riaz.somc/transformers
1
0
Fork 0
mirror of https://github.com/huggingface/transformers.git synced 2025-07-24 23:08:57 +06:00
Code Issues Actions 32 Packages Projects Releases Wiki Activity

Merge pull request #672 from oliverguhr/master

Browse Source 
Add vocabulary and model config to the finetune output
This commit is contained in:
Thomas Wolf 2019-06-14 17:02:47 +02:00 committed by GitHub
commit cad88e19de
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
2 changed files with 14 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

11
examples/lm_finetuning/finetune_on_pregenerated.py
View File

@ -1,5 +1,6 @@
from argparse import ArgumentParser
from pathlib import Path
import os
import torch
import logging
import json
@ -12,6 +13,7 @@ from torch.utils.data import DataLoader, Dataset, RandomSampler
from torch.utils.data.distributed import DistributedSampler
from tqdm import tqdm
from pytorch_pretrained_bert import WEIGHTS_NAME, CONFIG_NAME
from pytorch_pretrained_bert.modeling import BertForPreTraining
from pytorch_pretrained_bert.tokenization import BertTokenizer
from pytorch_pretrained_bert.optimization import BertAdam, WarmupLinearSchedule
@ -325,8 +327,13 @@ def main():
# Save a trained model
logging.info("** ** * Saving fine-tuned model ** ** * ")
model_to_save = model.module if hasattr(model, 'module') else model # Only save the model it-self
output_model_file = args.output_dir / "pytorch_model.bin"
torch.save(model_to_save.state_dict(), str(output_model_file))
output_model_file = os.path.join(args.output_dir, WEIGHTS_NAME)
output_config_file = os.path.join(args.output_dir, CONFIG_NAME)
torch.save(model_to_save.state_dict(), output_model_file)
model_to_save.config.to_json_file(output_config_file)
tokenizer.save_vocabulary(args.output_dir)
if __name__ == '__main__':

6
examples/lm_finetuning/simple_lm_finetuning.py
View File

@ -29,6 +29,7 @@ from torch.utils.data import DataLoader, Dataset, RandomSampler
from torch.utils.data.distributed import DistributedSampler
from tqdm import tqdm, trange
from pytorch_pretrained_bert import WEIGHTS_NAME, CONFIG_NAME
from pytorch_pretrained_bert.modeling import BertForPreTraining
from pytorch_pretrained_bert.tokenization import BertTokenizer
from pytorch_pretrained_bert.optimization import BertAdam, WarmupLinearSchedule
@ -614,9 +615,12 @@ def main():
# Save a trained model
logger.info("** ** * Saving fine - tuned model ** ** * ")
model_to_save = model.module if hasattr(model, 'module') else model # Only save the model it-self
output_model_file = os.path.join(args.output_dir, "pytorch_model.bin")
output_model_file = os.path.join(args.output_dir, WEIGHTS_NAME)
output_config_file = os.path.join(args.output_dir, CONFIG_NAME)
if args.do_train:
torch.save(model_to_save.state_dict(), output_model_file)
model_to_save.config.to_json_file(output_config_file)
tokenizer.save_vocabulary(args.output_dir)
def _truncate_seq_pair(tokens_a, tokens_b, max_length):