Spaces:
No application file
No application file
File size: 11,400 Bytes
d08dd00 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 |
{
"nbformat": 4,
"nbformat_minor": 0,
"metadata": {
"colab": {
"name": "albert_glue_fine_tuning_tutorial",
"provenance": [],
"collapsed_sections": [],
"toc_visible": true
},
"kernelspec": {
"name": "python3",
"display_name": "Python 3"
},
"accelerator": "TPU"
},
"cells": [
{
"cell_type": "markdown",
"metadata": {
"id": "y8SJfpgTccDB",
"colab_type": "text"
},
"source": [
"\n",
"<a href=\"https://colab.research.google.com/github/google-research/albert/blob/master/albert_glue_fine_tuning_tutorial.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
]
},
{
"cell_type": "code",
"metadata": {
"id": "wHQH4OCHZ9bq",
"colab_type": "code",
"cellView": "form",
"colab": {}
},
"source": [
"# @title Copyright 2020 The ALBERT Authors. All Rights Reserved.\n",
"#\n",
"# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
"# you may not use this file except in compliance with the License.\n",
"# You may obtain a copy of the License at\n",
"#\n",
"# http://www.apache.org/licenses/LICENSE-2.0\n",
"#\n",
"# Unless required by applicable law or agreed to in writing, software\n",
"# distributed under the License is distributed on an \"AS IS\" BASIS,\n",
"# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n",
"# See the License for the specific language governing permissions and\n",
"# limitations under the License.\n",
"# =============================================================================="
],
"execution_count": 0,
"outputs": []
},
{
"cell_type": "markdown",
"metadata": {
"id": "rkTLZ3I4_7c_",
"colab_type": "text"
},
"source": [
"# ALBERT End to End (Fine-tuning + Predicting) with Cloud TPU"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "1wtjs1QDb3DX",
"colab_type": "text"
},
"source": [
"## Overview\n",
"\n",
"ALBERT is \"A Lite\" version of BERT, a popular unsupervised language representation learning algorithm. ALBERT uses parameter-reduction techniques that allow for large-scale configurations, overcome previous memory limitations, and achieve better behavior with respect to model degradation.\n",
"\n",
"For a technical description of the algorithm, see our paper:\n",
"\n",
"https://arxiv.org/abs/1909.11942\n",
"\n",
"Zhenzhong Lan, Mingda Chen, Sebastian Goodman, Kevin Gimpel, Piyush Sharma, Radu Soricut\n",
"\n",
"This Colab demonstates using a free Colab Cloud TPU to fine-tune GLUE tasks built on top of pretrained ALBERT models and \n",
"run predictions on tuned model. The colab demonsrates loading pretrained ALBERT models from both [TF Hub](https://www.tensorflow.org/hub) and checkpoints.\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",
"This notebook is hosted on GitHub. To view it in its original repository, after opening the notebook, select **File > View on GitHub**."
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "Ld-JXlueIuPH",
"colab_type": "text"
},
"source": [
"## Instructions"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "POkof5uHaQ_c",
"colab_type": "text"
},
"source": [
"<h3><a href=\"https://cloud.google.com/tpu/\"><img valign=\"middle\" src=\"https://raw.githubusercontent.com/GoogleCloudPlatform/tensorflow-without-a-phd/master/tensorflow-rl-pong/images/tpu-hexagon.png\" width=\"50\"></a> Train on TPU</h3>\n",
"\n",
" 1. Create a Cloud Storage bucket for your TensorBoard logs at http://console.cloud.google.com/storage and fill in the BUCKET parameter in the \"Parameters\" section below.\n",
" \n",
" 1. On the main menu, click Runtime and select **Change runtime type**. Set \"TPU\" as the hardware accelerator.\n",
" 1. Click Runtime again and select **Runtime > Run All** (Watch out: the \"Colab-only auth for this notebook and the TPU\" cell requires user input). You can also run the cells manually with Shift-ENTER."
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "UdMmwCJFaT8F",
"colab_type": "text"
},
"source": [
"### Set up your TPU environment\n",
"\n",
"In this section, you perform the following tasks:\n",
"\n",
"* Set up a Colab TPU running environment\n",
"* Verify that you are connected to a TPU device\n",
"* Upload your credentials to TPU to access your GCS bucket."
]
},
{
"cell_type": "code",
"metadata": {
"id": "191zq3ZErihP",
"colab_type": "code",
"colab": {}
},
"source": [
"# TODO(lanzhzh): Add support for 2.x.\n",
"%tensorflow_version 1.x\n",
"import os\n",
"import pprint\n",
"import json\n",
"import tensorflow as tf\n",
"\n",
"assert \"COLAB_TPU_ADDR\" in os.environ, \"ERROR: Not connected to a TPU runtime; please see the first cell in this notebook for instructions!\"\n",
"TPU_ADDRESS = \"grpc://\" + os.environ[\"COLAB_TPU_ADDR\"] \n",
"TPU_TOPOLOGY = \"2x2\"\n",
"print(\"TPU address is\", TPU_ADDRESS)\n",
"\n",
"from google.colab import auth\n",
"auth.authenticate_user()\n",
"with tf.Session(TPU_ADDRESS) as session:\n",
" print('TPU devices:')\n",
" pprint.pprint(session.list_devices())\n",
"\n",
" # Upload credentials to TPU.\n",
" with open('/content/adc.json', 'r') as f:\n",
" auth_info = json.load(f)\n",
" tf.contrib.cloud.configure_gcs(session, credentials=auth_info)\n",
" # Now credentials are set for all future sessions on this TPU."
],
"execution_count": 0,
"outputs": []
},
{
"cell_type": "markdown",
"metadata": {
"id": "HUBP35oCDmbF",
"colab_type": "text"
},
"source": [
"### Prepare and import ALBERT modules\n",
"\n",
"With your environment configured, you can now prepare and import the ALBERT modules. The following step clones the source code from GitHub."
]
},
{
"cell_type": "code",
"metadata": {
"id": "7wzwke0sxS6W",
"colab_type": "code",
"colab": {},
"cellView": "code"
},
"source": [
"#TODO(lanzhzh): Add pip support\n",
"import sys\n",
"\n",
"!test -d albert || git clone https://github.com/google-research/albert albert\n",
"if not 'albert' in sys.path:\n",
" sys.path += ['albert']\n",
" \n",
"!pip install sentencepiece\n"
],
"execution_count": 0,
"outputs": []
},
{
"cell_type": "markdown",
"metadata": {
"id": "RRu1aKO1D7-Z",
"colab_type": "text"
},
"source": [
"### Prepare for training\n",
"\n",
"This next section of code performs the following tasks:\n",
"\n",
"* Specify GS bucket, create output directory for model checkpoints and eval results.\n",
"* Specify task and download training data.\n",
"* Specify ALBERT pretrained model\n",
"\n",
"\n",
"\n"
]
},
{
"cell_type": "code",
"metadata": {
"id": "tYkaAlJNfhul",
"colab_type": "code",
"colab": {},
"cellView": "form"
},
"source": [
"# Please find the full list of tasks and their fintuning hyperparameters\n",
"# here https://github.com/google-research/albert/blob/master/run_glue.sh\n",
"\n",
"BUCKET = \"albert_tutorial_glue\" #@param { type: \"string\" }\n",
"TASK = 'MRPC' #@param {type:\"string\"}\n",
"# Available pretrained model checkpoints:\n",
"# base, large, xlarge, xxlarge\n",
"ALBERT_MODEL = 'base' #@param {type:\"string\"}\n",
"\n",
"TASK_DATA_DIR = 'glue_data'\n",
"\n",
"BASE_DIR = \"gs://\" + BUCKET\n",
"if not BASE_DIR or BASE_DIR == \"gs://\":\n",
" raise ValueError(\"You must enter a BUCKET.\")\n",
"DATA_DIR = os.path.join(BASE_DIR, \"data\")\n",
"MODELS_DIR = os.path.join(BASE_DIR, \"models\")\n",
"OUTPUT_DIR = 'gs://{}/albert-tfhub/models/{}'.format(BUCKET, TASK)\n",
"tf.gfile.MakeDirs(OUTPUT_DIR)\n",
"print('***** Model output directory: {} *****'.format(OUTPUT_DIR))\n",
"\n",
"# Download glue data.\n",
"! test -d download_glue_repo || git clone https://gist.github.com/60c2bdb54d156a41194446737ce03e2e.git download_glue_repo\n",
"!python download_glue_repo/download_glue_data.py --data_dir=$TASK_DATA_DIR --tasks=$TASK\n",
"print('***** Task data directory: {} *****'.format(TASK_DATA_DIR))\n",
"\n",
"ALBERT_MODEL_HUB = 'https://tfhub.dev/google/albert_' + ALBERT_MODEL + '/3'"
],
"execution_count": 0,
"outputs": []
},
{
"cell_type": "markdown",
"metadata": {
"id": "Hcpfl4N2EdOk",
"colab_type": "text"
},
"source": [
"Now let's run the fine-tuning scripts. If you use the default MRPC task, this should be finished in around 10 mintues and you will get an accuracy of around 86.5."
]
},
{
"cell_type": "code",
"metadata": {
"id": "o8qXPxv8-kBO",
"colab_type": "code",
"colab": {}
},
"source": [
"os.environ['TFHUB_CACHE_DIR'] = OUTPUT_DIR\n",
"!python -m albert.run_classifier \\\n",
" --data_dir=\"glue_data/\" \\\n",
" --output_dir=$OUTPUT_DIR \\\n",
" --albert_hub_module_handle=$ALBERT_MODEL_HUB \\\n",
" --spm_model_file=\"from_tf_hub\" \\\n",
" --do_train=True \\\n",
" --do_eval=True \\\n",
" --do_predict=False \\\n",
" --max_seq_length=512 \\\n",
" --optimizer=adamw \\\n",
" --task_name=$TASK \\\n",
" --warmup_step=200 \\\n",
" --learning_rate=2e-5 \\\n",
" --train_step=800 \\\n",
" --save_checkpoints_steps=100 \\\n",
" --train_batch_size=32 \\\n",
" --tpu_name=$TPU_ADDRESS \\\n",
" --use_tpu=True"
],
"execution_count": 0,
"outputs": []
}
]
}
|