" <a target=\"_blank\" href=\"https://colab.research.google.com/github/tensorflow/tpu/blob/master/tools/colab/bert_finetuning_with_cloud_tpus.ipynb\"><img src=\"https://www.tensorflow.org/images/colab_logo_32px.png\" />Run in Google Colab</a>\n",
" </td>\n",
" <td>\n",
" <a target=\"_blank\" href=\"https://github.com/tensorflow/tpu/blob/master/tools/colab/bert_finetuning_with_cloud_tpus.ipynb\"><img src=\"https://www.tensorflow.org/images/GitHub-Mark-32px.png\" />View source on GitHub</a>\n",
" </td>\n",
"</table>\n"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "1wtjs1QDb3DX",
"colab_type": "text"
},
"source": [
"**BERT**, or **B**idirectional **E**mbedding **R**epresentations from **T**ransformers, is a new method of pre-training language representations which obtains state-of-the-art results on a wide array of Natural Language Processing (NLP) tasks. The academic paper can be found here: https://arxiv.org/abs/1810.04805.\n",
"\n",
"This Colab demonstates using a free Colab Cloud TPU to fine-tune sentence and sentence-pair classification tasks built on top of pretrained BERT models.\n",
"\n",
"**Note:** You will need a GCP (Google Compute Engine) account and a GCS (Google Cloud \n",
"Storage) bucket for this Colab to run.\n",
"\n",
"Please follow the [Google Cloud TPU quickstart](https://cloud.google.com/tpu/docs/quickstart) for how to create GCP account and GCS bucket. You have [$300 free credit](https://cloud.google.com/free/) to get started with any GCP product. You can learn more about Cloud TPU at https://cloud.google.com/tpu/docs.\n",
"\n",
"Once you finish the setup, let's start!"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "ycHMh-bhC-vX",
"colab_type": "text"
},
"source": [
"**Firstly**, we need to set up Colab TPU running environment, verify a TPU device is succesfully connected and upload credentials to TPU for GCS bucket usage."
"WARNING:tensorflow:Estimator's model_fn (<function model_fn_builder.<locals>.model_fn at 0x7fcce37cf9d8>) includes params argument, but params are not passed to Estimator.\n",
"INFO:tensorflow:tokens: [CLS] chris 1791 news buster ##s too years ago # hillary # never answered whether she used private email # liberal # media passed on reporting [SEP]\n",
"INFO:tensorflow:tokens: [CLS] d new ha ##user take that , marco rub ##io go ##p cannot pan ##der to the latino vote while pushing policies that hurt the community most [SEP]\n",
"INFO:tensorflow:tokens: [CLS] state dept am ##b cathy russell adam smith usa hillary clinton hillary for i a barack obama the whole # world # is supporting you [SEP]\n",
"INFO:tensorflow:tokens: [CLS] lets remember # dick cheney # is an un ##ind ##ic ##ted war criminal before we start yelling # ben ##gh ##azi # day after day will we ever see justice ? [SEP]\n",
"WARNING:tensorflow:Estimator's model_fn (<function model_fn_builder.<locals>.model_fn at 0x7fcce37cf9d8>) includes params argument, but params are not passed to Estimator.\n",
"INFO:tensorflow:tokens: [CLS] # mt ##p # meet the press how is del ##eti ##ng emails part of the government record different from eras ##ing parts of a tape ? # nixon # # p ##2 # [SEP]\n",
"INFO:tensorflow:tokens: [CLS] jd son 78 andrew b roe ring andrew why do you care about what i think ? i did not realize that i was this important sir t ##wee ##t andrew is a paid troll [SEP]\n",
"INFO:tensorflow:tokens: [CLS] the white male vote is solid ##ly go ##p the black vote is solid ##ly them that leaves white females and brown people # feel the bern # [SEP]\n",
"INFO:tensorflow:tokens: [CLS] go ##p why should i believe you on this ? the go ##p leaders in congress wo n ' t fight obama now ! ! ! # t cot # [SEP]\n",
"INFO:tensorflow: name = bert/embeddings/word_embeddings:0, shape = (30522, 1024), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/embeddings/token_type_embeddings:0, shape = (2, 1024), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/embeddings/position_embeddings:0, shape = (512, 1024), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/embeddings/LayerNorm/beta:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/embeddings/LayerNorm/gamma:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_0/attention/self/query/kernel:0, shape = (1024, 1024), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_0/attention/self/query/bias:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_0/attention/self/key/kernel:0, shape = (1024, 1024), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_0/attention/self/key/bias:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_0/attention/self/value/kernel:0, shape = (1024, 1024), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_0/attention/self/value/bias:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_0/attention/output/dense/kernel:0, shape = (1024, 1024), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_0/attention/output/dense/bias:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_0/attention/output/LayerNorm/beta:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_0/attention/output/LayerNorm/gamma:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_0/intermediate/dense/kernel:0, shape = (1024, 4096), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_0/intermediate/dense/bias:0, shape = (4096,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_0/output/dense/kernel:0, shape = (4096, 1024), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_0/output/dense/bias:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_0/output/LayerNorm/beta:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_0/output/LayerNorm/gamma:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_1/attention/self/query/kernel:0, shape = (1024, 1024), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_1/attention/self/query/bias:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_1/attention/self/key/kernel:0, shape = (1024, 1024), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_1/attention/self/key/bias:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_1/attention/self/value/kernel:0, shape = (1024, 1024), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_1/attention/self/value/bias:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_1/attention/output/dense/kernel:0, shape = (1024, 1024), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_1/attention/output/dense/bias:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_1/attention/output/LayerNorm/beta:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_1/attention/output/LayerNorm/gamma:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_1/intermediate/dense/kernel:0, shape = (1024, 4096), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_1/intermediate/dense/bias:0, shape = (4096,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_1/output/dense/kernel:0, shape = (4096, 1024), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_1/output/dense/bias:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_1/output/LayerNorm/beta:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_1/output/LayerNorm/gamma:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_2/attention/self/query/kernel:0, shape = (1024, 1024), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_2/attention/self/query/bias:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_2/attention/self/key/kernel:0, shape = (1024, 1024), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_2/attention/self/key/bias:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_2/attention/self/value/kernel:0, shape = (1024, 1024), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_2/attention/self/value/bias:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_2/attention/output/dense/kernel:0, shape = (1024, 1024), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_2/attention/output/dense/bias:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_2/attention/output/LayerNorm/beta:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_2/attention/output/LayerNorm/gamma:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_2/intermediate/dense/kernel:0, shape = (1024, 4096), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_2/intermediate/dense/bias:0, shape = (4096,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_2/output/dense/kernel:0, shape = (4096, 1024), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_2/output/dense/bias:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_2/output/LayerNorm/beta:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_2/output/LayerNorm/gamma:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_3/attention/self/query/kernel:0, shape = (1024, 1024), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_3/attention/self/query/bias:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_3/attention/self/key/kernel:0, shape = (1024, 1024), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_3/attention/self/key/bias:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_3/attention/self/value/kernel:0, shape = (1024, 1024), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_3/attention/self/value/bias:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_3/attention/output/dense/kernel:0, shape = (1024, 1024), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_3/attention/output/dense/bias:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_3/attention/output/LayerNorm/beta:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_3/attention/output/LayerNorm/gamma:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_3/intermediate/dense/kernel:0, shape = (1024, 4096), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_3/intermediate/dense/bias:0, shape = (4096,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_3/output/dense/kernel:0, shape = (4096, 1024), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_3/output/dense/bias:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_3/output/LayerNorm/beta:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_3/output/LayerNorm/gamma:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_4/attention/self/query/kernel:0, shape = (1024, 1024), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_4/attention/self/query/bias:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_4/attention/self/key/kernel:0, shape = (1024, 1024), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_4/attention/self/key/bias:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_4/attention/self/value/kernel:0, shape = (1024, 1024), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_4/attention/self/value/bias:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_4/attention/output/dense/kernel:0, shape = (1024, 1024), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_4/attention/output/dense/bias:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_4/attention/output/LayerNorm/beta:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_4/attention/output/LayerNorm/gamma:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_4/intermediate/dense/kernel:0, shape = (1024, 4096), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_4/intermediate/dense/bias:0, shape = (4096,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_4/output/dense/kernel:0, shape = (4096, 1024), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_4/output/dense/bias:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_4/output/LayerNorm/beta:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_4/output/LayerNorm/gamma:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_5/attention/self/query/kernel:0, shape = (1024, 1024), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_5/attention/self/query/bias:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_5/attention/self/key/kernel:0, shape = (1024, 1024), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_5/attention/self/key/bias:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_5/attention/self/value/kernel:0, shape = (1024, 1024), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_5/attention/self/value/bias:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_5/attention/output/dense/kernel:0, shape = (1024, 1024), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_5/attention/output/dense/bias:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_5/attention/output/LayerNorm/beta:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_5/attention/output/LayerNorm/gamma:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_5/intermediate/dense/kernel:0, shape = (1024, 4096), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_5/intermediate/dense/bias:0, shape = (4096,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_5/output/dense/kernel:0, shape = (4096, 1024), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_5/output/dense/bias:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_5/output/LayerNorm/beta:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_5/output/LayerNorm/gamma:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_6/attention/self/query/kernel:0, shape = (1024, 1024), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_6/attention/self/query/bias:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_6/attention/self/key/kernel:0, shape = (1024, 1024), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_6/attention/self/key/bias:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_6/attention/self/value/kernel:0, shape = (1024, 1024), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_6/attention/self/value/bias:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_6/attention/output/dense/kernel:0, shape = (1024, 1024), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_6/attention/output/dense/bias:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_6/attention/output/LayerNorm/beta:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_6/attention/output/LayerNorm/gamma:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_6/intermediate/dense/kernel:0, shape = (1024, 4096), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_6/intermediate/dense/bias:0, shape = (4096,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_6/output/dense/kernel:0, shape = (4096, 1024), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_6/output/dense/bias:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_6/output/LayerNorm/beta:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_6/output/LayerNorm/gamma:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_7/attention/self/query/kernel:0, shape = (1024, 1024), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_7/attention/self/query/bias:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_7/attention/self/key/kernel:0, shape = (1024, 1024), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_7/attention/self/key/bias:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_7/attention/self/value/kernel:0, shape = (1024, 1024), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_7/attention/self/value/bias:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_7/attention/output/dense/kernel:0, shape = (1024, 1024), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_7/attention/output/dense/bias:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_7/attention/output/LayerNorm/beta:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_7/attention/output/LayerNorm/gamma:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_7/intermediate/dense/kernel:0, shape = (1024, 4096), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_7/intermediate/dense/bias:0, shape = (4096,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_7/output/dense/kernel:0, shape = (4096, 1024), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_7/output/dense/bias:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_7/output/LayerNorm/beta:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_7/output/LayerNorm/gamma:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_8/attention/self/query/kernel:0, shape = (1024, 1024), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_8/attention/self/query/bias:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_8/attention/self/key/kernel:0, shape = (1024, 1024), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_8/attention/self/key/bias:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_8/attention/self/value/kernel:0, shape = (1024, 1024), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_8/attention/self/value/bias:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_8/attention/output/dense/kernel:0, shape = (1024, 1024), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_8/attention/output/dense/bias:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_8/attention/output/LayerNorm/beta:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_8/attention/output/LayerNorm/gamma:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_8/intermediate/dense/kernel:0, shape = (1024, 4096), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_8/intermediate/dense/bias:0, shape = (4096,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_8/output/dense/kernel:0, shape = (4096, 1024), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_8/output/dense/bias:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_8/output/LayerNorm/beta:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_8/output/LayerNorm/gamma:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_9/attention/self/query/kernel:0, shape = (1024, 1024), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_9/attention/self/query/bias:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_9/attention/self/key/kernel:0, shape = (1024, 1024), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_9/attention/self/key/bias:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_9/attention/self/value/kernel:0, shape = (1024, 1024), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_9/attention/self/value/bias:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_9/attention/output/dense/kernel:0, shape = (1024, 1024), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_9/attention/output/dense/bias:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_9/attention/output/LayerNorm/beta:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_9/attention/output/LayerNorm/gamma:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_9/intermediate/dense/kernel:0, shape = (1024, 4096), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_9/intermediate/dense/bias:0, shape = (4096,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_9/output/dense/kernel:0, shape = (4096, 1024), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_9/output/dense/bias:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_9/output/LayerNorm/beta:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_9/output/LayerNorm/gamma:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_10/attention/self/query/kernel:0, shape = (1024, 1024), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_10/attention/self/query/bias:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_10/attention/self/key/kernel:0, shape = (1024, 1024), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_10/attention/self/key/bias:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_10/attention/self/value/kernel:0, shape = (1024, 1024), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_10/attention/self/value/bias:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_10/attention/output/dense/kernel:0, shape = (1024, 1024), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_10/attention/output/dense/bias:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_10/attention/output/LayerNorm/beta:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_10/attention/output/LayerNorm/gamma:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_10/intermediate/dense/kernel:0, shape = (1024, 4096), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_10/intermediate/dense/bias:0, shape = (4096,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_10/output/dense/kernel:0, shape = (4096, 1024), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_10/output/dense/bias:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_10/output/LayerNorm/beta:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_10/output/LayerNorm/gamma:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_11/attention/self/query/kernel:0, shape = (1024, 1024), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_11/attention/self/query/bias:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_11/attention/self/key/kernel:0, shape = (1024, 1024), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_11/attention/self/key/bias:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_11/attention/self/value/kernel:0, shape = (1024, 1024), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_11/attention/self/value/bias:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_11/attention/output/dense/kernel:0, shape = (1024, 1024), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_11/attention/output/dense/bias:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_11/attention/output/LayerNorm/beta:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_11/attention/output/LayerNorm/gamma:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_11/intermediate/dense/kernel:0, shape = (1024, 4096), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_11/intermediate/dense/bias:0, shape = (4096,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_11/output/dense/kernel:0, shape = (4096, 1024), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_11/output/dense/bias:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_11/output/LayerNorm/beta:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_11/output/LayerNorm/gamma:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_12/attention/self/query/kernel:0, shape = (1024, 1024), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_12/attention/self/query/bias:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_12/attention/self/key/kernel:0, shape = (1024, 1024), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_12/attention/self/key/bias:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_12/attention/self/value/kernel:0, shape = (1024, 1024), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_12/attention/self/value/bias:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_12/attention/output/dense/kernel:0, shape = (1024, 1024), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_12/attention/output/dense/bias:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_12/attention/output/LayerNorm/beta:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_12/attention/output/LayerNorm/gamma:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_12/intermediate/dense/kernel:0, shape = (1024, 4096), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_12/intermediate/dense/bias:0, shape = (4096,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_12/output/dense/kernel:0, shape = (4096, 1024), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_12/output/dense/bias:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_12/output/LayerNorm/beta:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_12/output/LayerNorm/gamma:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_13/attention/self/query/kernel:0, shape = (1024, 1024), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_13/attention/self/query/bias:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_13/attention/self/key/kernel:0, shape = (1024, 1024), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_13/attention/self/key/bias:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_13/attention/self/value/kernel:0, shape = (1024, 1024), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_13/attention/self/value/bias:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_13/attention/output/dense/kernel:0, shape = (1024, 1024), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_13/attention/output/dense/bias:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_13/attention/output/LayerNorm/beta:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_13/attention/output/LayerNorm/gamma:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_13/intermediate/dense/kernel:0, shape = (1024, 4096), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_13/intermediate/dense/bias:0, shape = (4096,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_13/output/dense/kernel:0, shape = (4096, 1024), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_13/output/dense/bias:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_13/output/LayerNorm/beta:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_13/output/LayerNorm/gamma:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_14/attention/self/query/kernel:0, shape = (1024, 1024), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_14/attention/self/query/bias:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_14/attention/self/key/kernel:0, shape = (1024, 1024), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_14/attention/self/key/bias:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_14/attention/self/value/kernel:0, shape = (1024, 1024), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_14/attention/self/value/bias:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_14/attention/output/dense/kernel:0, shape = (1024, 1024), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_14/attention/output/dense/bias:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_14/attention/output/LayerNorm/beta:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_14/attention/output/LayerNorm/gamma:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_14/intermediate/dense/kernel:0, shape = (1024, 4096), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_14/intermediate/dense/bias:0, shape = (4096,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_14/output/dense/kernel:0, shape = (4096, 1024), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_14/output/dense/bias:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_14/output/LayerNorm/beta:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_14/output/LayerNorm/gamma:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_15/attention/self/query/kernel:0, shape = (1024, 1024), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_15/attention/self/query/bias:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_15/attention/self/key/kernel:0, shape = (1024, 1024), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_15/attention/self/key/bias:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_15/attention/self/value/kernel:0, shape = (1024, 1024), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_15/attention/self/value/bias:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_15/attention/output/dense/kernel:0, shape = (1024, 1024), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_15/attention/output/dense/bias:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_15/attention/output/LayerNorm/beta:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_15/attention/output/LayerNorm/gamma:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_15/intermediate/dense/kernel:0, shape = (1024, 4096), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_15/intermediate/dense/bias:0, shape = (4096,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_15/output/dense/kernel:0, shape = (4096, 1024), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_15/output/dense/bias:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_15/output/LayerNorm/beta:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_15/output/LayerNorm/gamma:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_16/attention/self/query/kernel:0, shape = (1024, 1024), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_16/attention/self/query/bias:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_16/attention/self/key/kernel:0, shape = (1024, 1024), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_16/attention/self/key/bias:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_16/attention/self/value/kernel:0, shape = (1024, 1024), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_16/attention/self/value/bias:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_16/attention/output/dense/kernel:0, shape = (1024, 1024), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_16/attention/output/dense/bias:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_16/attention/output/LayerNorm/beta:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_16/attention/output/LayerNorm/gamma:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_16/intermediate/dense/kernel:0, shape = (1024, 4096), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_16/intermediate/dense/bias:0, shape = (4096,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_16/output/dense/kernel:0, shape = (4096, 1024), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_16/output/dense/bias:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_16/output/LayerNorm/beta:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_16/output/LayerNorm/gamma:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_17/attention/self/query/kernel:0, shape = (1024, 1024), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_17/attention/self/query/bias:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_17/attention/self/key/kernel:0, shape = (1024, 1024), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_17/attention/self/key/bias:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_17/attention/self/value/kernel:0, shape = (1024, 1024), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_17/attention/self/value/bias:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_17/attention/output/dense/kernel:0, shape = (1024, 1024), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_17/attention/output/dense/bias:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_17/attention/output/LayerNorm/beta:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_17/attention/output/LayerNorm/gamma:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_17/intermediate/dense/kernel:0, shape = (1024, 4096), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_17/intermediate/dense/bias:0, shape = (4096,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_17/output/dense/kernel:0, shape = (4096, 1024), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_17/output/dense/bias:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_17/output/LayerNorm/beta:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_17/output/LayerNorm/gamma:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_18/attention/self/query/kernel:0, shape = (1024, 1024), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_18/attention/self/query/bias:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_18/attention/self/key/kernel:0, shape = (1024, 1024), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_18/attention/self/key/bias:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_18/attention/self/value/kernel:0, shape = (1024, 1024), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_18/attention/self/value/bias:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_18/attention/output/dense/kernel:0, shape = (1024, 1024), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_18/attention/output/dense/bias:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_18/attention/output/LayerNorm/beta:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_18/attention/output/LayerNorm/gamma:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_18/intermediate/dense/kernel:0, shape = (1024, 4096), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_18/intermediate/dense/bias:0, shape = (4096,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_18/output/dense/kernel:0, shape = (4096, 1024), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_18/output/dense/bias:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_18/output/LayerNorm/beta:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_18/output/LayerNorm/gamma:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_19/attention/self/query/kernel:0, shape = (1024, 1024), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_19/attention/self/query/bias:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_19/attention/self/key/kernel:0, shape = (1024, 1024), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_19/attention/self/key/bias:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_19/attention/self/value/kernel:0, shape = (1024, 1024), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_19/attention/self/value/bias:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_19/attention/output/dense/kernel:0, shape = (1024, 1024), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_19/attention/output/dense/bias:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_19/attention/output/LayerNorm/beta:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_19/attention/output/LayerNorm/gamma:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_19/intermediate/dense/kernel:0, shape = (1024, 4096), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_19/intermediate/dense/bias:0, shape = (4096,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_19/output/dense/kernel:0, shape = (4096, 1024), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_19/output/dense/bias:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_19/output/LayerNorm/beta:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_19/output/LayerNorm/gamma:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_20/attention/self/query/kernel:0, shape = (1024, 1024), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_20/attention/self/query/bias:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_20/attention/self/key/kernel:0, shape = (1024, 1024), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_20/attention/self/key/bias:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_20/attention/self/value/kernel:0, shape = (1024, 1024), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_20/attention/self/value/bias:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_20/attention/output/dense/kernel:0, shape = (1024, 1024), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_20/attention/output/dense/bias:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_20/attention/output/LayerNorm/beta:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_20/attention/output/LayerNorm/gamma:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_20/intermediate/dense/kernel:0, shape = (1024, 4096), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_20/intermediate/dense/bias:0, shape = (4096,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_20/output/dense/kernel:0, shape = (4096, 1024), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_20/output/dense/bias:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_20/output/LayerNorm/beta:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_20/output/LayerNorm/gamma:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_21/attention/self/query/kernel:0, shape = (1024, 1024), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_21/attention/self/query/bias:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_21/attention/self/key/kernel:0, shape = (1024, 1024), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_21/attention/self/key/bias:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_21/attention/self/value/kernel:0, shape = (1024, 1024), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_21/attention/self/value/bias:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_21/attention/output/dense/kernel:0, shape = (1024, 1024), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_21/attention/output/dense/bias:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_21/attention/output/LayerNorm/beta:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_21/attention/output/LayerNorm/gamma:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_21/intermediate/dense/kernel:0, shape = (1024, 4096), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_21/intermediate/dense/bias:0, shape = (4096,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_21/output/dense/kernel:0, shape = (4096, 1024), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_21/output/dense/bias:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_21/output/LayerNorm/beta:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_21/output/LayerNorm/gamma:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_22/attention/self/query/kernel:0, shape = (1024, 1024), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_22/attention/self/query/bias:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_22/attention/self/key/kernel:0, shape = (1024, 1024), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_22/attention/self/key/bias:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_22/attention/self/value/kernel:0, shape = (1024, 1024), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_22/attention/self/value/bias:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_22/attention/output/dense/kernel:0, shape = (1024, 1024), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_22/attention/output/dense/bias:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_22/attention/output/LayerNorm/beta:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_22/attention/output/LayerNorm/gamma:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_22/intermediate/dense/kernel:0, shape = (1024, 4096), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_22/intermediate/dense/bias:0, shape = (4096,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_22/output/dense/kernel:0, shape = (4096, 1024), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_22/output/dense/bias:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_22/output/LayerNorm/beta:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_22/output/LayerNorm/gamma:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_23/attention/self/query/kernel:0, shape = (1024, 1024), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_23/attention/self/query/bias:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_23/attention/self/key/kernel:0, shape = (1024, 1024), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_23/attention/self/key/bias:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_23/attention/self/value/kernel:0, shape = (1024, 1024), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_23/attention/self/value/bias:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_23/attention/output/dense/kernel:0, shape = (1024, 1024), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_23/attention/output/dense/bias:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_23/attention/output/LayerNorm/beta:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_23/attention/output/LayerNorm/gamma:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_23/intermediate/dense/kernel:0, shape = (1024, 4096), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_23/intermediate/dense/bias:0, shape = (4096,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_23/output/dense/kernel:0, shape = (4096, 1024), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_23/output/dense/bias:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_23/output/LayerNorm/beta:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/encoder/layer_23/output/LayerNorm/gamma:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/pooler/dense/kernel:0, shape = (1024, 1024), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = bert/pooler/dense/bias:0, shape = (1024,), *INIT_FROM_CKPT*\n",
"INFO:tensorflow: name = output_weights:0, shape = (3, 1024)\n",
"INFO:tensorflow: name = output_bias:0, shape = (3,)\n",
"INFO:tensorflow:Done calling model_fn.\n",
"INFO:tensorflow:TPU job name worker\n",
"INFO:tensorflow:Graph was finalized.\n",
"WARNING:tensorflow:From /usr/local/lib/python3.6/dist-packages/tensorflow/python/training/saver.py:1266: checkpoint_exists (from tensorflow.python.training.checkpoint_management) is deprecated and will be removed in a future version.\n",
"Instructions for updating:\n",
"Use standard file APIs to check for files with this prefix.\n",
"INFO:tensorflow:Restoring parameters from gs://bert-large-pair/bert/models/uncased_L-24_H-1024_A-16/HC_new/model.ckpt-199\n",