SUMIN/HuggingFace_transformer
1
0
Fork 0
Code Issues Pull Requests Actions 7 Packages Projects Releases Wiki Activity

[Examples] Replicates the new --log_level feature to all trainer-based pytorch (#12359)

Browse Source 
* added log_level

* fix comment

* fixed log_level

* Trigger CI

* Unfied logging

* simplified args for log_level
This commit is contained in:
Bhadresh Savani
2021-06-25 22:58:42 +01:00
committed by GitHub
parent 64e6098094
commit 539ee456d4
13 changed files with 202 additions and 165 deletions
Download Patch File Download Diff File Expand all files Collapse all files

25
examples/pytorch/multiple-choice/run_swag.py
View File

@@ -24,6 +24,7 @@ import sys
from dataclasses import dataclass, field
from typing import Optional, Union
import datasets
import numpy as np
import torch
from datasets import load_dataset
@@ -220,18 +221,18 @@ def main():
datefmt="%m/%d/%Y %H:%M:%S",
handlers=[logging.StreamHandler(sys.stdout)],
)
logger.setLevel(logging.INFO if training_args.should_log else logging.WARN)
log_level = training_args.get_process_log_level()
logger.setLevel(log_level)
datasets.utils.logging.set_verbosity(log_level)
transformers.utils.logging.set_verbosity(log_level)
transformers.utils.logging.enable_default_handler()
transformers.utils.logging.enable_explicit_format()
# Log on each process the small summary:
logger.warning(
f"Process rank: {training_args.local_rank}, device: {training_args.device}, n_gpu: {training_args.n_gpu}"
+ f"distributed training: {bool(training_args.local_rank != -1)}, 16-bits training: {training_args.fp16}"
)
# Set the verbosity to info of the Transformers logger (on main process only):
if training_args.should_log:
transformers.utils.logging.set_verbosity_info()
transformers.utils.logging.enable_default_handler()
transformers.utils.logging.enable_explicit_format()
logger.info(f"Training/evaluation parameters {training_args}")
# Detecting last checkpoint.
@@ -268,10 +269,10 @@ def main():
if data_args.validation_file is not None:
data_files["validation"] = data_args.validation_file
extension = data_args.train_file.split(".")[-1]
datasets = load_dataset(extension, data_files=data_files, cache_dir=model_args.cache_dir)
raw_datasets = load_dataset(extension, data_files=data_files, cache_dir=model_args.cache_dir)
else:
# Downloading and loading the swag dataset from the hub.
datasets = load_dataset("swag", "regular", cache_dir=model_args.cache_dir)
raw_datasets = load_dataset("swag", "regular", cache_dir=model_args.cache_dir)
# See more about loading any type of standard or custom dataset (from files, python dict, pandas DataFrame, etc) at
# https://huggingface.co/docs/datasets/loading_datasets.html.
@@ -347,9 +348,9 @@ def main():
return {k: [v[i : i + 4] for i in range(0, len(v), 4)] for k, v in tokenized_examples.items()}
if training_args.do_train:
if "train" not in datasets:
if "train" not in raw_datasets:
raise ValueError("--do_train requires a train dataset")
train_dataset = datasets["train"]
train_dataset = raw_datasets["train"]
if data_args.max_train_samples is not None:
train_dataset = train_dataset.select(range(data_args.max_train_samples))
train_dataset = train_dataset.map(
@@ -360,9 +361,9 @@ def main():
)
if training_args.do_eval:
if "validation" not in datasets:
if "validation" not in raw_datasets:
raise ValueError("--do_eval requires a validation dataset")
eval_dataset = datasets["validation"]
eval_dataset = raw_datasets["validation"]
if data_args.max_eval_samples is not None:
eval_dataset = eval_dataset.select(range(data_args.max_eval_samples))
eval_dataset = eval_dataset.map(