/python3.7/runpy.py", line 193, in _run_module_as_main
"__main__", mod_spec)
File "/usr/lib/python3.7/runpy.py", line 85, in _run_code
exec(code, run_globals)
File "/usr/local/lib/python3.7/dist-packages/ipykernel_launcher.py", line 16, in <module>
app.launch_new_instance()
File "/usr/local/lib/python3.7/dist-packages/traitlets/config/application.py", line 846, in launch_instance
app.start()
File "/usr/local/lib/python3.7/dist-packages/ipykernel/kernelapp.py", line 499, in start
self.io_loop.start()
File "/usr/local/lib/python3.7/dist-packages/tornado/platform/asyncio.py", line 132, in start
self.asyncio_loop.run_forever()
File "/usr/lib/python3.7/asyncio/base_events.py", line 541, in run_forever
self._run_once()
File "/usr/lib/python3.7/asyncio/base_events.py", line 1786, in _run_once
handle._run()
File "/usr/lib/python3.7/asyncio/events.py", line 88, in _run
self._context.run(self._callback, *self._args)
File "/usr/local/lib/python3.7/dist-packages/tornado/platform/asyncio.py", line 122, in _handle_events
handler_func(fileobj, events)
File "/usr/local/lib/python3.7/dist-packages/tornado/stack_context.py", line 300, in null_wrapper
return fn(*args, **kwargs)
File "/usr/local/lib/python3.7/dist-packages/zmq/eventloop/zmqstream.py", line 577, in _handle_events
self._handle_recv()
File "/usr/local/lib/python3.7/dist-packages/zmq/eventloop/zmqstream.py", line 606, in _handle_recv
self._run_callback(callback, msg)
File "/usr/local/lib/python3.7/dist-packages/zmq/eventloop/zmqstream.py", line 556, in _run_callback
callback(*args, **kwargs)
File "/usr/local/lib/python3.7/dist-packages/tornado/stack_context.py", line 300, in null_wrapper
return fn(*args, **kwargs)
File "/usr/local/lib/python3.7/dist-packages/ipykernel/kernelbase.py", line 283, in dispatcher
return self.dispatch_shell(stream, msg)
File "/usr/local/lib/python3.7/dist-packages/ipykernel/kernelbase.py", line 233, in dispatch_shell
handler(stream, idents, msg)
File "/usr/local/lib/python3.7/dist-packages/ipykernel/kernelbase.py", line 399, in execute_request
user_expressions, allow_stdin)
File "/usr/local/lib/python3.7/dist-packages/ipykernel/ipkernel.py", line 208, in do_execute
res = shell.run_cell(code, store_history=store_history, silent=silent)
File "/usr/local/lib/python3.7/dist-packages/ipykernel/zmqshell.py", line 537, in run_cell
return super(ZMQInteractiveShell, self).run_cell(*args, **kwargs)
File "/usr/local/lib/python3.7/dist-packages/IPython/core/interactiveshell.py", line 2718, in run_cell
interactivity=interactivity, compiler=compiler, result=result)
File "/usr/local/lib/python3.7/dist-packages/IPython/core/interactiveshell.py", line 2822, in run_ast_nodes
if self.run_code(code, result):
File "/usr/local/lib/python3.7/dist-packages/IPython/core/interactiveshell.py", line 2882, in run_code
exec(code_obj, self.user_global_ns, self.user_ns)
File "<ipython-input-49-8aa1173bef76>", line 6, in <module>
history = model.fit(train_dataset, epochs=1, validation_data=valid_dataset)
File "/usr/local/lib/python3.7/dist-packages/keras/utils/traceback_utils.py", line 64, in error_handler
return fn(*args, **kwargs)
File "/usr/local/lib/python3.7/dist-packages/keras/engine/training.py", line 1384, in fit
tmp_logs = self.train_function(iterator)
File "/usr/local/lib/python3.7/dist-packages/keras/engine/training.py", line 1021, in train_function
return step_function(self, iterator)
File "/usr/local/lib/python3.7/dist-packages/keras/engine/training.py", line 1010, in step_function
outputs = model.distribute_strategy.run(run_step, args=(data,))
File "/usr/local/lib/python3.7/dist-packages/keras/engine/training.py", line 1000, in run_step
outputs = model.train_step(data)
File "/usr/local/lib/python3.7/dist-packages/transformers/modeling_tf_utils.py", line 1156, in train_step
self.compiled_metrics.update_state(y, y_pred, sample_weight)
File "/usr/local/lib/python3.7/dist-packages/keras/engine/compile_utils.py", line 459, in update_state
metric_obj.update_state(y_t, y_p, sample_weight=mask)
File "/usr/local/lib/python3.7/dist-packages/keras/utils/metrics_utils.py", line 70, in decorated
update_op = update_state_fn(*args, **kwargs)
File "/usr/local/lib/python3.7/dist-packages/keras/metrics.py", line 178, in update_state_fn
return ag_update_state(*args, **kwargs)
File "/usr/local/lib/python3.7/dist-packages/keras/metrics.py", line 729, in update_state
matches = ag_fn(y_true, y_pred, **self._fn_kwargs)
File "/usr/local/lib/python3.7/dist-packages/keras/metrics.py", line 4086, in sparse_categorical_accuracy
return tf.cast(tf.equal(y_true, y_pred), backend.floatx())
Node: 'Equal'
required broadcastable shapes
[[{{node Equal}}]] [Op:__inference_train_function_214932]
I hope I believe given major changes both in tf2 and (TF-based) huggingface transformers
UPDATE
Here is the entire code with a dummy dataset; the whole thing is also available on this colab notebook
load the libraries
import os
import pandas as pd
import numpy as np
from transformers import TFBertPreTrainedModel
from transformers import TFBertMainLayer
from keras.preprocessing.sequence import pad_sequences
from tqdm import tqdm
from transformers import BertTokenizer
import tensorflow as tf
make a dummy data
x_train = ['هان از وقتی که زفتم مدرسه',
'معاویه برادر شمر',
'وقتی که از پنجره سرشرو میاره بیرون دالی میکنه',
'هر دو سحرند این کجا و آن کجا']
y_train = [[1, 0, 0, 0, 0, 0, 0], [0, 1, 0, 0, 0, 0, 1], [1, 0, 0, 0, 0, 0, 0], [1, 0, 0, 0, 0, 0, 0]]
x_test, x_valid = x_train, x_train
y_test, y_valid = y_train, y_train
add the configs
# general config
MAX_LEN = 128
batch_size = 32
TRAIN_BATCH_SIZE = batch_size
VALID_BATCH_SIZE = batch_size
TEST_BATCH_SIZE = batch_size
EPOCHS = 3
EEVERY_EPOCH = 1000
LEARNING_RATE = 2e-5
CLIP = 0.0
make the data huggingface friendly
MODEL_NAME_OR_PATH = 'HooshvareLab/bert-fa-base-uncased'
tokenizer = BertTokenizer.from_pretrained(MODEL_NAME_OR_PATH)
MAX_LEN = 128
def tokenize_sentences(sentences, tokenizer, max_seq_len = 128):
tokenized_sentences = []
for sentence in tqdm(sentences):
tokenized_sentence = tokenizer.encode(
sentence, # Sentence to encode.
add_special_tokens = True, # Add '[CLS]' and '[SEP]'
max_length = max_seq_len, # Truncate all sentences.
)
tokenized_sentences.append(tokenized_sentence)
return tokenized_sentences
def create_attention_masks(tokenized_and_padded_sentences):
attention_masks = []
for sentence in tokenized_and_padded_sentences:
att_mask = [int(token_id > 0) for token_id in sentence]
attention_masks.append(att_mask)
return np.asarray(attention_masks)
train_ids = tokenize_sentences(x_train, tokenizer, max_seq_len = 128)
train_ids = pad_sequences(train_ids, maxlen=MAX_LEN, dtype="long", value=0, truncating="post", padding="post")
train_masks = create_attention_masks(train_ids)
valid_ids = tokenize_sentences(x_valid, tokenizer, max_seq_len = 128)
valid_ids = pad_sequences(valid_ids, maxlen=MAX_LEN, dtype="long", value=0, truncating="post", padding="post")
valid_masks = create_attention_masks(valid_ids)
test_ids = tokenize_sentences(x_test, tokenizer, max_seq_len = 128)
test_ids = pad_sequences(test_ids, maxlen=MAX_LEN, dtype="long", value=0, truncating="post", padding="post")
test_masks = create_attention_masks(test_ids)
create the datasets
def create_dataset(ids, masks, labels):
def gen():
for i in range(len(ids)):
yield (
{
"input_ids": ids[i],
"attention_mask": masks[i]
},
labels[i],
)
return tf.data.Dataset.from_generator(
gen,
({"input_ids": tf.int32, "attention_mask": tf.int32}, tf.int64),
(
{
"input_ids": tf.TensorShape([None]),
"attention_mask": tf.TensorShape([None])
},
tf.TensorShape([None]),
),
)
train_dataset = create_dataset(train_ids, train_masks, y_train)
valid_dataset = create_dataset(valid_ids, valid_masks, y_valid)
test_dataset = create_dataset(test_ids, test_masks, y_test)
that is how the data looks like
for item in train_dataset.take(1):
print(item)
Approach 1
class TFBertForMultilabelClassification(TFBertPreTrainedModel):
def __init__(self, config, *inputs, **kwargs):
super(TFBertForMultilabelClassification, self).__init__(config, *inputs, **kwargs)
self.num_labels = config.num_labels
self.bert = TFBertMainLayer(config, name='bert')
self.dropout = tf.keras.layers.Dropout(config.hidden_dropout_prob)
self.classifier = tf.keras.layers.Dense(config.num_labels,
kernel_initializer='random_normal', #get_initializer(config.initializer_range),
name='classifier',
activation='sigmoid')
def call(self, inputs, **kwargs):
outputs = self.bert(inputs, **kwargs)
pooled_output = outputs[1]
pooled_output = self.dropout(pooled_output, training=kwargs.get('training', False))
logits = self.classifier(pooled_output)
outputs = (logits,) + outputs[2:] # add hidden states and attention if they are here
return outputs # logits, (hidden_states), (attentions)
NUM_LABELS = len(y_train[0])
model = TFBertForMultilabelClassification.from_pretrained(MODEL_NAME_OR_PATH, num_labels=NUM_LABELS)
optimizer = tf.keras.optimizers.Adam(learning_rate=0.001,epsilon=1e-08, clipnorm=1)
# we do not have one-hot vectors, we can use sparce categorical cross entropy and accuracy
loss = tf.keras.losses.BinaryCrossentropy()
metric = tf.keras.metrics.CategoricalAccuracy()
model.compile(optimizer=optimizer, loss=loss, metrics=['accuracy'])
history = model.fit(train_dataset, epochs=1, validation_data=valid_dataset)
with an error
---------------------------------------------------------------------------
AttributeError Traceback (most recent call last)
<ipython-input-36-8aa1173bef76> in <module>()
4 metric = tf.keras.metrics.CategoricalAccuracy()
5 model.compile(optimizer=optimizer, loss=loss, metrics=['accuracy'])
----> 6 history = model.fit(train_dataset, epochs=1, validation_data=valid_dataset)
1 frames
/usr/local/lib/python3.7/dist-packages/tensorflow/python/framework/func_graph.py in autograph_handler(*args, **kwargs)
1145 except Exception as e: # pylint:disable=broad-except
1146 if hasattr(e, "ag_error_metadata"):
-> 1147 raise e.ag_error_metadata.to_exception(e)
1148 else:
1149 raise
AttributeError: in user code:
File "/usr/local/lib/python3.7/dist-packages/keras/engine/training.py", line 1021, in train_function *
return step_function(self, iterator)
File "/usr/local/lib/python3.7/dist-packages/keras/engine/training.py", line 1010, in step_function **
outputs = model.distribute_strategy.run(run_step, args=(data,))
File "/usr/local/lib/python3.7/dist-packages/keras/engine/training.py", line 1000, in run_step **
outputs = model.train_step(data)
File "/usr/local/lib/python3.7/dist-packages/transformers/modeling_tf_utils.py", line 1145, in train_step
if list(y_pred.keys())[0] == "loss":
AttributeError: 'tuple' object has no attribute 'keys'
Approach 2:
MODEL_NAME_OR_PATH = 'HooshvareLab/bert-fa-base-uncased'
NUM_LABELS = 7
from transformers import TFBertForSequenceClassification, BertConfig
model = TFBertForSequenceClassification.from_pretrained(
MODEL_NAME_OR_PATH,
config=BertConfig.from_pretrained(MODEL_NAME_OR_PATH, num_labels=NUM_LABELS, problem_type="multi_label_classification")
)
loss = tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True)
model.compile(optimizer='adam', loss=loss, metrics=['accuracy'])
history = model.fit(train_dataset, epochs=1, steps_per_epoch=115, validation_data=valid_dataset, validation_steps=7)
and the error
outputs = model.distribute_strategy.run(run_step, args=(data,))
File "/usr/local/lib/python3.7/dist-packages/keras/engine/training.py", line 1000, in run_step
outputs = model.train_step(data)
File "/usr/local/lib/python3.7/dist-packages/transformers/modeling_tf_utils.py", line 1151, in train_step
loss = self.compiled_loss(y, y_pred, sample_weight, regularization_losses=self.losses)
File "/usr/local/lib/python3.7/dist-packages/keras/engine/compile_utils.py", line 201, in __call__
loss_value = loss_obj(y_t, y_p, sample_weight=sw)
File "/usr/local/lib/python3.7/dist-packages/keras/losses.py", line 141, in __call__
losses = call_fn(y_true, y_pred)
File "/usr/local/lib/python3.7/dist-packages/keras/losses.py", line 245, in call
return ag_fn(y_true, y_pred, **self._fn_kwargs)
File "/usr/local/lib/python3.7/dist-packages/keras/losses.py", line 1863, in sparse_categorical_crossentropy
y_true, y_pred, from_logits=from_logits, axis=axis)
File "/usr/local/lib/python3.7/dist-packages/keras/backend.py", line 5203, in sparse_categorical_crossentropy
labels=target, logits=output)
Node: 'sparse_categorical_crossentropy/SparseSoftmaxCrossEntropyWithLogits/SparseSoftmaxCrossEntropyWithLogits'
logits and labels must have the same first dimension, got logits shape [128,7] and labels shape [7]
[[{{node sparse_categorical_crossentropy/SparseSoftmaxCrossEntropyWithLogits/SparseSoftmaxCrossEntropyWithLogits}}]] [Op:__inference_train_function_67923]