Spaces:
Configuration error
Configuration error
File size: 4,173 Bytes
25f0c96 |
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 |
from sagemaker.huggingface import HuggingFace
import logging
import sys
from contextlib import contextmanager
from io import StringIO
from streamlit.report_thread import REPORT_CONTEXT_ATTR_NAME
from threading import current_thread
import streamlit as st
import sys
import sagemaker
import boto3
@contextmanager
def st_redirect(src, dst):
placeholder = st.empty()
output_func = getattr(placeholder, dst)
with StringIO() as buffer:
old_write = src.write
def new_write(b):
if getattr(current_thread(), REPORT_CONTEXT_ATTR_NAME, None):
buffer.write(b)
output_func(buffer.getvalue())
else:
old_write(b)
try:
src.write = new_write
yield
finally:
src.write = old_write
@contextmanager
def st_stdout(dst):
with st_redirect(sys.stdout, dst):
yield
@contextmanager
def st_stderr(dst):
with st_redirect(sys.stderr, dst):
yield
task2script = {
"text-classification": {
"entry_point": "run_glue.py",
"source_dir": "examples/text-classification",
},
"token-classification": {
"entry_point": "run_ner.py",
"source_dir": "examples/token-classification",
},
"question-answering": {
"entry_point": "run_qa.py",
"source_dir": "examples/question-answering",
},
"summarization": {
"entry_point": "run_summarization.py",
"source_dir": "examples/seq2seq",
},
"translation": {
"entry_point": "run_translation.py",
"source_dir": "examples/seq2seq",
},
"causal-language-modeling": {
"entry_point": "run_clm.py",
"source_dir": "examples/language-modeling",
},
"masked-language-modeling": {
"entry_point": "run_mlm.py",
"source_dir": "examples/language-modeling",
},
}
def train_estimtator(parameter, config):
with st_stdout("code"):
logger = logging.getLogger(__name__)
logging.basicConfig(
level=logging.getLevelName("INFO"),
handlers=[logging.StreamHandler(sys.stdout)],
format="%(asctime)s - %(name)s - %(levelname)s - %(message)s",
)
logger.info = print
# git configuration to download our fine-tuning script
git_config = {"repo": "https://github.com/huggingface/transformers.git", "branch": "v4.4.2"}
# creating fine-tuning script
entry_point = task2script[parameter["task"]]["entry_point"]
source_dir = task2script[parameter["task"]]["source_dir"]
# create train file
# iam configuration
session = boto3.session.Session(
aws_access_key_id=config["aws_access_key_id"],
aws_secret_access_key=config["aws_secret_accesskey"],
region_name=config["region"],
)
sess = sagemaker.Session(boto_session=session)
iam = session.client(
"iam", aws_access_key_id=config["aws_access_key_id"], aws_secret_access_key=config["aws_secret_accesskey"]
)
role = iam.get_role(RoleName=config["aws_sagemaker_role"])["Role"]["Arn"]
logger.info(f"role: {role}")
instance_type = config["instance_type"].split("|")[1].split("|")[0].strip()
logger.info(f"instance_type: {instance_type}")
hyperparameters = {
"output_dir": "/opt/ml/model",
"do_train": True,
"do_eval": True,
"do_predict": True,
**parameter,
}
del hyperparameters["task"]
# create estimator
huggingface_estimator = HuggingFace(
entry_point=entry_point,
source_dir=source_dir,
git_config=git_config,
base_job_name=config["job_name"],
instance_type=instance_type,
sagemaker_session=sess,
instance_count=config["instance_count"],
role=role,
transformers_version="4.4",
pytorch_version="1.6",
py_version="py36",
hyperparameters=hyperparameters,
)
# train
huggingface_estimator.fit()
|