c-my/transformers
1
0 Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
Files
2397f958f99767290e8bc54f96e1df62f63d34af
transformers/notebooks/Comparing-TF-and-PT-models-MLM-NSP.ipynb
T
thomwolf 0bab55d5d5 [BIG] name change
2019-07-05 11:55:36 +02:00

169 KiB
Raw Blame History

Comparing TensorFlow (original) and PyTorch models

You can use this small notebook to check the conversion of the model's weights from the TensorFlow model to the PyTorch model. In the following, we compare the weights of the last layer on a simple example (in input.txt) but both models returns all the hidden layers so you can check every stage of the model.

To run this notebook, follow these instructions:

  • make sure that your Python environment has both TensorFlow and PyTorch installed,
  • download the original TensorFlow implementation,
  • download a pre-trained TensorFlow model as indicaded in the TensorFlow implementation readme,
  • run the script convert_tf_checkpoint_to_pytorch.py as indicated in the README to convert the pre-trained TensorFlow model to PyTorch.

If needed change the relative paths indicated in this notebook (at the beggining of Sections 1 and 2) to point to the relevent models and code.

In [1]:
import os
os.chdir('../')

1/ TensorFlow code

In [2]:
original_tf_inplem_dir = "./tensorflow_code/"
model_dir = "../google_models/uncased_L-12_H-768_A-12/"

vocab_file = model_dir + "vocab.txt"
bert_config_file = model_dir + "bert_config.json"
init_checkpoint = model_dir + "bert_model.ckpt"

input_file = "./samples/input.txt"
max_seq_length = 128
max_predictions_per_seq = 20

masked_lm_positions = [6]
In [3]:
import importlib.util
import sys
import tensorflow as tf
import pytorch_transformers as ppb

def del_all_flags(FLAGS):
    flags_dict = FLAGS._flags()    
    keys_list = [keys for keys in flags_dict]    
    for keys in keys_list:
        FLAGS.__delattr__(keys)

del_all_flags(tf.flags.FLAGS)
import tensorflow_code.extract_features as ef
del_all_flags(tf.flags.FLAGS)
import tensorflow_code.modeling as tfm
del_all_flags(tf.flags.FLAGS)
import tensorflow_code.tokenization as tft
del_all_flags(tf.flags.FLAGS)
import tensorflow_code.run_pretraining as rp
del_all_flags(tf.flags.FLAGS)
import tensorflow_code.create_pretraining_data as cpp
In [4]:
import re
class InputExample(object):
    """A single instance example."""

    def __init__(self, tokens, segment_ids, masked_lm_positions,
                 masked_lm_labels, is_random_next):
        self.tokens = tokens
        self.segment_ids = segment_ids
        self.masked_lm_positions = masked_lm_positions
        self.masked_lm_labels = masked_lm_labels
        self.is_random_next = is_random_next
    def __repr__(self):
        return '\n'.join(k + ":" + str(v) for k, v in self.__dict__.items())


def read_examples(input_file, tokenizer, masked_lm_positions):
    """Read a list of `InputExample`s from an input file."""
    examples = []
    unique_id = 0
    with tf.gfile.GFile(input_file, "r") as reader:
        while True:
            line = reader.readline()
            if not line:
                break
            line = line.strip()
            text_a = None
            text_b = None
            m = re.match(r"^(.*) \|\|\| (.*)$", line)
            if m is None:
                text_a = line
            else:
                text_a = m.group(1)
                text_b = m.group(2)
            tokens_a = tokenizer.tokenize(text_a)
            tokens_b = None
            if text_b:
                tokens_b = tokenizer.tokenize(text_b)
            tokens = tokens_a + tokens_b
            masked_lm_labels = []
            for m_pos in masked_lm_positions:
                masked_lm_labels.append(tokens[m_pos])
                tokens[m_pos] = '[MASK]'
            examples.append(
                InputExample(
                    tokens = tokens,
                    segment_ids = [0] * len(tokens_a) + [1] * len(tokens_b),
                    masked_lm_positions = masked_lm_positions,
                    masked_lm_labels = masked_lm_labels,
                    is_random_next = False))
            unique_id += 1
    return examples
In [5]:
bert_config = tfm.BertConfig.from_json_file(bert_config_file)
tokenizer = ppb.BertTokenizer(
    vocab_file=vocab_file, do_lower_case=True)
examples = read_examples(input_file, tokenizer, masked_lm_positions=masked_lm_positions)

print(examples[0])
tokens:['who', 'was', 'jim', 'henson', '?', 'jim', '[MASK]', 'was', 'a', 'puppet', '##eer']
segment_ids:[0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1]
masked_lm_positions:[6]
masked_lm_labels:['henson']
is_random_next:False
In [6]:
class InputFeatures(object):
    """A single set of features of data."""

    def __init__(self, input_ids, input_mask, segment_ids, masked_lm_positions,
                 masked_lm_ids, masked_lm_weights, next_sentence_label):
        self.input_ids = input_ids
        self.input_mask = input_mask
        self.segment_ids = segment_ids
        self.masked_lm_positions = masked_lm_positions
        self.masked_lm_ids = masked_lm_ids
        self.masked_lm_weights = masked_lm_weights
        self.next_sentence_labels = next_sentence_label

    def __repr__(self):
        return '\n'.join(k + ":" + str(v) for k, v in self.__dict__.items())

def pretraining_convert_examples_to_features(instances, tokenizer, max_seq_length,
                                 max_predictions_per_seq):
    """Create TF example files from `TrainingInstance`s."""
    features = []
    for (inst_index, instance) in enumerate(instances):
        input_ids = tokenizer.convert_tokens_to_ids(instance.tokens)
        input_mask = [1] * len(input_ids)
        segment_ids = list(instance.segment_ids)
        assert len(input_ids) <= max_seq_length

        while len(input_ids) < max_seq_length:
            input_ids.append(0)
            input_mask.append(0)
            segment_ids.append(0)

        assert len(input_ids) == max_seq_length
        assert len(input_mask) == max_seq_length
        assert len(segment_ids) == max_seq_length

        masked_lm_positions = list(instance.masked_lm_positions)
        masked_lm_ids = tokenizer.convert_tokens_to_ids(instance.masked_lm_labels)
        masked_lm_weights = [1.0] * len(masked_lm_ids)

        while len(masked_lm_positions) < max_predictions_per_seq:
            masked_lm_positions.append(0)
            masked_lm_ids.append(0)
            masked_lm_weights.append(0.0)

        next_sentence_label = 1 if instance.is_random_next else 0

        features.append(
            InputFeatures(input_ids, input_mask, segment_ids,
                          masked_lm_positions, masked_lm_ids,
                          masked_lm_weights, next_sentence_label))

        if inst_index < 5:
            tf.logging.info("*** Example ***")
            tf.logging.info("tokens: %s" % " ".join(
                [str(x) for x in instance.tokens]))
            tf.logging.info("features: %s" % str(features[-1]))
    return features
In [7]:
features = pretraining_convert_examples_to_features(
    instances=examples, max_seq_length=max_seq_length, 
    max_predictions_per_seq=max_predictions_per_seq, tokenizer=tokenizer)
INFO:tensorflow:*** Example ***

11/16/2018 11:02:34 - INFO - tensorflow -   *** Example ***

INFO:tensorflow:tokens: who was jim henson ? jim [MASK] was a puppet ##eer

11/16/2018 11:02:34 - INFO - tensorflow -   tokens: who was jim henson ? jim [MASK] was a puppet ##eer

INFO:tensorflow:features: input_ids:[2040, 2001, 3958, 27227, 1029, 3958, 103, 2001, 1037, 13997, 11510, 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]
input_mask:[1, 1, 1, 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]
segment_ids:[0, 0, 0, 0, 0, 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]
masked_lm_positions:[6, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
masked_lm_ids:[27227, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
masked_lm_weights:[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]
next_sentence_labels:0

11/16/2018 11:02:34 - INFO - tensorflow -   features: input_ids:[2040, 2001, 3958, 27227, 1029, 3958, 103, 2001, 1037, 13997, 11510, 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]
input_mask:[1, 1, 1, 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]
segment_ids:[0, 0, 0, 0, 0, 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]
masked_lm_positions:[6, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
masked_lm_ids:[27227, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
masked_lm_weights:[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]
next_sentence_labels:0
In [8]:
def input_fn_builder(features, seq_length, max_predictions_per_seq, tokenizer):
    """Creates an `input_fn` closure to be passed to TPUEstimator."""

    all_input_ids = []
    all_input_mask = []
    all_segment_ids = []
    all_masked_lm_positions = []
    all_masked_lm_ids = []
    all_masked_lm_weights = []
    all_next_sentence_labels = []

    for feature in features:
        all_input_ids.append(feature.input_ids)
        all_input_mask.append(feature.input_mask)
        all_segment_ids.append(feature.segment_ids)
        all_masked_lm_positions.append(feature.masked_lm_positions)
        all_masked_lm_ids.append(feature.masked_lm_ids)
        all_masked_lm_weights.append(feature.masked_lm_weights)
        all_next_sentence_labels.append(feature.next_sentence_labels)

    def input_fn(params):
        """The actual input function."""
        batch_size = params["batch_size"]

        num_examples = len(features)

        # This is for demo purposes and does NOT scale to large data sets. We do
        # not use Dataset.from_generator() because that uses tf.py_func which is
        # not TPU compatible. The right way to load data is with TFRecordReader.
        d = tf.data.Dataset.from_tensor_slices({
            "input_ids":
                tf.constant(
                    all_input_ids, shape=[num_examples, seq_length],
                    dtype=tf.int32),
            "input_mask":
                tf.constant(
                    all_input_mask,
                    shape=[num_examples, seq_length],
                    dtype=tf.int32),
            "segment_ids":
                tf.constant(
                    all_segment_ids,
                    shape=[num_examples, seq_length],
                    dtype=tf.int32),
            "masked_lm_positions":
                tf.constant(
                    all_masked_lm_positions,
                    shape=[num_examples, max_predictions_per_seq],
                    dtype=tf.int32),
        "masked_lm_ids":
                tf.constant(
                    all_masked_lm_ids,
                    shape=[num_examples, max_predictions_per_seq],
                    dtype=tf.int32),
        "masked_lm_weights":
                tf.constant(
                    all_masked_lm_weights,
                    shape=[num_examples, max_predictions_per_seq],
                    dtype=tf.float32),
        "next_sentence_labels":
                tf.constant(
                    all_next_sentence_labels,
                    shape=[num_examples, 1],
                    dtype=tf.int32),
        })

        d = d.batch(batch_size=batch_size, drop_remainder=False)
        return d

    return input_fn
In [9]:
def model_fn_builder(bert_config, init_checkpoint, learning_rate,
                     num_train_steps, num_warmup_steps, use_tpu,
                     use_one_hot_embeddings):
    """Returns `model_fn` closure for TPUEstimator."""

    def model_fn(features, labels, mode, params):  # pylint: disable=unused-argument
        """The `model_fn` for TPUEstimator."""

        tf.logging.info("*** Features ***")
        for name in sorted(features.keys()):
            tf.logging.info("  name = %s, shape = %s" % (name, features[name].shape))

        input_ids = features["input_ids"]
        input_mask = features["input_mask"]
        segment_ids = features["segment_ids"]
        masked_lm_positions = features["masked_lm_positions"]
        masked_lm_ids = features["masked_lm_ids"]
        masked_lm_weights = features["masked_lm_weights"]
        next_sentence_labels = features["next_sentence_labels"]

        is_training = (mode == tf.estimator.ModeKeys.TRAIN)

        model = tfm.BertModel(
            config=bert_config,
            is_training=is_training,
            input_ids=input_ids,
            input_mask=input_mask,
            token_type_ids=segment_ids,
            use_one_hot_embeddings=use_one_hot_embeddings)

        (masked_lm_loss,
         masked_lm_example_loss, masked_lm_log_probs) = rp.get_masked_lm_output(
            bert_config, model.get_sequence_output(), model.get_embedding_table(),
            masked_lm_positions, masked_lm_ids, masked_lm_weights)

        (next_sentence_loss, next_sentence_example_loss,
         next_sentence_log_probs) = rp.get_next_sentence_output(
            bert_config, model.get_pooled_output(), next_sentence_labels)

        total_loss = masked_lm_loss + next_sentence_loss

        tvars = tf.trainable_variables()

        initialized_variable_names = {}
        scaffold_fn = None
        if init_checkpoint:
            (assignment_map,
             initialized_variable_names) = tfm.get_assigment_map_from_checkpoint(
                tvars, init_checkpoint)
            if use_tpu:

                def tpu_scaffold():
                    tf.train.init_from_checkpoint(init_checkpoint, assignment_map)
                    return tf.train.Scaffold()

                scaffold_fn = tpu_scaffold
            else:
                tf.train.init_from_checkpoint(init_checkpoint, assignment_map)

        tf.logging.info("**** Trainable Variables ****")
        for var in tvars:
            init_string = ""
            if var.name in initialized_variable_names:
                init_string = ", *INIT_FROM_CKPT*"
            tf.logging.info("  name = %s, shape = %s%s", var.name, var.shape,
                            init_string)

        output_spec = None
        if mode == tf.estimator.ModeKeys.TRAIN:
            masked_lm_positions = features["masked_lm_positions"]
            masked_lm_ids = features["masked_lm_ids"]
            masked_lm_weights = features["masked_lm_weights"]
            next_sentence_labels = features["next_sentence_labels"]
            train_op = optimization.create_optimizer(
                total_loss, learning_rate, num_train_steps, num_warmup_steps, use_tpu)

            output_spec = tf.contrib.tpu.TPUEstimatorSpec(
                mode=mode,
                loss=total_loss,
                train_op=train_op,
                scaffold_fn=scaffold_fn)
        elif mode == tf.estimator.ModeKeys.EVAL:
            masked_lm_positions = features["masked_lm_positions"]
            masked_lm_ids = features["masked_lm_ids"]
            masked_lm_weights = features["masked_lm_weights"]
            next_sentence_labels = features["next_sentence_labels"]

            def metric_fn(masked_lm_example_loss, masked_lm_log_probs, masked_lm_ids,
                          masked_lm_weights, next_sentence_example_loss,
                          next_sentence_log_probs, next_sentence_labels):
                """Computes the loss and accuracy of the model."""
                masked_lm_log_probs = tf.reshape(masked_lm_log_probs,
                                                 [-1, masked_lm_log_probs.shape[-1]])
                masked_lm_predictions = tf.argmax(
                    masked_lm_log_probs, axis=-1, output_type=tf.int32)
                masked_lm_example_loss = tf.reshape(masked_lm_example_loss, [-1])
                masked_lm_ids = tf.reshape(masked_lm_ids, [-1])
                masked_lm_weights = tf.reshape(masked_lm_weights, [-1])
                masked_lm_accuracy = tf.metrics.accuracy(
                    labels=masked_lm_ids,
                    predictions=masked_lm_predictions,
                    weights=masked_lm_weights)
                masked_lm_mean_loss = tf.metrics.mean(
                    values=masked_lm_example_loss, weights=masked_lm_weights)

                next_sentence_log_probs = tf.reshape(
                    next_sentence_log_probs, [-1, next_sentence_log_probs.shape[-1]])
                next_sentence_predictions = tf.argmax(
                    next_sentence_log_probs, axis=-1, output_type=tf.int32)
                next_sentence_labels = tf.reshape(next_sentence_labels, [-1])
                next_sentence_accuracy = tf.metrics.accuracy(
                    labels=next_sentence_labels, predictions=next_sentence_predictions)
                next_sentence_mean_loss = tf.metrics.mean(
                    values=next_sentence_example_loss)

                return {
                    "masked_lm_accuracy": masked_lm_accuracy,
                    "masked_lm_loss": masked_lm_mean_loss,
                    "next_sentence_accuracy": next_sentence_accuracy,
                    "next_sentence_loss": next_sentence_mean_loss,
                }

            eval_metrics = (metric_fn, [
                masked_lm_example_loss, masked_lm_log_probs, masked_lm_ids,
                masked_lm_weights, next_sentence_example_loss,
                next_sentence_log_probs, next_sentence_labels
            ])
            output_spec = tf.contrib.tpu.TPUEstimatorSpec(
                mode=mode,
                loss=total_loss,
                eval_metrics=eval_metrics,
                scaffold_fn=scaffold_fn)
        elif mode == tf.estimator.ModeKeys.PREDICT:
            masked_lm_log_probs = tf.reshape(masked_lm_log_probs,
                                                [-1, masked_lm_log_probs.shape[-1]])
            masked_lm_predictions = tf.argmax(
                masked_lm_log_probs, axis=-1, output_type=tf.int32)

            next_sentence_log_probs = tf.reshape(
                next_sentence_log_probs, [-1, next_sentence_log_probs.shape[-1]])
            next_sentence_predictions = tf.argmax(
                next_sentence_log_probs, axis=-1, output_type=tf.int32)

            masked_lm_predictions = tf.reshape(masked_lm_predictions,
                                                [1, masked_lm_positions.shape[-1]])
            next_sentence_predictions = tf.reshape(next_sentence_predictions,
                                                [1, 1])

            predictions = {
                "masked_lm_predictions": masked_lm_predictions,
                "next_sentence_predictions": next_sentence_predictions
            }

            output_spec = tf.contrib.tpu.TPUEstimatorSpec(
                mode=mode, predictions=predictions, scaffold_fn=scaffold_fn)
            return output_spec
        else:
            raise ValueError("Only TRAIN, EVAL and PREDICT modes are supported: %s" % (mode))

        return output_spec

    return model_fn
In [10]:
is_per_host = tf.contrib.tpu.InputPipelineConfig.PER_HOST_V2
run_config = tf.contrib.tpu.RunConfig(
    master=None,
    tpu_config=tf.contrib.tpu.TPUConfig(
        num_shards=1,
        per_host_input_for_training=is_per_host))

model_fn = model_fn_builder(
    bert_config=bert_config,
    init_checkpoint=init_checkpoint,
    learning_rate=0,
    num_train_steps=1,
    num_warmup_steps=1,
    use_tpu=False,
    use_one_hot_embeddings=False)

# If TPU is not available, this will fall back to normal Estimator on CPU
# or GPU.
estimator = tf.contrib.tpu.TPUEstimator(
    use_tpu=False,
    model_fn=model_fn,
    config=run_config,
    predict_batch_size=1)

input_fn = input_fn_builder(
    features=features, seq_length=max_seq_length, max_predictions_per_seq=max_predictions_per_seq,
tokenizer=tokenizer)
WARNING:tensorflow:Estimator's model_fn (<function model_fn_builder.<locals>.model_fn at 0x12a864ae8>) includes params argument, but params are not passed to Estimator.

11/16/2018 11:02:40 - WARNING - tensorflow -   Estimator's model_fn (<function model_fn_builder.<locals>.model_fn at 0x12a864ae8>) includes params argument, but params are not passed to Estimator.

WARNING:tensorflow:Using temporary folder as model directory: /var/folders/yx/cw8n_njx3js5jksyw_qlp8p00000gn/T/tmp4x8r3x3d

11/16/2018 11:02:40 - WARNING - tensorflow -   Using temporary folder as model directory: /var/folders/yx/cw8n_njx3js5jksyw_qlp8p00000gn/T/tmp4x8r3x3d

INFO:tensorflow:Using config: {'_model_dir': '/var/folders/yx/cw8n_njx3js5jksyw_qlp8p00000gn/T/tmp4x8r3x3d', '_tf_random_seed': None, '_save_summary_steps': 100, '_save_checkpoints_steps': None, '_save_checkpoints_secs': 600, '_session_config': allow_soft_placement: true
graph_options {
  rewrite_options {
    meta_optimizer_iterations: ONE
  }
}
, '_keep_checkpoint_max': 5, '_keep_checkpoint_every_n_hours': 10000, '_log_step_count_steps': None, '_train_distribute': None, '_device_fn': None, '_protocol': None, '_eval_distribute': None, '_experimental_distribute': None, '_service': None, '_cluster_spec': <tensorflow.python.training.server_lib.ClusterSpec object at 0x12dbb5ac8>, '_task_type': 'worker', '_task_id': 0, '_global_id_in_cluster': 0, '_master': '', '_evaluation_master': '', '_is_chief': True, '_num_ps_replicas': 0, '_num_worker_replicas': 1, '_tpu_config': TPUConfig(iterations_per_loop=2, num_shards=1, num_cores_per_replica=None, per_host_input_for_training=3, tpu_job_name=None, initial_infeed_sleep_secs=None, input_partition_dims=None), '_cluster': None}

11/16/2018 11:02:40 - INFO - tensorflow -   Using config: {'_model_dir': '/var/folders/yx/cw8n_njx3js5jksyw_qlp8p00000gn/T/tmp4x8r3x3d', '_tf_random_seed': None, '_save_summary_steps': 100, '_save_checkpoints_steps': None, '_save_checkpoints_secs': 600, '_session_config': allow_soft_placement: true
graph_options {
  rewrite_options {
    meta_optimizer_iterations: ONE
  }
}
, '_keep_checkpoint_max': 5, '_keep_checkpoint_every_n_hours': 10000, '_log_step_count_steps': None, '_train_distribute': None, '_device_fn': None, '_protocol': None, '_eval_distribute': None, '_experimental_distribute': None, '_service': None, '_cluster_spec': <tensorflow.python.training.server_lib.ClusterSpec object at 0x12dbb5ac8>, '_task_type': 'worker', '_task_id': 0, '_global_id_in_cluster': 0, '_master': '', '_evaluation_master': '', '_is_chief': True, '_num_ps_replicas': 0, '_num_worker_replicas': 1, '_tpu_config': TPUConfig(iterations_per_loop=2, num_shards=1, num_cores_per_replica=None, per_host_input_for_training=3, tpu_job_name=None, initial_infeed_sleep_secs=None, input_partition_dims=None), '_cluster': None}

WARNING:tensorflow:Setting TPUConfig.num_shards==1 is an unsupported behavior. Please fix as soon as possible (leaving num_shards as None.

11/16/2018 11:02:40 - WARNING - tensorflow -   Setting TPUConfig.num_shards==1 is an unsupported behavior. Please fix as soon as possible (leaving num_shards as None.

INFO:tensorflow:_TPUContext: eval_on_tpu True

11/16/2018 11:02:40 - INFO - tensorflow -   _TPUContext: eval_on_tpu True

WARNING:tensorflow:eval_on_tpu ignored because use_tpu is False.

11/16/2018 11:02:40 - WARNING - tensorflow -   eval_on_tpu ignored because use_tpu is False.
In [11]:
tensorflow_all_out = []
for result in estimator.predict(input_fn, yield_single_examples=True):
    tensorflow_all_out.append(result)
INFO:tensorflow:Could not find trained model in model_dir: /var/folders/yx/cw8n_njx3js5jksyw_qlp8p00000gn/T/tmp4x8r3x3d, running initialization to predict.

11/16/2018 11:02:40 - INFO - tensorflow -   Could not find trained model in model_dir: /var/folders/yx/cw8n_njx3js5jksyw_qlp8p00000gn/T/tmp4x8r3x3d, running initialization to predict.

INFO:tensorflow:Calling model_fn.

11/16/2018 11:02:40 - INFO - tensorflow -   Calling model_fn.

INFO:tensorflow:Running infer on CPU

11/16/2018 11:02:40 - INFO - tensorflow -   Running infer on CPU

INFO:tensorflow:*** Features ***

11/16/2018 11:02:40 - INFO - tensorflow -   *** Features ***

INFO:tensorflow:  name = input_ids, shape = (?, 128)

11/16/2018 11:02:40 - INFO - tensorflow -     name = input_ids, shape = (?, 128)

INFO:tensorflow:  name = input_mask, shape = (?, 128)

11/16/2018 11:02:40 - INFO - tensorflow -     name = input_mask, shape = (?, 128)

INFO:tensorflow:  name = masked_lm_ids, shape = (?, 20)

11/16/2018 11:02:40 - INFO - tensorflow -     name = masked_lm_ids, shape = (?, 20)

INFO:tensorflow:  name = masked_lm_positions, shape = (?, 20)

11/16/2018 11:02:40 - INFO - tensorflow -     name = masked_lm_positions, shape = (?, 20)

INFO:tensorflow:  name = masked_lm_weights, shape = (?, 20)

11/16/2018 11:02:40 - INFO - tensorflow -     name = masked_lm_weights, shape = (?, 20)

INFO:tensorflow:  name = next_sentence_labels, shape = (?, 1)

11/16/2018 11:02:40 - INFO - tensorflow -     name = next_sentence_labels, shape = (?, 1)

INFO:tensorflow:  name = segment_ids, shape = (?, 128)

11/16/2018 11:02:40 - INFO - tensorflow -     name = segment_ids, shape = (?, 128)

INFO:tensorflow:**** Trainable Variables ****

11/16/2018 11:02:43 - INFO - tensorflow -   **** Trainable Variables ****

INFO:tensorflow:  name = bert/embeddings/word_embeddings:0, shape = (30522, 768), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/embeddings/word_embeddings:0, shape = (30522, 768), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/embeddings/token_type_embeddings:0, shape = (2, 768), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/embeddings/token_type_embeddings:0, shape = (2, 768), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/embeddings/position_embeddings:0, shape = (512, 768), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/embeddings/position_embeddings:0, shape = (512, 768), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/embeddings/LayerNorm/beta:0, shape = (768,), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/embeddings/LayerNorm/beta:0, shape = (768,), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/embeddings/LayerNorm/gamma:0, shape = (768,), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/embeddings/LayerNorm/gamma:0, shape = (768,), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_0/attention/self/query/kernel:0, shape = (768, 768), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_0/attention/self/query/kernel:0, shape = (768, 768), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_0/attention/self/query/bias:0, shape = (768,), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_0/attention/self/query/bias:0, shape = (768,), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_0/attention/self/key/kernel:0, shape = (768, 768), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_0/attention/self/key/kernel:0, shape = (768, 768), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_0/attention/self/key/bias:0, shape = (768,), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_0/attention/self/key/bias:0, shape = (768,), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_0/attention/self/value/kernel:0, shape = (768, 768), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_0/attention/self/value/kernel:0, shape = (768, 768), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_0/attention/self/value/bias:0, shape = (768,), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_0/attention/self/value/bias:0, shape = (768,), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_0/attention/output/dense/kernel:0, shape = (768, 768), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_0/attention/output/dense/kernel:0, shape = (768, 768), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_0/attention/output/dense/bias:0, shape = (768,), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_0/attention/output/dense/bias:0, shape = (768,), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_0/attention/output/LayerNorm/beta:0, shape = (768,), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_0/attention/output/LayerNorm/beta:0, shape = (768,), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_0/attention/output/LayerNorm/gamma:0, shape = (768,), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_0/attention/output/LayerNorm/gamma:0, shape = (768,), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_0/intermediate/dense/kernel:0, shape = (768, 3072), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_0/intermediate/dense/kernel:0, shape = (768, 3072), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_0/intermediate/dense/bias:0, shape = (3072,), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_0/intermediate/dense/bias:0, shape = (3072,), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_0/output/dense/kernel:0, shape = (3072, 768), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_0/output/dense/kernel:0, shape = (3072, 768), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_0/output/dense/bias:0, shape = (768,), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_0/output/dense/bias:0, shape = (768,), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_0/output/LayerNorm/beta:0, shape = (768,), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_0/output/LayerNorm/beta:0, shape = (768,), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_0/output/LayerNorm/gamma:0, shape = (768,), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_0/output/LayerNorm/gamma:0, shape = (768,), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_1/attention/self/query/kernel:0, shape = (768, 768), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_1/attention/self/query/kernel:0, shape = (768, 768), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_1/attention/self/query/bias:0, shape = (768,), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_1/attention/self/query/bias:0, shape = (768,), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_1/attention/self/key/kernel:0, shape = (768, 768), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_1/attention/self/key/kernel:0, shape = (768, 768), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_1/attention/self/key/bias:0, shape = (768,), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_1/attention/self/key/bias:0, shape = (768,), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_1/attention/self/value/kernel:0, shape = (768, 768), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_1/attention/self/value/kernel:0, shape = (768, 768), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_1/attention/self/value/bias:0, shape = (768,), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_1/attention/self/value/bias:0, shape = (768,), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_1/attention/output/dense/kernel:0, shape = (768, 768), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_1/attention/output/dense/kernel:0, shape = (768, 768), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_1/attention/output/dense/bias:0, shape = (768,), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_1/attention/output/dense/bias:0, shape = (768,), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_1/attention/output/LayerNorm/beta:0, shape = (768,), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_1/attention/output/LayerNorm/beta:0, shape = (768,), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_1/attention/output/LayerNorm/gamma:0, shape = (768,), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_1/attention/output/LayerNorm/gamma:0, shape = (768,), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_1/intermediate/dense/kernel:0, shape = (768, 3072), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_1/intermediate/dense/kernel:0, shape = (768, 3072), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_1/intermediate/dense/bias:0, shape = (3072,), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_1/intermediate/dense/bias:0, shape = (3072,), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_1/output/dense/kernel:0, shape = (3072, 768), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_1/output/dense/kernel:0, shape = (3072, 768), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_1/output/dense/bias:0, shape = (768,), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_1/output/dense/bias:0, shape = (768,), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_1/output/LayerNorm/beta:0, shape = (768,), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_1/output/LayerNorm/beta:0, shape = (768,), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_1/output/LayerNorm/gamma:0, shape = (768,), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_1/output/LayerNorm/gamma:0, shape = (768,), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_2/attention/self/query/kernel:0, shape = (768, 768), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_2/attention/self/query/kernel:0, shape = (768, 768), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_2/attention/self/query/bias:0, shape = (768,), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_2/attention/self/query/bias:0, shape = (768,), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_2/attention/self/key/kernel:0, shape = (768, 768), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_2/attention/self/key/kernel:0, shape = (768, 768), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_2/attention/self/key/bias:0, shape = (768,), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_2/attention/self/key/bias:0, shape = (768,), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_2/attention/self/value/kernel:0, shape = (768, 768), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_2/attention/self/value/kernel:0, shape = (768, 768), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_2/attention/self/value/bias:0, shape = (768,), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_2/attention/self/value/bias:0, shape = (768,), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_2/attention/output/dense/kernel:0, shape = (768, 768), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_2/attention/output/dense/kernel:0, shape = (768, 768), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_2/attention/output/dense/bias:0, shape = (768,), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_2/attention/output/dense/bias:0, shape = (768,), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_2/attention/output/LayerNorm/beta:0, shape = (768,), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_2/attention/output/LayerNorm/beta:0, shape = (768,), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_2/attention/output/LayerNorm/gamma:0, shape = (768,), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_2/attention/output/LayerNorm/gamma:0, shape = (768,), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_2/intermediate/dense/kernel:0, shape = (768, 3072), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_2/intermediate/dense/kernel:0, shape = (768, 3072), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_2/intermediate/dense/bias:0, shape = (3072,), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_2/intermediate/dense/bias:0, shape = (3072,), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_2/output/dense/kernel:0, shape = (3072, 768), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_2/output/dense/kernel:0, shape = (3072, 768), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_2/output/dense/bias:0, shape = (768,), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_2/output/dense/bias:0, shape = (768,), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_2/output/LayerNorm/beta:0, shape = (768,), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_2/output/LayerNorm/beta:0, shape = (768,), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_2/output/LayerNorm/gamma:0, shape = (768,), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_2/output/LayerNorm/gamma:0, shape = (768,), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_3/attention/self/query/kernel:0, shape = (768, 768), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_3/attention/self/query/kernel:0, shape = (768, 768), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_3/attention/self/query/bias:0, shape = (768,), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_3/attention/self/query/bias:0, shape = (768,), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_3/attention/self/key/kernel:0, shape = (768, 768), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_3/attention/self/key/kernel:0, shape = (768, 768), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_3/attention/self/key/bias:0, shape = (768,), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_3/attention/self/key/bias:0, shape = (768,), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_3/attention/self/value/kernel:0, shape = (768, 768), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_3/attention/self/value/kernel:0, shape = (768, 768), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_3/attention/self/value/bias:0, shape = (768,), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_3/attention/self/value/bias:0, shape = (768,), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_3/attention/output/dense/kernel:0, shape = (768, 768), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_3/attention/output/dense/kernel:0, shape = (768, 768), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_3/attention/output/dense/bias:0, shape = (768,), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_3/attention/output/dense/bias:0, shape = (768,), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_3/attention/output/LayerNorm/beta:0, shape = (768,), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_3/attention/output/LayerNorm/beta:0, shape = (768,), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_3/attention/output/LayerNorm/gamma:0, shape = (768,), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_3/attention/output/LayerNorm/gamma:0, shape = (768,), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_3/intermediate/dense/kernel:0, shape = (768, 3072), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_3/intermediate/dense/kernel:0, shape = (768, 3072), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_3/intermediate/dense/bias:0, shape = (3072,), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_3/intermediate/dense/bias:0, shape = (3072,), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_3/output/dense/kernel:0, shape = (3072, 768), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_3/output/dense/kernel:0, shape = (3072, 768), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_3/output/dense/bias:0, shape = (768,), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_3/output/dense/bias:0, shape = (768,), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_3/output/LayerNorm/beta:0, shape = (768,), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_3/output/LayerNorm/beta:0, shape = (768,), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_3/output/LayerNorm/gamma:0, shape = (768,), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_3/output/LayerNorm/gamma:0, shape = (768,), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_4/attention/self/query/kernel:0, shape = (768, 768), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_4/attention/self/query/kernel:0, shape = (768, 768), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_4/attention/self/query/bias:0, shape = (768,), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_4/attention/self/query/bias:0, shape = (768,), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_4/attention/self/key/kernel:0, shape = (768, 768), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_4/attention/self/key/kernel:0, shape = (768, 768), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_4/attention/self/key/bias:0, shape = (768,), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_4/attention/self/key/bias:0, shape = (768,), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_4/attention/self/value/kernel:0, shape = (768, 768), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_4/attention/self/value/kernel:0, shape = (768, 768), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_4/attention/self/value/bias:0, shape = (768,), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_4/attention/self/value/bias:0, shape = (768,), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_4/attention/output/dense/kernel:0, shape = (768, 768), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_4/attention/output/dense/kernel:0, shape = (768, 768), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_4/attention/output/dense/bias:0, shape = (768,), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_4/attention/output/dense/bias:0, shape = (768,), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_4/attention/output/LayerNorm/beta:0, shape = (768,), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_4/attention/output/LayerNorm/beta:0, shape = (768,), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_4/attention/output/LayerNorm/gamma:0, shape = (768,), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_4/attention/output/LayerNorm/gamma:0, shape = (768,), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_4/intermediate/dense/kernel:0, shape = (768, 3072), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_4/intermediate/dense/kernel:0, shape = (768, 3072), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_4/intermediate/dense/bias:0, shape = (3072,), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_4/intermediate/dense/bias:0, shape = (3072,), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_4/output/dense/kernel:0, shape = (3072, 768), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_4/output/dense/kernel:0, shape = (3072, 768), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_4/output/dense/bias:0, shape = (768,), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_4/output/dense/bias:0, shape = (768,), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_4/output/LayerNorm/beta:0, shape = (768,), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_4/output/LayerNorm/beta:0, shape = (768,), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_4/output/LayerNorm/gamma:0, shape = (768,), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_4/output/LayerNorm/gamma:0, shape = (768,), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_5/attention/self/query/kernel:0, shape = (768, 768), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_5/attention/self/query/kernel:0, shape = (768, 768), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_5/attention/self/query/bias:0, shape = (768,), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_5/attention/self/query/bias:0, shape = (768,), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_5/attention/self/key/kernel:0, shape = (768, 768), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_5/attention/self/key/kernel:0, shape = (768, 768), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_5/attention/self/key/bias:0, shape = (768,), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_5/attention/self/key/bias:0, shape = (768,), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_5/attention/self/value/kernel:0, shape = (768, 768), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_5/attention/self/value/kernel:0, shape = (768, 768), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_5/attention/self/value/bias:0, shape = (768,), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_5/attention/self/value/bias:0, shape = (768,), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_5/attention/output/dense/kernel:0, shape = (768, 768), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_5/attention/output/dense/kernel:0, shape = (768, 768), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_5/attention/output/dense/bias:0, shape = (768,), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_5/attention/output/dense/bias:0, shape = (768,), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_5/attention/output/LayerNorm/beta:0, shape = (768,), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_5/attention/output/LayerNorm/beta:0, shape = (768,), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_5/attention/output/LayerNorm/gamma:0, shape = (768,), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_5/attention/output/LayerNorm/gamma:0, shape = (768,), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_5/intermediate/dense/kernel:0, shape = (768, 3072), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_5/intermediate/dense/kernel:0, shape = (768, 3072), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_5/intermediate/dense/bias:0, shape = (3072,), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_5/intermediate/dense/bias:0, shape = (3072,), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_5/output/dense/kernel:0, shape = (3072, 768), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_5/output/dense/kernel:0, shape = (3072, 768), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_5/output/dense/bias:0, shape = (768,), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_5/output/dense/bias:0, shape = (768,), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_5/output/LayerNorm/beta:0, shape = (768,), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_5/output/LayerNorm/beta:0, shape = (768,), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_5/output/LayerNorm/gamma:0, shape = (768,), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_5/output/LayerNorm/gamma:0, shape = (768,), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_6/attention/self/query/kernel:0, shape = (768, 768), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_6/attention/self/query/kernel:0, shape = (768, 768), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_6/attention/self/query/bias:0, shape = (768,), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_6/attention/self/query/bias:0, shape = (768,), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_6/attention/self/key/kernel:0, shape = (768, 768), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_6/attention/self/key/kernel:0, shape = (768, 768), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_6/attention/self/key/bias:0, shape = (768,), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_6/attention/self/key/bias:0, shape = (768,), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_6/attention/self/value/kernel:0, shape = (768, 768), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_6/attention/self/value/kernel:0, shape = (768, 768), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_6/attention/self/value/bias:0, shape = (768,), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_6/attention/self/value/bias:0, shape = (768,), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_6/attention/output/dense/kernel:0, shape = (768, 768), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_6/attention/output/dense/kernel:0, shape = (768, 768), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_6/attention/output/dense/bias:0, shape = (768,), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_6/attention/output/dense/bias:0, shape = (768,), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_6/attention/output/LayerNorm/beta:0, shape = (768,), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_6/attention/output/LayerNorm/beta:0, shape = (768,), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_6/attention/output/LayerNorm/gamma:0, shape = (768,), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_6/attention/output/LayerNorm/gamma:0, shape = (768,), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_6/intermediate/dense/kernel:0, shape = (768, 3072), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_6/intermediate/dense/kernel:0, shape = (768, 3072), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_6/intermediate/dense/bias:0, shape = (3072,), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_6/intermediate/dense/bias:0, shape = (3072,), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_6/output/dense/kernel:0, shape = (3072, 768), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_6/output/dense/kernel:0, shape = (3072, 768), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_6/output/dense/bias:0, shape = (768,), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_6/output/dense/bias:0, shape = (768,), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_6/output/LayerNorm/beta:0, shape = (768,), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_6/output/LayerNorm/beta:0, shape = (768,), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_6/output/LayerNorm/gamma:0, shape = (768,), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_6/output/LayerNorm/gamma:0, shape = (768,), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_7/attention/self/query/kernel:0, shape = (768, 768), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_7/attention/self/query/kernel:0, shape = (768, 768), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_7/attention/self/query/bias:0, shape = (768,), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_7/attention/self/query/bias:0, shape = (768,), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_7/attention/self/key/kernel:0, shape = (768, 768), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_7/attention/self/key/kernel:0, shape = (768, 768), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_7/attention/self/key/bias:0, shape = (768,), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_7/attention/self/key/bias:0, shape = (768,), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_7/attention/self/value/kernel:0, shape = (768, 768), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_7/attention/self/value/kernel:0, shape = (768, 768), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_7/attention/self/value/bias:0, shape = (768,), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_7/attention/self/value/bias:0, shape = (768,), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_7/attention/output/dense/kernel:0, shape = (768, 768), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_7/attention/output/dense/kernel:0, shape = (768, 768), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_7/attention/output/dense/bias:0, shape = (768,), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_7/attention/output/dense/bias:0, shape = (768,), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_7/attention/output/LayerNorm/beta:0, shape = (768,), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_7/attention/output/LayerNorm/beta:0, shape = (768,), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_7/attention/output/LayerNorm/gamma:0, shape = (768,), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_7/attention/output/LayerNorm/gamma:0, shape = (768,), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_7/intermediate/dense/kernel:0, shape = (768, 3072), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_7/intermediate/dense/kernel:0, shape = (768, 3072), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_7/intermediate/dense/bias:0, shape = (3072,), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_7/intermediate/dense/bias:0, shape = (3072,), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_7/output/dense/kernel:0, shape = (3072, 768), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_7/output/dense/kernel:0, shape = (3072, 768), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_7/output/dense/bias:0, shape = (768,), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_7/output/dense/bias:0, shape = (768,), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_7/output/LayerNorm/beta:0, shape = (768,), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_7/output/LayerNorm/beta:0, shape = (768,), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_7/output/LayerNorm/gamma:0, shape = (768,), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_7/output/LayerNorm/gamma:0, shape = (768,), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_8/attention/self/query/kernel:0, shape = (768, 768), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_8/attention/self/query/kernel:0, shape = (768, 768), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_8/attention/self/query/bias:0, shape = (768,), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_8/attention/self/query/bias:0, shape = (768,), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_8/attention/self/key/kernel:0, shape = (768, 768), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_8/attention/self/key/kernel:0, shape = (768, 768), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_8/attention/self/key/bias:0, shape = (768,), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_8/attention/self/key/bias:0, shape = (768,), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_8/attention/self/value/kernel:0, shape = (768, 768), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_8/attention/self/value/kernel:0, shape = (768, 768), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_8/attention/self/value/bias:0, shape = (768,), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_8/attention/self/value/bias:0, shape = (768,), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_8/attention/output/dense/kernel:0, shape = (768, 768), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_8/attention/output/dense/kernel:0, shape = (768, 768), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_8/attention/output/dense/bias:0, shape = (768,), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_8/attention/output/dense/bias:0, shape = (768,), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_8/attention/output/LayerNorm/beta:0, shape = (768,), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_8/attention/output/LayerNorm/beta:0, shape = (768,), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_8/attention/output/LayerNorm/gamma:0, shape = (768,), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_8/attention/output/LayerNorm/gamma:0, shape = (768,), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_8/intermediate/dense/kernel:0, shape = (768, 3072), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_8/intermediate/dense/kernel:0, shape = (768, 3072), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_8/intermediate/dense/bias:0, shape = (3072,), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_8/intermediate/dense/bias:0, shape = (3072,), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_8/output/dense/kernel:0, shape = (3072, 768), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_8/output/dense/kernel:0, shape = (3072, 768), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_8/output/dense/bias:0, shape = (768,), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_8/output/dense/bias:0, shape = (768,), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_8/output/LayerNorm/beta:0, shape = (768,), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_8/output/LayerNorm/beta:0, shape = (768,), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_8/output/LayerNorm/gamma:0, shape = (768,), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_8/output/LayerNorm/gamma:0, shape = (768,), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_9/attention/self/query/kernel:0, shape = (768, 768), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_9/attention/self/query/kernel:0, shape = (768, 768), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_9/attention/self/query/bias:0, shape = (768,), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_9/attention/self/query/bias:0, shape = (768,), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_9/attention/self/key/kernel:0, shape = (768, 768), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_9/attention/self/key/kernel:0, shape = (768, 768), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_9/attention/self/key/bias:0, shape = (768,), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_9/attention/self/key/bias:0, shape = (768,), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_9/attention/self/value/kernel:0, shape = (768, 768), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_9/attention/self/value/kernel:0, shape = (768, 768), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_9/attention/self/value/bias:0, shape = (768,), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_9/attention/self/value/bias:0, shape = (768,), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_9/attention/output/dense/kernel:0, shape = (768, 768), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_9/attention/output/dense/kernel:0, shape = (768, 768), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_9/attention/output/dense/bias:0, shape = (768,), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_9/attention/output/dense/bias:0, shape = (768,), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_9/attention/output/LayerNorm/beta:0, shape = (768,), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_9/attention/output/LayerNorm/beta:0, shape = (768,), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_9/attention/output/LayerNorm/gamma:0, shape = (768,), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_9/attention/output/LayerNorm/gamma:0, shape = (768,), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_9/intermediate/dense/kernel:0, shape = (768, 3072), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_9/intermediate/dense/kernel:0, shape = (768, 3072), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_9/intermediate/dense/bias:0, shape = (3072,), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_9/intermediate/dense/bias:0, shape = (3072,), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_9/output/dense/kernel:0, shape = (3072, 768), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_9/output/dense/kernel:0, shape = (3072, 768), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_9/output/dense/bias:0, shape = (768,), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_9/output/dense/bias:0, shape = (768,), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_9/output/LayerNorm/beta:0, shape = (768,), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_9/output/LayerNorm/beta:0, shape = (768,), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_9/output/LayerNorm/gamma:0, shape = (768,), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_9/output/LayerNorm/gamma:0, shape = (768,), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_10/attention/self/query/kernel:0, shape = (768, 768), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_10/attention/self/query/kernel:0, shape = (768, 768), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_10/attention/self/query/bias:0, shape = (768,), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_10/attention/self/query/bias:0, shape = (768,), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_10/attention/self/key/kernel:0, shape = (768, 768), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_10/attention/self/key/kernel:0, shape = (768, 768), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_10/attention/self/key/bias:0, shape = (768,), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_10/attention/self/key/bias:0, shape = (768,), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_10/attention/self/value/kernel:0, shape = (768, 768), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_10/attention/self/value/kernel:0, shape = (768, 768), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_10/attention/self/value/bias:0, shape = (768,), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_10/attention/self/value/bias:0, shape = (768,), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_10/attention/output/dense/kernel:0, shape = (768, 768), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_10/attention/output/dense/kernel:0, shape = (768, 768), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_10/attention/output/dense/bias:0, shape = (768,), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_10/attention/output/dense/bias:0, shape = (768,), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_10/attention/output/LayerNorm/beta:0, shape = (768,), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_10/attention/output/LayerNorm/beta:0, shape = (768,), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_10/attention/output/LayerNorm/gamma:0, shape = (768,), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_10/attention/output/LayerNorm/gamma:0, shape = (768,), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_10/intermediate/dense/kernel:0, shape = (768, 3072), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_10/intermediate/dense/kernel:0, shape = (768, 3072), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_10/intermediate/dense/bias:0, shape = (3072,), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_10/intermediate/dense/bias:0, shape = (3072,), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_10/output/dense/kernel:0, shape = (3072, 768), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_10/output/dense/kernel:0, shape = (3072, 768), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_10/output/dense/bias:0, shape = (768,), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_10/output/dense/bias:0, shape = (768,), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_10/output/LayerNorm/beta:0, shape = (768,), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_10/output/LayerNorm/beta:0, shape = (768,), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_10/output/LayerNorm/gamma:0, shape = (768,), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_10/output/LayerNorm/gamma:0, shape = (768,), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_11/attention/self/query/kernel:0, shape = (768, 768), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_11/attention/self/query/kernel:0, shape = (768, 768), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_11/attention/self/query/bias:0, shape = (768,), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_11/attention/self/query/bias:0, shape = (768,), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_11/attention/self/key/kernel:0, shape = (768, 768), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_11/attention/self/key/kernel:0, shape = (768, 768), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_11/attention/self/key/bias:0, shape = (768,), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_11/attention/self/key/bias:0, shape = (768,), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_11/attention/self/value/kernel:0, shape = (768, 768), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_11/attention/self/value/kernel:0, shape = (768, 768), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_11/attention/self/value/bias:0, shape = (768,), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_11/attention/self/value/bias:0, shape = (768,), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_11/attention/output/dense/kernel:0, shape = (768, 768), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_11/attention/output/dense/kernel:0, shape = (768, 768), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_11/attention/output/dense/bias:0, shape = (768,), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_11/attention/output/dense/bias:0, shape = (768,), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_11/attention/output/LayerNorm/beta:0, shape = (768,), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_11/attention/output/LayerNorm/beta:0, shape = (768,), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_11/attention/output/LayerNorm/gamma:0, shape = (768,), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_11/attention/output/LayerNorm/gamma:0, shape = (768,), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_11/intermediate/dense/kernel:0, shape = (768, 3072), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_11/intermediate/dense/kernel:0, shape = (768, 3072), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_11/intermediate/dense/bias:0, shape = (3072,), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_11/intermediate/dense/bias:0, shape = (3072,), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_11/output/dense/kernel:0, shape = (3072, 768), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_11/output/dense/kernel:0, shape = (3072, 768), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_11/output/dense/bias:0, shape = (768,), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_11/output/dense/bias:0, shape = (768,), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_11/output/LayerNorm/beta:0, shape = (768,), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_11/output/LayerNorm/beta:0, shape = (768,), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/encoder/layer_11/output/LayerNorm/gamma:0, shape = (768,), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/encoder/layer_11/output/LayerNorm/gamma:0, shape = (768,), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/pooler/dense/kernel:0, shape = (768, 768), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/pooler/dense/kernel:0, shape = (768, 768), *INIT_FROM_CKPT*

INFO:tensorflow:  name = bert/pooler/dense/bias:0, shape = (768,), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = bert/pooler/dense/bias:0, shape = (768,), *INIT_FROM_CKPT*

INFO:tensorflow:  name = cls/predictions/transform/dense/kernel:0, shape = (768, 768), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = cls/predictions/transform/dense/kernel:0, shape = (768, 768), *INIT_FROM_CKPT*

INFO:tensorflow:  name = cls/predictions/transform/dense/bias:0, shape = (768,), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = cls/predictions/transform/dense/bias:0, shape = (768,), *INIT_FROM_CKPT*

INFO:tensorflow:  name = cls/predictions/transform/LayerNorm/beta:0, shape = (768,), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = cls/predictions/transform/LayerNorm/beta:0, shape = (768,), *INIT_FROM_CKPT*

INFO:tensorflow:  name = cls/predictions/transform/LayerNorm/gamma:0, shape = (768,), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = cls/predictions/transform/LayerNorm/gamma:0, shape = (768,), *INIT_FROM_CKPT*

INFO:tensorflow:  name = cls/predictions/output_bias:0, shape = (30522,), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = cls/predictions/output_bias:0, shape = (30522,), *INIT_FROM_CKPT*

INFO:tensorflow:  name = cls/seq_relationship/output_weights:0, shape = (2, 768), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = cls/seq_relationship/output_weights:0, shape = (2, 768), *INIT_FROM_CKPT*

INFO:tensorflow:  name = cls/seq_relationship/output_bias:0, shape = (2,), *INIT_FROM_CKPT*

11/16/2018 11:02:43 - INFO - tensorflow -     name = cls/seq_relationship/output_bias:0, shape = (2,), *INIT_FROM_CKPT*

INFO:tensorflow:Done calling model_fn.

11/16/2018 11:02:43 - INFO - tensorflow -   Done calling model_fn.

INFO:tensorflow:Graph was finalized.

11/16/2018 11:02:44 - INFO - tensorflow -   Graph was finalized.

INFO:tensorflow:Running local_init_op.

11/16/2018 11:02:45 - INFO - tensorflow -   Running local_init_op.

INFO:tensorflow:Done running local_init_op.

11/16/2018 11:02:45 - INFO - tensorflow -   Done running local_init_op.

INFO:tensorflow:prediction_loop marked as finished

11/16/2018 11:02:46 - INFO - tensorflow -   prediction_loop marked as finished

INFO:tensorflow:prediction_loop marked as finished

11/16/2018 11:02:46 - INFO - tensorflow -   prediction_loop marked as finished
In [12]:
print(len(tensorflow_all_out))
print(len(tensorflow_all_out[0]))
print(tensorflow_all_out[0].keys())
print("masked_lm_predictions", tensorflow_all_out[0]['masked_lm_predictions'])
print("predicted token", tokenizer.convert_ids_to_tokens(tensorflow_all_out[0]['masked_lm_predictions']))
1
2
dict_keys(['masked_lm_predictions', 'next_sentence_predictions'])
masked_lm_predictions [27227  1010  1010  1010  1010  1010  1010  1010  1010  1010  1010  1010
  1010  1010  1010  1010  1010  1010  1010  1010]
predicted token ['henson', ',', ',', ',', ',', ',', ',', ',', ',', ',', ',', ',', ',', ',', ',', ',', ',', ',', ',', ',']
In [13]:
tensorflow_outputs = tokenizer.convert_ids_to_tokens(tensorflow_all_out[0]['masked_lm_predictions'])[:len(masked_lm_positions)]
print("tensorflow_output:", tensorflow_outputs)
tensorflow_output: ['henson']

2/ PyTorch code

In [14]:
from examples import extract_features
from examples.extract_features import *
In [15]:
init_checkpoint_pt = "../google_models/uncased_L-12_H-768_A-12/pytorch_model.bin"
In [16]:
device = torch.device("cpu")
model = ppb.BertForPreTraining.from_pretrained('bert-base-uncased')
model.to(device)
Out [16]:
11/16/2018 11:03:05 - INFO - pytorch_transformers.modeling_bert -   loading archive file https://s3.amazonaws.com/models.huggingface.co/bert/bert-base-uncased.tar.gz from cache at /Users/thomaswolf/.pytorch_transformers/9c41111e2de84547a463fd39217199738d1e3deb72d4fec4399e6e241983c6f0.ae3cef932725ca7a30cdcb93fc6e09150a55e2a130ec7af63975a16c153ae2ba
11/16/2018 11:03:05 - INFO - pytorch_transformers.modeling_bert -   extracting archive file /Users/thomaswolf/.pytorch_transformers/9c41111e2de84547a463fd39217199738d1e3deb72d4fec4399e6e241983c6f0.ae3cef932725ca7a30cdcb93fc6e09150a55e2a130ec7af63975a16c153ae2ba to temp dir /var/folders/yx/cw8n_njx3js5jksyw_qlp8p00000gn/T/tmpaqgsm566
11/16/2018 11:03:08 - INFO - pytorch_transformers.modeling_bert -   Model config {
  "attention_probs_dropout_prob": 0.1,
  "hidden_act": "gelu",
  "hidden_dropout_prob": 0.1,
  "hidden_size": 768,
  "initializer_range": 0.02,
  "intermediate_size": 3072,
  "max_position_embeddings": 512,
  "num_attention_heads": 12,
  "num_hidden_layers": 12,
  "type_vocab_size": 2,
  "vocab_size": 30522
}


BertForPreTraining(
  (bert): BertModel(
    (embeddings): BertEmbeddings(
      (word_embeddings): Embedding(30522, 768)
      (position_embeddings): Embedding(512, 768)
      (token_type_embeddings): Embedding(2, 768)
      (LayerNorm): BertLayerNorm()
      (dropout): Dropout(p=0.1)
    )
    (encoder): BertEncoder(
      (layer): ModuleList(
        (0): BertLayer(
          (attention): BertAttention(
            (self): BertSelfAttention(
              (query): Linear(in_features=768, out_features=768, bias=True)
              (key): Linear(in_features=768, out_features=768, bias=True)
              (value): Linear(in_features=768, out_features=768, bias=True)
              (dropout): Dropout(p=0.1)
            )
            (output): BertSelfOutput(
              (dense): Linear(in_features=768, out_features=768, bias=True)
              (LayerNorm): BertLayerNorm()
              (dropout): Dropout(p=0.1)
            )
          )
          (intermediate): BertIntermediate(
            (dense): Linear(in_features=768, out_features=3072, bias=True)
          )
          (output): BertOutput(
            (dense): Linear(in_features=3072, out_features=768, bias=True)
            (LayerNorm): BertLayerNorm()
            (dropout): Dropout(p=0.1)
          )
        )
        (1): BertLayer(
          (attention): BertAttention(
            (self): BertSelfAttention(
              (query): Linear(in_features=768, out_features=768, bias=True)
              (key): Linear(in_features=768, out_features=768, bias=True)
              (value): Linear(in_features=768, out_features=768, bias=True)
              (dropout): Dropout(p=0.1)
            )
            (output): BertSelfOutput(
              (dense): Linear(in_features=768, out_features=768, bias=True)
              (LayerNorm): BertLayerNorm()
              (dropout): Dropout(p=0.1)
            )
          )
          (intermediate): BertIntermediate(
            (dense): Linear(in_features=768, out_features=3072, bias=True)
          )
          (output): BertOutput(
            (dense): Linear(in_features=3072, out_features=768, bias=True)
            (LayerNorm): BertLayerNorm()
            (dropout): Dropout(p=0.1)
          )
        )
        (2): BertLayer(
          (attention): BertAttention(
            (self): BertSelfAttention(
              (query): Linear(in_features=768, out_features=768, bias=True)
              (key): Linear(in_features=768, out_features=768, bias=True)
              (value): Linear(in_features=768, out_features=768, bias=True)
              (dropout): Dropout(p=0.1)
            )
            (output): BertSelfOutput(
              (dense): Linear(in_features=768, out_features=768, bias=True)
              (LayerNorm): BertLayerNorm()
              (dropout): Dropout(p=0.1)
            )
          )
          (intermediate): BertIntermediate(
            (dense): Linear(in_features=768, out_features=3072, bias=True)
          )
          (output): BertOutput(
            (dense): Linear(in_features=3072, out_features=768, bias=True)
            (LayerNorm): BertLayerNorm()
            (dropout): Dropout(p=0.1)
          )
        )
        (3): BertLayer(
          (attention): BertAttention(
            (self): BertSelfAttention(
              (query): Linear(in_features=768, out_features=768, bias=True)
              (key): Linear(in_features=768, out_features=768, bias=True)
              (value): Linear(in_features=768, out_features=768, bias=True)
              (dropout): Dropout(p=0.1)
            )
            (output): BertSelfOutput(
              (dense): Linear(in_features=768, out_features=768, bias=True)
              (LayerNorm): BertLayerNorm()
              (dropout): Dropout(p=0.1)
            )
          )
          (intermediate): BertIntermediate(
            (dense): Linear(in_features=768, out_features=3072, bias=True)
          )
          (output): BertOutput(
            (dense): Linear(in_features=3072, out_features=768, bias=True)
            (LayerNorm): BertLayerNorm()
            (dropout): Dropout(p=0.1)
          )
        )
        (4): BertLayer(
          (attention): BertAttention(
            (self): BertSelfAttention(
              (query): Linear(in_features=768, out_features=768, bias=True)
              (key): Linear(in_features=768, out_features=768, bias=True)
              (value): Linear(in_features=768, out_features=768, bias=True)
              (dropout): Dropout(p=0.1)
            )
            (output): BertSelfOutput(
              (dense): Linear(in_features=768, out_features=768, bias=True)
              (LayerNorm): BertLayerNorm()
              (dropout): Dropout(p=0.1)
            )
          )
          (intermediate): BertIntermediate(
            (dense): Linear(in_features=768, out_features=3072, bias=True)
          )
          (output): BertOutput(
            (dense): Linear(in_features=3072, out_features=768, bias=True)
            (LayerNorm): BertLayerNorm()
            (dropout): Dropout(p=0.1)
          )
        )
        (5): BertLayer(
          (attention): BertAttention(
            (self): BertSelfAttention(
              (query): Linear(in_features=768, out_features=768, bias=True)
              (key): Linear(in_features=768, out_features=768, bias=True)
              (value): Linear(in_features=768, out_features=768, bias=True)
              (dropout): Dropout(p=0.1)
            )
            (output): BertSelfOutput(
              (dense): Linear(in_features=768, out_features=768, bias=True)
              (LayerNorm): BertLayerNorm()
              (dropout): Dropout(p=0.1)
            )
          )
          (intermediate): BertIntermediate(
            (dense): Linear(in_features=768, out_features=3072, bias=True)
          )
          (output): BertOutput(
            (dense): Linear(in_features=3072, out_features=768, bias=True)
            (LayerNorm): BertLayerNorm()
            (dropout): Dropout(p=0.1)
          )
        )
        (6): BertLayer(
          (attention): BertAttention(
            (self): BertSelfAttention(
              (query): Linear(in_features=768, out_features=768, bias=True)
              (key): Linear(in_features=768, out_features=768, bias=True)
              (value): Linear(in_features=768, out_features=768, bias=True)
              (dropout): Dropout(p=0.1)
            )
            (output): BertSelfOutput(
              (dense): Linear(in_features=768, out_features=768, bias=True)
              (LayerNorm): BertLayerNorm()
              (dropout): Dropout(p=0.1)
            )
          )
          (intermediate): BertIntermediate(
            (dense): Linear(in_features=768, out_features=3072, bias=True)
          )
          (output): BertOutput(
            (dense): Linear(in_features=3072, out_features=768, bias=True)
            (LayerNorm): BertLayerNorm()
            (dropout): Dropout(p=0.1)
          )
        )
        (7): BertLayer(
          (attention): BertAttention(
            (self): BertSelfAttention(
              (query): Linear(in_features=768, out_features=768, bias=True)
              (key): Linear(in_features=768, out_features=768, bias=True)
              (value): Linear(in_features=768, out_features=768, bias=True)
              (dropout): Dropout(p=0.1)
            )
            (output): BertSelfOutput(
              (dense): Linear(in_features=768, out_features=768, bias=True)
              (LayerNorm): BertLayerNorm()
              (dropout): Dropout(p=0.1)
            )
          )
          (intermediate): BertIntermediate(
            (dense): Linear(in_features=768, out_features=3072, bias=True)
          )
          (output): BertOutput(
            (dense): Linear(in_features=3072, out_features=768, bias=True)
            (LayerNorm): BertLayerNorm()
            (dropout): Dropout(p=0.1)
          )
        )
        (8): BertLayer(
          (attention): BertAttention(
            (self): BertSelfAttention(
              (query): Linear(in_features=768, out_features=768, bias=True)
              (key): Linear(in_features=768, out_features=768, bias=True)
              (value): Linear(in_features=768, out_features=768, bias=True)
              (dropout): Dropout(p=0.1)
            )
            (output): BertSelfOutput(
              (dense): Linear(in_features=768, out_features=768, bias=True)
              (LayerNorm): BertLayerNorm()
              (dropout): Dropout(p=0.1)
            )
          )
          (intermediate): BertIntermediate(
            (dense): Linear(in_features=768, out_features=3072, bias=True)
          )
          (output): BertOutput(
            (dense): Linear(in_features=3072, out_features=768, bias=True)
            (LayerNorm): BertLayerNorm()
            (dropout): Dropout(p=0.1)
          )
        )
        (9): BertLayer(
          (attention): BertAttention(
            (self): BertSelfAttention(
              (query): Linear(in_features=768, out_features=768, bias=True)
              (key): Linear(in_features=768, out_features=768, bias=True)
              (value): Linear(in_features=768, out_features=768, bias=True)
              (dropout): Dropout(p=0.1)
            )
            (output): BertSelfOutput(
              (dense): Linear(in_features=768, out_features=768, bias=True)
              (LayerNorm): BertLayerNorm()
              (dropout): Dropout(p=0.1)
            )
          )
          (intermediate): BertIntermediate(
            (dense): Linear(in_features=768, out_features=3072, bias=True)
          )
          (output): BertOutput(
            (dense): Linear(in_features=3072, out_features=768, bias=True)
            (LayerNorm): BertLayerNorm()
            (dropout): Dropout(p=0.1)
          )
        )
        (10): BertLayer(
          (attention): BertAttention(
            (self): BertSelfAttention(
              (query): Linear(in_features=768, out_features=768, bias=True)
              (key): Linear(in_features=768, out_features=768, bias=True)
              (value): Linear(in_features=768, out_features=768, bias=True)
              (dropout): Dropout(p=0.1)
            )
            (output): BertSelfOutput(
              (dense): Linear(in_features=768, out_features=768, bias=True)
              (LayerNorm): BertLayerNorm()
              (dropout): Dropout(p=0.1)
            )
          )
          (intermediate): BertIntermediate(
            (dense): Linear(in_features=768, out_features=3072, bias=True)
          )
          (output): BertOutput(
            (dense): Linear(in_features=3072, out_features=768, bias=True)
            (LayerNorm): BertLayerNorm()
            (dropout): Dropout(p=0.1)
          )
        )
        (11): BertLayer(
          (attention): BertAttention(
            (self): BertSelfAttention(
              (query): Linear(in_features=768, out_features=768, bias=True)
              (key): Linear(in_features=768, out_features=768, bias=True)
              (value): Linear(in_features=768, out_features=768, bias=True)
              (dropout): Dropout(p=0.1)
            )
            (output): BertSelfOutput(
              (dense): Linear(in_features=768, out_features=768, bias=True)
              (LayerNorm): BertLayerNorm()
              (dropout): Dropout(p=0.1)
            )
          )
          (intermediate): BertIntermediate(
            (dense): Linear(in_features=768, out_features=3072, bias=True)
          )
          (output): BertOutput(
            (dense): Linear(in_features=3072, out_features=768, bias=True)
            (LayerNorm): BertLayerNorm()
            (dropout): Dropout(p=0.1)
          )
        )
      )
    )
    (pooler): BertPooler(
      (dense): Linear(in_features=768, out_features=768, bias=True)
      (activation): Tanh()
    )
  )
  (cls): BertPreTrainingHeads(
    (predictions): BertLMPredictionHead(
      (transform): BertPredictionHeadTransform(
        (dense): Linear(in_features=768, out_features=768, bias=True)
        (LayerNorm): BertLayerNorm()
      )
      (decoder): Linear(in_features=768, out_features=30522, bias=False)
    )
    (seq_relationship): Linear(in_features=768, out_features=2, bias=True)
  )
)
In [17]:
all_input_ids = torch.tensor([f.input_ids for f in features], dtype=torch.long)
all_input_mask = torch.tensor([f.input_mask for f in features], dtype=torch.long)
all_segment_ids = torch.tensor([f.segment_ids for f in features], dtype=torch.long)
all_masked_lm_positions = torch.tensor([f.masked_lm_positions for f in features], dtype=torch.long)

eval_data = TensorDataset(all_input_ids, all_input_mask, all_segment_ids, all_masked_lm_positions)
eval_sampler = SequentialSampler(eval_data)
eval_dataloader = DataLoader(eval_data, sampler=eval_sampler, batch_size=1)

model.eval()
Out [17]:
BertForPreTraining(
  (bert): BertModel(
    (embeddings): BertEmbeddings(
      (word_embeddings): Embedding(30522, 768)
      (position_embeddings): Embedding(512, 768)
      (token_type_embeddings): Embedding(2, 768)
      (LayerNorm): BertLayerNorm()
      (dropout): Dropout(p=0.1)
    )
    (encoder): BertEncoder(
      (layer): ModuleList(
        (0): BertLayer(
          (attention): BertAttention(
            (self): BertSelfAttention(
              (query): Linear(in_features=768, out_features=768, bias=True)
              (key): Linear(in_features=768, out_features=768, bias=True)
              (value): Linear(in_features=768, out_features=768, bias=True)
              (dropout): Dropout(p=0.1)
            )
            (output): BertSelfOutput(
              (dense): Linear(in_features=768, out_features=768, bias=True)
              (LayerNorm): BertLayerNorm()
              (dropout): Dropout(p=0.1)
            )
          )
          (intermediate): BertIntermediate(
            (dense): Linear(in_features=768, out_features=3072, bias=True)
          )
          (output): BertOutput(
            (dense): Linear(in_features=3072, out_features=768, bias=True)
            (LayerNorm): BertLayerNorm()
            (dropout): Dropout(p=0.1)
          )
        )
        (1): BertLayer(
          (attention): BertAttention(
            (self): BertSelfAttention(
              (query): Linear(in_features=768, out_features=768, bias=True)
              (key): Linear(in_features=768, out_features=768, bias=True)
              (value): Linear(in_features=768, out_features=768, bias=True)
              (dropout): Dropout(p=0.1)
            )
            (output): BertSelfOutput(
              (dense): Linear(in_features=768, out_features=768, bias=True)
              (LayerNorm): BertLayerNorm()
              (dropout): Dropout(p=0.1)
            )
          )
          (intermediate): BertIntermediate(
            (dense): Linear(in_features=768, out_features=3072, bias=True)
          )
          (output): BertOutput(
            (dense): Linear(in_features=3072, out_features=768, bias=True)
            (LayerNorm): BertLayerNorm()
            (dropout): Dropout(p=0.1)
          )
        )
        (2): BertLayer(
          (attention): BertAttention(
            (self): BertSelfAttention(
              (query): Linear(in_features=768, out_features=768, bias=True)
              (key): Linear(in_features=768, out_features=768, bias=True)
              (value): Linear(in_features=768, out_features=768, bias=True)
              (dropout): Dropout(p=0.1)
            )
            (output): BertSelfOutput(
              (dense): Linear(in_features=768, out_features=768, bias=True)
              (LayerNorm): BertLayerNorm()
              (dropout): Dropout(p=0.1)
            )
          )
          (intermediate): BertIntermediate(
            (dense): Linear(in_features=768, out_features=3072, bias=True)
          )
          (output): BertOutput(
            (dense): Linear(in_features=3072, out_features=768, bias=True)
            (LayerNorm): BertLayerNorm()
            (dropout): Dropout(p=0.1)
          )
        )
        (3): BertLayer(
          (attention): BertAttention(
            (self): BertSelfAttention(
              (query): Linear(in_features=768, out_features=768, bias=True)
              (key): Linear(in_features=768, out_features=768, bias=True)
              (value): Linear(in_features=768, out_features=768, bias=True)
              (dropout): Dropout(p=0.1)
            )
            (output): BertSelfOutput(
              (dense): Linear(in_features=768, out_features=768, bias=True)
              (LayerNorm): BertLayerNorm()
              (dropout): Dropout(p=0.1)
            )
          )
          (intermediate): BertIntermediate(
            (dense): Linear(in_features=768, out_features=3072, bias=True)
          )
          (output): BertOutput(
            (dense): Linear(in_features=3072, out_features=768, bias=True)
            (LayerNorm): BertLayerNorm()
            (dropout): Dropout(p=0.1)
          )
        )
        (4): BertLayer(
          (attention): BertAttention(
            (self): BertSelfAttention(
              (query): Linear(in_features=768, out_features=768, bias=True)
              (key): Linear(in_features=768, out_features=768, bias=True)
              (value): Linear(in_features=768, out_features=768, bias=True)
              (dropout): Dropout(p=0.1)
            )
            (output): BertSelfOutput(
              (dense): Linear(in_features=768, out_features=768, bias=True)
              (LayerNorm): BertLayerNorm()
              (dropout): Dropout(p=0.1)
            )
          )
          (intermediate): BertIntermediate(
            (dense): Linear(in_features=768, out_features=3072, bias=True)
          )
          (output): BertOutput(
            (dense): Linear(in_features=3072, out_features=768, bias=True)
            (LayerNorm): BertLayerNorm()
            (dropout): Dropout(p=0.1)
          )
        )
        (5): BertLayer(
          (attention): BertAttention(
            (self): BertSelfAttention(
              (query): Linear(in_features=768, out_features=768, bias=True)
              (key): Linear(in_features=768, out_features=768, bias=True)
              (value): Linear(in_features=768, out_features=768, bias=True)
              (dropout): Dropout(p=0.1)
            )
            (output): BertSelfOutput(
              (dense): Linear(in_features=768, out_features=768, bias=True)
              (LayerNorm): BertLayerNorm()
              (dropout): Dropout(p=0.1)
            )
          )
          (intermediate): BertIntermediate(
            (dense): Linear(in_features=768, out_features=3072, bias=True)
          )
          (output): BertOutput(
            (dense): Linear(in_features=3072, out_features=768, bias=True)
            (LayerNorm): BertLayerNorm()
            (dropout): Dropout(p=0.1)
          )
        )
        (6): BertLayer(
          (attention): BertAttention(
            (self): BertSelfAttention(
              (query): Linear(in_features=768, out_features=768, bias=True)
              (key): Linear(in_features=768, out_features=768, bias=True)
              (value): Linear(in_features=768, out_features=768, bias=True)
              (dropout): Dropout(p=0.1)
            )
            (output): BertSelfOutput(
              (dense): Linear(in_features=768, out_features=768, bias=True)
              (LayerNorm): BertLayerNorm()
              (dropout): Dropout(p=0.1)
            )
          )
          (intermediate): BertIntermediate(
            (dense): Linear(in_features=768, out_features=3072, bias=True)
          )
          (output): BertOutput(
            (dense): Linear(in_features=3072, out_features=768, bias=True)
            (LayerNorm): BertLayerNorm()
            (dropout): Dropout(p=0.1)
          )
        )
        (7): BertLayer(
          (attention): BertAttention(
            (self): BertSelfAttention(
              (query): Linear(in_features=768, out_features=768, bias=True)
              (key): Linear(in_features=768, out_features=768, bias=True)
              (value): Linear(in_features=768, out_features=768, bias=True)
              (dropout): Dropout(p=0.1)
            )
            (output): BertSelfOutput(
              (dense): Linear(in_features=768, out_features=768, bias=True)
              (LayerNorm): BertLayerNorm()
              (dropout): Dropout(p=0.1)
            )
          )
          (intermediate): BertIntermediate(
            (dense): Linear(in_features=768, out_features=3072, bias=True)
          )
          (output): BertOutput(
            (dense): Linear(in_features=3072, out_features=768, bias=True)
            (LayerNorm): BertLayerNorm()
            (dropout): Dropout(p=0.1)
          )
        )
        (8): BertLayer(
          (attention): BertAttention(
            (self): BertSelfAttention(
              (query): Linear(in_features=768, out_features=768, bias=True)
              (key): Linear(in_features=768, out_features=768, bias=True)
              (value): Linear(in_features=768, out_features=768, bias=True)
              (dropout): Dropout(p=0.1)
            )
            (output): BertSelfOutput(
              (dense): Linear(in_features=768, out_features=768, bias=True)
              (LayerNorm): BertLayerNorm()
              (dropout): Dropout(p=0.1)
            )
          )
          (intermediate): BertIntermediate(
            (dense): Linear(in_features=768, out_features=3072, bias=True)
          )
          (output): BertOutput(
            (dense): Linear(in_features=3072, out_features=768, bias=True)
            (LayerNorm): BertLayerNorm()
            (dropout): Dropout(p=0.1)
          )
        )
        (9): BertLayer(
          (attention): BertAttention(
            (self): BertSelfAttention(
              (query): Linear(in_features=768, out_features=768, bias=True)
              (key): Linear(in_features=768, out_features=768, bias=True)
              (value): Linear(in_features=768, out_features=768, bias=True)
              (dropout): Dropout(p=0.1)
            )
            (output): BertSelfOutput(
              (dense): Linear(in_features=768, out_features=768, bias=True)
              (LayerNorm): BertLayerNorm()
              (dropout): Dropout(p=0.1)
            )
          )
          (intermediate): BertIntermediate(
            (dense): Linear(in_features=768, out_features=3072, bias=True)
          )
          (output): BertOutput(
            (dense): Linear(in_features=3072, out_features=768, bias=True)
            (LayerNorm): BertLayerNorm()
            (dropout): Dropout(p=0.1)
          )
        )
        (10): BertLayer(
          (attention): BertAttention(
            (self): BertSelfAttention(
              (query): Linear(in_features=768, out_features=768, bias=True)
              (key): Linear(in_features=768, out_features=768, bias=True)
              (value): Linear(in_features=768, out_features=768, bias=True)
              (dropout): Dropout(p=0.1)
            )
            (output): BertSelfOutput(
              (dense): Linear(in_features=768, out_features=768, bias=True)
              (LayerNorm): BertLayerNorm()
              (dropout): Dropout(p=0.1)
            )
          )
          (intermediate): BertIntermediate(
            (dense): Linear(in_features=768, out_features=3072, bias=True)
          )
          (output): BertOutput(
            (dense): Linear(in_features=3072, out_features=768, bias=True)
            (LayerNorm): BertLayerNorm()
            (dropout): Dropout(p=0.1)
          )
        )
        (11): BertLayer(
          (attention): BertAttention(
            (self): BertSelfAttention(
              (query): Linear(in_features=768, out_features=768, bias=True)
              (key): Linear(in_features=768, out_features=768, bias=True)
              (value): Linear(in_features=768, out_features=768, bias=True)
              (dropout): Dropout(p=0.1)
            )
            (output): BertSelfOutput(
              (dense): Linear(in_features=768, out_features=768, bias=True)
              (LayerNorm): BertLayerNorm()
              (dropout): Dropout(p=0.1)
            )
          )
          (intermediate): BertIntermediate(
            (dense): Linear(in_features=768, out_features=3072, bias=True)
          )
          (output): BertOutput(
            (dense): Linear(in_features=3072, out_features=768, bias=True)
            (LayerNorm): BertLayerNorm()
            (dropout): Dropout(p=0.1)
          )
        )
      )
    )
    (pooler): BertPooler(
      (dense): Linear(in_features=768, out_features=768, bias=True)
      (activation): Tanh()
    )
  )
  (cls): BertPreTrainingHeads(
    (predictions): BertLMPredictionHead(
      (transform): BertPredictionHeadTransform(
        (dense): Linear(in_features=768, out_features=768, bias=True)
        (LayerNorm): BertLayerNorm()
      )
      (decoder): Linear(in_features=768, out_features=30522, bias=False)
    )
    (seq_relationship): Linear(in_features=768, out_features=2, bias=True)
  )
)
In [18]:
import numpy as np
pytorch_all_out = []
for input_ids, input_mask, segment_ids, tensor_masked_lm_positions in eval_dataloader:
    print(input_ids)
    print(input_mask)
    print(segment_ids)
    input_ids = input_ids.to(device)
    input_mask = input_mask.to(device)
    segment_ids = segment_ids.to(device)

    prediction_scores, _ = model(input_ids, token_type_ids=segment_ids, attention_mask=input_mask)
    prediction_scores = prediction_scores[0, tensor_masked_lm_positions].detach().cpu().numpy()
    print(prediction_scores.shape)
    masked_lm_predictions = np.argmax(prediction_scores, axis=-1).squeeze().tolist()
    print(masked_lm_predictions)
    pytorch_all_out.append(masked_lm_predictions)
tensor([[ 2040,  2001,  3958, 27227,  1029,  3958,   103,  2001,  1037, 13997,
         11510,     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]])
tensor([[1, 1, 1, 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]])
tensor([[0, 0, 0, 0, 0, 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]])
(1, 20, 30522)
[27227, 1010, 1010, 1010, 1010, 1010, 1010, 1010, 1010, 1010, 1010, 1010, 1010, 1010, 1010, 1010, 1010, 1010, 1010, 1010]
In [19]:
pytorch_outputs = tokenizer.convert_ids_to_tokens(pytorch_all_out[0])[:len(masked_lm_positions)]
print("pytorch_output:", pytorch_outputs)
print("tensorflow_output:", tensorflow_outputs)
pytorch_output: ['henson']
tensorflow_output: ['henson']
In [ ]:
Reference in new issue View Git Blame Copy Permalink