Merge remote-tracking branch 'refs/remotes/huggingface/master'

utils/download_glue_data.py

+''' Script for downloading all GLUE data.
+Original source: https://gist.github.com/W4ngatang/60c2bdb54d156a41194446737ce03e2e
+
+Note: for legal reasons, we are unable to host MRPC.
+You can either use the version hosted by the SentEval team, which is already tokenized, 
+or you can download the original data from (https://download.microsoft.com/download/D/4/6/D46FF87A-F6B9-4252-AA8B-3604ED519838/MSRParaphraseCorpus.msi) and extract the data from it manually.
+For Windows users, you can run the .msi file. For Mac and Linux users, consider an external library such as 'cabextract' (see below for an example).
+You should then rename and place specific files in a folder (see below for an example).
+
+mkdir MRPC
+cabextract MSRParaphraseCorpus.msi -d MRPC
+cat MRPC/_2DEC3DBE877E4DB192D17C0256E90F1D | tr -d $'\r' > MRPC/msr_paraphrase_train.txt
+cat MRPC/_D7B391F9EAFF4B1B8BCE8F21B20B1B61 | tr -d $'\r' > MRPC/msr_paraphrase_test.txt
+rm MRPC/_*
+rm MSRParaphraseCorpus.msi
+
+1/30/19: It looks like SentEval is no longer hosting their extracted and tokenized MRPC data, so you'll need to download the data from the original source for now.
+2/11/19: It looks like SentEval actually *is* hosting the extracted data. Hooray!
+'''
+
+import os
+import sys
+import shutil
+import argparse
+import tempfile
+import urllib.request
+import zipfile
+
+TASKS = ["CoLA", "SST", "MRPC", "QQP", "STS", "MNLI", "SNLI", "QNLI", "RTE", "WNLI", "diagnostic"]
+TASK2PATH = {"CoLA":'https://firebasestorage.googleapis.com/v0/b/mtl-sentence-representations.appspot.com/o/data%2FCoLA.zip?alt=media&token=46d5e637-3411-4188-bc44-5809b5bfb5f4',
+             "SST":'https://firebasestorage.googleapis.com/v0/b/mtl-sentence-representations.appspot.com/o/data%2FSST-2.zip?alt=media&token=aabc5f6b-e466-44a2-b9b4-cf6337f84ac8',
+             "MRPC":'https://firebasestorage.googleapis.com/v0/b/mtl-sentence-representations.appspot.com/o/data%2Fmrpc_dev_ids.tsv?alt=media&token=ec5c0836-31d5-48f4-b431-7480817f1adc',
+             "QQP":'https://firebasestorage.googleapis.com/v0/b/mtl-sentence-representations.appspot.com/o/data%2FQQP.zip?alt=media&token=700c6acf-160d-4d89-81d1-de4191d02cb5',
+             "STS":'https://firebasestorage.googleapis.com/v0/b/mtl-sentence-representations.appspot.com/o/data%2FSTS-B.zip?alt=media&token=bddb94a7-8706-4e0d-a694-1109e12273b5',
+             "MNLI":'https://firebasestorage.googleapis.com/v0/b/mtl-sentence-representations.appspot.com/o/data%2FMNLI.zip?alt=media&token=50329ea1-e339-40e2-809c-10c40afff3ce',
+             "SNLI":'https://firebasestorage.googleapis.com/v0/b/mtl-sentence-representations.appspot.com/o/data%2FSNLI.zip?alt=media&token=4afcfbb2-ff0c-4b2d-a09a-dbf07926f4df',
+             "QNLI": 'https://firebasestorage.googleapis.com/v0/b/mtl-sentence-representations.appspot.com/o/data%2FQNLIv2.zip?alt=media&token=6fdcf570-0fc5-4631-8456-9505272d1601',
+             "RTE":'https://firebasestorage.googleapis.com/v0/b/mtl-sentence-representations.appspot.com/o/data%2FRTE.zip?alt=media&token=5efa7e85-a0bb-4f19-8ea2-9e1840f077fb',
+             "WNLI":'https://firebasestorage.googleapis.com/v0/b/mtl-sentence-representations.appspot.com/o/data%2FWNLI.zip?alt=media&token=068ad0a0-ded7-4bd7-99a5-5e00222e0faf',
+             "diagnostic":'https://storage.googleapis.com/mtl-sentence-representations.appspot.com/tsvsWithoutLabels%2FAX.tsv?GoogleAccessId=firebase-adminsdk-0khhl@mtl-sentence-representations.iam.gserviceaccount.com&Expires=2498860800&Signature=DuQ2CSPt2Yfre0C%2BiISrVYrIFaZH1Lc7hBVZDD4ZyR7fZYOMNOUGpi8QxBmTNOrNPjR3z1cggo7WXFfrgECP6FBJSsURv8Ybrue8Ypt%2FTPxbuJ0Xc2FhDi%2BarnecCBFO77RSbfuz%2Bs95hRrYhTnByqu3U%2FYZPaj3tZt5QdfpH2IUROY8LiBXoXS46LE%2FgOQc%2FKN%2BA9SoscRDYsnxHfG0IjXGwHN%2Bf88q6hOmAxeNPx6moDulUF6XMUAaXCSFU%2BnRO2RDL9CapWxj%2BDl7syNyHhB7987hZ80B%2FwFkQ3MEs8auvt5XW1%2Bd4aCU7ytgM69r8JDCwibfhZxpaa4gd50QXQ%3D%3D'}
+
+MRPC_TRAIN = 'https://dl.fbaipublicfiles.com/senteval/senteval_data/msr_paraphrase_train.txt'
+MRPC_TEST = 'https://dl.fbaipublicfiles.com/senteval/senteval_data/msr_paraphrase_test.txt'
+
+def download_and_extract(task, data_dir):
+    print("Downloading and extracting %s..." % task)
+    data_file = "%s.zip" % task
+    urllib.request.urlretrieve(TASK2PATH[task], data_file)
+    with zipfile.ZipFile(data_file) as zip_ref:
+        zip_ref.extractall(data_dir)
+    os.remove(data_file)
+    print("\tCompleted!")
+
+def format_mrpc(data_dir, path_to_data):
+    print("Processing MRPC...")
+    mrpc_dir = os.path.join(data_dir, "MRPC")
+    if not os.path.isdir(mrpc_dir):
+        os.mkdir(mrpc_dir)
+    if path_to_data:
+        mrpc_train_file = os.path.join(path_to_data, "msr_paraphrase_train.txt")
+        mrpc_test_file = os.path.join(path_to_data, "msr_paraphrase_test.txt")
+    else:
+        print("Local MRPC data not specified, downloading data from %s" % MRPC_TRAIN)
+        mrpc_train_file = os.path.join(mrpc_dir, "msr_paraphrase_train.txt")
+        mrpc_test_file = os.path.join(mrpc_dir, "msr_paraphrase_test.txt")
+        urllib.request.urlretrieve(MRPC_TRAIN, mrpc_train_file)
+        urllib.request.urlretrieve(MRPC_TEST, mrpc_test_file)
+    assert os.path.isfile(mrpc_train_file), "Train data not found at %s" % mrpc_train_file
+    assert os.path.isfile(mrpc_test_file), "Test data not found at %s" % mrpc_test_file
+    urllib.request.urlretrieve(TASK2PATH["MRPC"], os.path.join(mrpc_dir, "dev_ids.tsv"))
+
+    dev_ids = []
+    with open(os.path.join(mrpc_dir, "dev_ids.tsv"), encoding="utf8") as ids_fh:
+        for row in ids_fh:
+            dev_ids.append(row.strip().split('\t'))
+
+    with open(mrpc_train_file, encoding="utf8") as data_fh, \
+         open(os.path.join(mrpc_dir, "train.tsv"), 'w', encoding="utf8") as train_fh, \
+         open(os.path.join(mrpc_dir, "dev.tsv"), 'w', encoding="utf8") as dev_fh:
+        header = data_fh.readline()
+        train_fh.write(header)
+        dev_fh.write(header)
+        for row in data_fh:
+            label, id1, id2, s1, s2 = row.strip().split('\t')
+            if [id1, id2] in dev_ids:
+                dev_fh.write("%s\t%s\t%s\t%s\t%s\n" % (label, id1, id2, s1, s2))
+            else:
+                train_fh.write("%s\t%s\t%s\t%s\t%s\n" % (label, id1, id2, s1, s2))
+
+    with open(mrpc_test_file, encoding="utf8") as data_fh, \
+            open(os.path.join(mrpc_dir, "test.tsv"), 'w', encoding="utf8") as test_fh:
+        header = data_fh.readline()
+        test_fh.write("index\t#1 ID\t#2 ID\t#1 String\t#2 String\n")
+        for idx, row in enumerate(data_fh):
+            label, id1, id2, s1, s2 = row.strip().split('\t')
+            test_fh.write("%d\t%s\t%s\t%s\t%s\n" % (idx, id1, id2, s1, s2))
+    print("\tCompleted!")
+
+def download_diagnostic(data_dir):
+    print("Downloading and extracting diagnostic...")
+    if not os.path.isdir(os.path.join(data_dir, "diagnostic")):
+        os.mkdir(os.path.join(data_dir, "diagnostic"))
+    data_file = os.path.join(data_dir, "diagnostic", "diagnostic.tsv")
+    urllib.request.urlretrieve(TASK2PATH["diagnostic"], data_file)
+    print("\tCompleted!")
+    return
+
+def get_tasks(task_names):
+    task_names = task_names.split(',')
+    if "all" in task_names:
+        tasks = TASKS
+    else:
+        tasks = []
+        for task_name in task_names:
+            assert task_name in TASKS, "Task %s not found!" % task_name
+            tasks.append(task_name)
+    return tasks
+
+def main(arguments):
+    parser = argparse.ArgumentParser()
+    parser.add_argument('--data_dir', help='directory to save data to', type=str, default='glue_data')
+    parser.add_argument('--tasks', help='tasks to download data for as a comma separated string',
+                        type=str, default='all')
+    parser.add_argument('--path_to_mrpc', help='path to directory containing extracted MRPC data, msr_paraphrase_train.txt and msr_paraphrase_text.txt',
+                        type=str, default='')
+    args = parser.parse_args(arguments)
+
+    if not os.path.isdir(args.data_dir):
+        os.mkdir(args.data_dir)
+    tasks = get_tasks(args.tasks)
+
+    for task in tasks:
+        if task == 'MRPC':
+            format_mrpc(args.data_dir, args.path_to_mrpc)
+        elif task == 'diagnostic':
+            download_diagnostic(args.data_dir)
+        else:
+            download_and_extract(task, args.data_dir)
+
+
+if __name__ == '__main__':
+    sys.exit(main(sys.argv[1:]))

utils/link_tester.py

+""" Link tester.
+
+This little utility reads all the python files in the repository,
+scans for links pointing to S3 and tests the links one by one. Raises an error
+at the end of the scan if at least one link was reported broken.
+"""
+import os
+import re
+import sys
+
+import requests
+
+
+REGEXP_FIND_S3_LINKS = r"""([\"'])(https:\/\/s3)(.*)?\1"""
+
+
+def list_python_files_in_repository():
+    """ List all python files in the repository.
+
+    This function assumes that the script is executed in the root folder.
+    """
+    source_code_files = []
+    for path, subdirs, files in os.walk("."):
+        if "templates" in path:
+            continue
+        for name in files:
+            if ".py" in name and ".pyc" not in name:
+                path_to_files = os.path.join(path, name)
+                source_code_files.append(path_to_files)
+
+    return source_code_files
+
+
+def find_all_links(file_paths):
+    links = []
+    for path in file_paths:
+        links += scan_code_for_links(path)
+
+    return links
+
+
+def scan_code_for_links(source):
+    """ Scans the file to find links using a regular expression.
+    Returns a list of links.
+    """
+    with open(source, 'r') as content:
+        content = content.read()
+        raw_links = re.findall(REGEXP_FIND_S3_LINKS, content)
+        links = [prefix + suffix for _, prefix, suffix in raw_links]
+
+    return links
+
+
+def check_all_links(links):
+    """ Check that the provided links are valid.
+
+    Links are considered valid if a HEAD request to the server
+    returns a 200 status code.
+    """
+    broken_links = []
+    for link in links:
+        head = requests.head(link)
+        if head.status_code != 200:
+            broken_links.append(link)
+
+    return broken_links
+
+
+if __name__ == "__main__":
+    file_paths = list_python_files_in_repository()
+    links = find_all_links(file_paths)
+    broken_links = check_all_links(links)
+    print("Looking for broken links to pre-trained models/configs/tokenizers...")
+    if broken_links:
+        print("The following links did not respond:")
+        for link in broken_links:
+            print("- {}".format(link))
+        sys.exit(1)
+    print("All links are ok.")

valohai.yaml

+---
+
+- step:
+    name: Execute python examples/run_glue.py
+    image: pytorch/pytorch:nightly-devel-cuda10.0-cudnn7
+    command:
+      - python /valohai/repository/utils/download_glue_data.py --data_dir=/glue_data
+      - pip install -e .
+      - pip install -r examples/requirements.txt
+      - python examples/run_glue.py --do_train --data_dir=/glue_data/{parameter-value:task_name} {parameters}
+    parameters:
+      - name: model_type
+        pass-as: --model_type={v}
+        type: string
+        default: bert
+      - name: model_name_or_path
+        pass-as: --model_name_or_path={v}
+        type: string
+        default: bert-base-uncased
+      - name: task_name
+        pass-as: --task_name={v}
+        type: string
+        default: MRPC
+      - name: max_seq_length
+        pass-as: --max_seq_length={v}
+        description: The maximum total input sequence length after tokenization. Sequences longer than this will be truncated, sequences shorter will be padded.
+        type: integer
+        default: 128
+      - name: per_gpu_train_batch_size
+        pass-as: --per_gpu_train_batch_size={v}
+        description: Batch size per GPU/CPU for training.
+        type: integer
+        default: 8
+      - name: per_gpu_eval_batch_size
+        pass-as: --per_gpu_eval_batch_size={v}
+        description: Batch size per GPU/CPU for evaluation.
+        type: integer
+        default: 8
+      - name: gradient_accumulation_steps
+        pass-as: --gradient_accumulation_steps={v}
+        description: Number of updates steps to accumulate before performing a backward/update pass.
+        type: integer
+        default: 1
+      - name: learning_rate
+        pass-as: --learning_rate={v}
+        description: The initial learning rate for Adam.
+        type: float
+        default: 0.00005
+      - name: adam_epsilon
+        pass-as: --adam_epsilon={v}
+        description: Epsilon for Adam optimizer.
+        type: float
+        default: 0.00000001
+      - name: max_grad_norm
+        pass-as: --max_grad_norm={v}
+        description: Max gradient norm.
+        type: float
+        default: 1.0
+      - name: num_train_epochs
+        pass-as: --num_train_epochs={v}
+        description: Total number of training epochs to perform.
+        type: integer
+        default: 3
+      - name: max_steps
+        pass-as: --max_steps={v}
+        description: If > 0, set total number of training steps to perform. Override num_train_epochs.
+        type: integer
+        default: -1
+      - name: warmup_steps
+        pass-as: --warmup_steps={v}
+        description: Linear warmup over warmup_steps.
+        type: integer
+        default: -1
+      - name: logging_steps
+        pass-as: --logging_steps={v}
+        description: Log every X updates steps.
+        type: integer
+        default: 25
+      - name: save_steps
+        pass-as: --save_steps={v}
+        description: Save checkpoint every X updates steps.
+        type: integer
+        default: -1
+      - name: output_dir
+        pass-as: --output_dir={v}
+        type: string
+        default: /valohai/outputs
+      - name: evaluate_during_training
+        description: Run evaluation during training at each logging step.
+        type: flag
+        default: true
+      - name: do_lower_case
+        description: Set this flag if you are using an uncased model.
+        type: flag