riaz.somc/transformers
1
0
Fork 0
mirror of https://github.com/huggingface/transformers.git synced 2025-08-01 02:31:11 +06:00
Code Issues Actions 3 Packages Projects Releases Wiki Activity

re-format

Browse Source
This commit is contained in:
jamin 2019-08-30 14:05:28 +09:00
parent c8731b9583
commit 2fb9a934b4
1 changed files with 24 additions and 24 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

22
examples/lm_finetuning/finetune_on_pregenerated.py
View File

@ -1,20 +1,22 @@
import json
import logging
import random
from argparse import ArgumentParser
from collections import namedtuple
from pathlib import Path
import os
import torch
import logging
import json
import random
import numpy as np
from collections import namedtuple
from tempfile import TemporaryDirectory
import numpy as np
import torch
from torch.utils.data import DataLoader, Dataset, RandomSampler
from torch.utils.data.distributed import DistributedSampler
from tqdm import tqdm
from pytorch_transformers import WEIGHTS_NAME, CONFIG_NAME
from pytorch_transformers.modeling_bert import BertForPreTraining
from pytorch_transformers.optimization import AdamW, WarmupLinearSchedule
from pytorch_transformers.tokenization_bert import BertTokenizer
from pytorch_transformers.optimization import AdamW, WarmupLinearSchedule
InputFeatures = namedtuple("InputFeatures", "input_ids input_mask segment_ids lm_label_ids is_next")
@ -123,8 +125,7 @@ def main():
parser = ArgumentParser()
parser.add_argument('--pregenerated_data', type=Path, required=True)
parser.add_argument('--output_dir', type=Path, required=True)
parser.add_argument("--bert_model", type=str, required=True,
help="Bert pre-trained model selected in the list: bert-base-uncased, "
parser.add_argument("--bert_model", type=str, required=True, help="Bert pre-trained model selected in the list: bert-base-uncased, "
"bert-large-uncased, bert-base-cased, bert-base-multilingual, bert-base-chinese.")
parser.add_argument("--do_lower_case", action="store_true")
parser.add_argument("--reduce_memory", action="store_true",
@ -336,8 +337,7 @@ def main():
# Save a trained model
if args.local_rank == -1 or torch.distributed.get_rank() == 0:
logging.info("** ** * Saving fine-tuned model ** ** * ")
model_to_save = model.module if hasattr(model,
'module') else model # Take care of distributed/parallel training
model_to_save = model.module if hasattr(model, 'module') else model # Take care of distributed/parallel training
model_to_save.save_pretrained(args.output_dir)
tokenizer.save_pretrained(args.output_dir)