File size: 13,166 Bytes
9615cd6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
"""
Fine-tuning the library models for language modeling on a text file (GPT, GPT-2, CTRL, BERT, RoBERTa, XLNet).
GPT, GPT-2 and CTRL are fine-tuned using a causal language modeling (CLM) loss. BERT and RoBERTa are fine-tuned
using a masked language modeling (MLM) loss. XLNet is fine-tuned using a permutation language modeling (PLM) loss.
"""

import logging
import math
import os
from dataclasses import dataclass, field
from glob import glob
from typing import Optional

from torch.utils.data import ConcatDataset

import transformers
from transformers import (
    CONFIG_MAPPING,
    MODEL_WITH_LM_HEAD_MAPPING,
    AutoConfig,
    AutoModelWithLMHead,
    AutoTokenizer,
    DataCollatorForLanguageModeling,
    DataCollatorForPermutationLanguageModeling,
    DataCollatorForWholeWordMask,
    HfArgumentParser,
    LineByLineTextDataset,
    LineByLineWithRefDataset,
    PreTrainedTokenizer,
    TextDataset,
    Trainer,
    TrainingArguments,
    set_seed,
)
from transformers.trainer_utils import is_main_process


logger = logging.getLogger(__name__)


MODEL_CONFIG_CLASSES = list(MODEL_WITH_LM_HEAD_MAPPING.keys())
MODEL_TYPES = tuple(conf.model_type for conf in MODEL_CONFIG_CLASSES)


@dataclass
class ModelArguments:
    """
    Arguments pertaining to which model/config/tokenizer we are going to fine-tune, or train from scratch.
    """

    model_name_or_path: Optional[str] = field(
        default=None,
        metadata={
            "help": (
                "The model checkpoint for weights initialization. Leave None if you want to train a model from"
                " scratch."
            )
        },
    )
    model_type: Optional[str] = field(
        default=None,
        metadata={"help": "If training from scratch, pass a model type from the list: " + ", ".join(MODEL_TYPES)},
    )
    config_name: Optional[str] = field(
        default=None, metadata={"help": "Pretrained config name or path if not the same as model_name"}
    )
    tokenizer_name: Optional[str] = field(
        default=None, metadata={"help": "Pretrained tokenizer name or path if not the same as model_name"}
    )
    cache_dir: Optional[str] = field(
        default=None,
        metadata={"help": "Where do you want to store the pretrained models downloaded from huggingface.co"},
    )


@dataclass
class DataTrainingArguments:
    """
    Arguments pertaining to what data we are going to input our model for training and eval.
    """

    train_data_file: Optional[str] = field(
        default=None, metadata={"help": "The input training data file (a text file)."}
    )
    train_data_files: Optional[str] = field(
        default=None,
        metadata={
            "help": (
                "The input training data files (multiple files in glob format). "
                "Very often splitting large files to smaller files can prevent tokenizer going out of memory"
            )
        },
    )
    eval_data_file: Optional[str] = field(
        default=None,
        metadata={"help": "An optional input evaluation data file to evaluate the perplexity on (a text file)."},
    )
    train_ref_file: Optional[str] = field(
        default=None,
        metadata={"help": "An optional input train ref data file for whole word mask in Chinese."},
    )
    eval_ref_file: Optional[str] = field(
        default=None,
        metadata={"help": "An optional input eval ref data file for whole word mask in Chinese."},
    )
    line_by_line: bool = field(
        default=False,
        metadata={"help": "Whether distinct lines of text in the dataset are to be handled as distinct sequences."},
    )

    mlm: bool = field(
        default=False, metadata={"help": "Train with masked-language modeling loss instead of language modeling."}
    )
    whole_word_mask: bool = field(default=False, metadata={"help": "Whether ot not to use whole word mask."})
    mlm_probability: float = field(
        default=0.15, metadata={"help": "Ratio of tokens to mask for masked language modeling loss"}
    )
    plm_probability: float = field(
        default=1 / 6,
        metadata={
            "help": (
                "Ratio of length of a span of masked tokens to surrounding context length for permutation language"
                " modeling."
            )
        },
    )
    max_span_length: int = field(
        default=5, metadata={"help": "Maximum length of a span of masked tokens for permutation language modeling."}
    )

    block_size: int = field(
        default=-1,
        metadata={
            "help": (
                "Optional input sequence length after tokenization. "
                "The training dataset will be truncated in block of this size for training."
                "Default to the model max input length for single sentence inputs (take into account special tokens)."
            )
        },
    )
    overwrite_cache: bool = field(
        default=False, metadata={"help": "Overwrite the cached training and evaluation sets"}
    )


def get_dataset(
    args: DataTrainingArguments,
    tokenizer: PreTrainedTokenizer,
    evaluate: bool = False,
    cache_dir: Optional[str] = None,
):
    def _dataset(file_path, ref_path=None):
        if args.line_by_line:
            if ref_path is not None:
                if not args.whole_word_mask or not args.mlm:
                    raise ValueError("You need to set world whole masking and mlm to True for Chinese Whole Word Mask")
                return LineByLineWithRefDataset(
                    tokenizer=tokenizer,
                    file_path=file_path,
                    block_size=args.block_size,
                    ref_path=ref_path,
                )

            return LineByLineTextDataset(tokenizer=tokenizer, file_path=file_path, block_size=args.block_size)
        else:
            return TextDataset(
                tokenizer=tokenizer,
                file_path=file_path,
                block_size=args.block_size,
                overwrite_cache=args.overwrite_cache,
                cache_dir=cache_dir,
            )

    if evaluate:
        return _dataset(args.eval_data_file, args.eval_ref_file)
    elif args.train_data_files:
        return ConcatDataset([_dataset(f) for f in glob(args.train_data_files)])
    else:
        return _dataset(args.train_data_file, args.train_ref_file)


def main():
    # See all possible arguments in src/transformers/training_args.py
    # or by passing the --help flag to this script.
    # We now keep distinct sets of args, for a cleaner separation of concerns.

    parser = HfArgumentParser((ModelArguments, DataTrainingArguments, TrainingArguments))
    model_args, data_args, training_args = parser.parse_args_into_dataclasses()

    if data_args.eval_data_file is None and training_args.do_eval:
        raise ValueError(
            "Cannot do evaluation without an evaluation data file. Either supply a file to --eval_data_file "
            "or remove the --do_eval argument."
        )
    if (
        os.path.exists(training_args.output_dir)
        and os.listdir(training_args.output_dir)
        and training_args.do_train
        and not training_args.overwrite_output_dir
    ):
        raise ValueError(
            f"Output directory ({training_args.output_dir}) already exists and is not empty. Use"
            " --overwrite_output_dir to overcome."
        )

    # Setup logging
    logging.basicConfig(
        format="%(asctime)s - %(levelname)s - %(name)s - %(message)s",
        datefmt="%m/%d/%Y %H:%M:%S",
        level=logging.INFO if training_args.local_rank in [-1, 0] else logging.WARN,
    )
    logger.warning(
        "Process rank: %s, device: %s, n_gpu: %s, distributed training: %s, 16-bits training: %s",
        training_args.local_rank,
        training_args.device,
        training_args.n_gpu,
        bool(training_args.local_rank != -1),
        training_args.fp16,
    )
    # Set the verbosity to info of the Transformers logger (on main process only):
    if is_main_process(training_args.local_rank):
        transformers.utils.logging.set_verbosity_info()
        transformers.utils.logging.enable_default_handler()
        transformers.utils.logging.enable_explicit_format()
    logger.info("Training/evaluation parameters %s", training_args)

    # Set seed
    set_seed(training_args.seed)

    # Load pretrained model and tokenizer
    #
    # Distributed training:
    # The .from_pretrained methods guarantee that only one local process can concurrently
    # download model & vocab.

    if model_args.config_name:
        config = AutoConfig.from_pretrained(model_args.config_name, cache_dir=model_args.cache_dir)
    elif model_args.model_name_or_path:
        config = AutoConfig.from_pretrained(model_args.model_name_or_path, cache_dir=model_args.cache_dir)
    else:
        config = CONFIG_MAPPING[model_args.model_type]()
        logger.warning("You are instantiating a new config instance from scratch.")

    if model_args.tokenizer_name:
        tokenizer = AutoTokenizer.from_pretrained(model_args.tokenizer_name, cache_dir=model_args.cache_dir)
    elif model_args.model_name_or_path:
        tokenizer = AutoTokenizer.from_pretrained(model_args.model_name_or_path, cache_dir=model_args.cache_dir)
    else:
        raise ValueError(
            "You are instantiating a new tokenizer from scratch. This is not supported, but you can do it from another"
            " script, save it,and load it from here, using --tokenizer_name"
        )

    if model_args.model_name_or_path:
        model = AutoModelWithLMHead.from_pretrained(
            model_args.model_name_or_path,
            from_tf=bool(".ckpt" in model_args.model_name_or_path),
            config=config,
            cache_dir=model_args.cache_dir,
        )
    else:
        logger.info("Training new model from scratch")
        model = AutoModelWithLMHead.from_config(config)

    model.resize_token_embeddings(len(tokenizer))

    if config.model_type in ["bert", "roberta", "distilbert", "camembert"] and not data_args.mlm:
        raise ValueError(
            "BERT and RoBERTa-like models do not have LM heads but masked LM heads. They must be run using the "
            "--mlm flag (masked language modeling)."
        )

    if data_args.block_size <= 0:
        data_args.block_size = tokenizer.max_len
        # Our input block size will be the max possible for the model
    else:
        data_args.block_size = min(data_args.block_size, tokenizer.max_len)

    # Get datasets

    train_dataset = (
        get_dataset(data_args, tokenizer=tokenizer, cache_dir=model_args.cache_dir) if training_args.do_train else None
    )
    eval_dataset = (
        get_dataset(data_args, tokenizer=tokenizer, evaluate=True, cache_dir=model_args.cache_dir)
        if training_args.do_eval
        else None
    )
    if config.model_type == "xlnet":
        data_collator = DataCollatorForPermutationLanguageModeling(
            tokenizer=tokenizer,
            plm_probability=data_args.plm_probability,
            max_span_length=data_args.max_span_length,
        )
    else:
        if data_args.mlm and data_args.whole_word_mask:
            data_collator = DataCollatorForWholeWordMask(
                tokenizer=tokenizer, mlm_probability=data_args.mlm_probability
            )
        else:
            data_collator = DataCollatorForLanguageModeling(
                tokenizer=tokenizer, mlm=data_args.mlm, mlm_probability=data_args.mlm_probability
            )

    # Initialize our Trainer
    trainer = Trainer(
        model=model,
        args=training_args,
        data_collator=data_collator,
        train_dataset=train_dataset,
        eval_dataset=eval_dataset,
        prediction_loss_only=True,
    )

    # Training
    if training_args.do_train:
        model_path = (
            model_args.model_name_or_path
            if model_args.model_name_or_path is not None and os.path.isdir(model_args.model_name_or_path)
            else None
        )
        trainer.train(model_path=model_path)
        trainer.save_model()
        # For convenience, we also re-save the tokenizer to the same directory,
        # so that you can share your model easily on huggingface.co/models =)
        if trainer.is_world_master():
            tokenizer.save_pretrained(training_args.output_dir)

    # Evaluation
    results = {}
    if training_args.do_eval:
        logger.info("*** Evaluate ***")

        eval_output = trainer.evaluate()

        perplexity = math.exp(eval_output["eval_loss"])
        result = {"perplexity": perplexity}

        output_eval_file = os.path.join(training_args.output_dir, "eval_results_lm.txt")
        if trainer.is_world_master():
            with open(output_eval_file, "w") as writer:
                logger.info("***** Eval results *****")
                for key in sorted(result.keys()):
                    logger.info("  %s = %s", key, str(result[key]))
                    writer.write("%s = %s\n" % (key, str(result[key])))

        results.update(result)

    return results


def _mp_fn(index):
    # For xla_spawn (TPUs)
    main()


if __name__ == "__main__":
    main()