初始化项目，由ModelHub XC社区提供模型
Model: AI4PD/ZymCTRL Source: Original Platform
This commit is contained in:
ModelHub XC
385
5.run_clm-post.py
Normal file
385
5.run_clm-post.py
Normal file
@@ -0,0 +1,385 @@
|
||||
#!/usr/bin/env python
|
||||
# coding=utf-8
|
||||
# Copyright 2020 The HuggingFace Inc. team. All rights reserved.
|
||||
#
|
||||
# Licensed under the Apache License, Version 2.0 (the "License");
|
||||
# you may not use this file except in compliance with the License.
|
||||
# You may obtain a copy of the License at
|
||||
#
|
||||
# http://www.apache.org/licenses/LICENSE-2.0
|
||||
#
|
||||
# Unless required by applicable law or agreed to in writing, software
|
||||
# distributed under the License is distributed on an "AS IS" BASIS,
|
||||
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
# See the License for the specific language governing permissions and
|
||||
# limitations under the License.
|
||||
"""
|
||||
Fine-tuning the library models for causal language modeling (GPT, GPT-2, CTRL, ...) on a text file or a dataset.
|
||||
|
||||
Here is the full list of checkpoints on the hub that can be fine-tuned by this script:
|
||||
https://huggingface.co/models?filter=causal-lm
|
||||
"""
|
||||
# You can also adapt this script on your own causal language modeling task. Pointers for this are left as comments.
|
||||
|
||||
import logging
|
||||
import math
|
||||
import os
|
||||
import sys
|
||||
from dataclasses import dataclass, field
|
||||
from typing import Optional
|
||||
|
||||
import datasets
|
||||
from datasets import load_dataset
|
||||
from datasets import load_from_disk
|
||||
|
||||
import transformers
|
||||
from transformers import (
|
||||
CONFIG_MAPPING,
|
||||
MODEL_FOR_CAUSAL_LM_MAPPING,
|
||||
AutoConfig,
|
||||
AutoModelForCausalLM,
|
||||
AutoTokenizer,
|
||||
HfArgumentParser,
|
||||
Trainer,
|
||||
TrainingArguments,
|
||||
default_data_collator,
|
||||
set_seed,
|
||||
)
|
||||
from transformers.testing_utils import CaptureLogger
|
||||
from transformers.trainer_utils import get_last_checkpoint
|
||||
from transformers.utils import check_min_version
|
||||
from transformers.utils.versions import require_version
|
||||
|
||||
|
||||
# Will error if the minimal version of Transformers is not installed. Remove at your own risks.
|
||||
check_min_version("4.13.0.dev0")
|
||||
|
||||
require_version("datasets>=1.8.0", "To fix: pip install -r examples/pytorch/language-modeling/requirements.txt")
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
MODEL_CONFIG_CLASSES = list(MODEL_FOR_CAUSAL_LM_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."
|
||||
"Don't set 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_overrides: Optional[str] = field(
|
||||
default=None,
|
||||
metadata={
|
||||
"help": "Override some existing default config settings when a model is trained from scratch. Example: "
|
||||
"n_embd=10,resid_pdrop=0.2,scale_attn_weights=false,summary_type=cls_index"
|
||||
},
|
||||
)
|
||||
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"},
|
||||
)
|
||||
use_fast_tokenizer: bool = field(
|
||||
default=True,
|
||||
metadata={"help": "Whether to use one of the fast tokenizer (backed by the tokenizers library) or not."},
|
||||
)
|
||||
model_revision: str = field(
|
||||
default="main",
|
||||
metadata={"help": "The specific model version to use (can be a branch name, tag name or commit id)."},
|
||||
)
|
||||
use_auth_token: bool = field(
|
||||
default=False,
|
||||
metadata={
|
||||
"help": "Will use the token generated when running `transformers-cli login` (necessary to use this script "
|
||||
"with private models)."
|
||||
},
|
||||
)
|
||||
|
||||
def __post_init__(self):
|
||||
if self.config_overrides is not None and (self.config_name is not None or self.model_name_or_path is not None):
|
||||
raise ValueError(
|
||||
"--config_overrides can't be used in combination with --config_name or --model_name_or_path"
|
||||
)
|
||||
|
||||
|
||||
@dataclass
|
||||
class DataTrainingArguments:
|
||||
"""
|
||||
Arguments pertaining to what data we are going to input our model for training and eval.
|
||||
"""
|
||||
|
||||
dataset_name: Optional[str] = field(
|
||||
default=None, metadata={"help": "The name of the dataset to use (via the datasets library)."}
|
||||
)
|
||||
dataset_config_name: Optional[str] = field(
|
||||
default=None, metadata={"help": "The configuration name of the dataset to use (via the datasets library)."}
|
||||
)
|
||||
train_file: Optional[str] = field(default=None, metadata={"help": "The input training data file (a text file)."})
|
||||
validation_file: Optional[str] = field(
|
||||
default=None,
|
||||
metadata={"help": "An optional input evaluation data file to evaluate the perplexity on (a text file)."},
|
||||
)
|
||||
max_train_samples: Optional[int] = field(
|
||||
default=None,
|
||||
metadata={
|
||||
"help": "For debugging purposes or quicker training, truncate the number of training examples to this "
|
||||
"value if set."
|
||||
},
|
||||
)
|
||||
max_eval_samples: Optional[int] = field(
|
||||
default=None,
|
||||
metadata={
|
||||
"help": "For debugging purposes or quicker training, truncate the number of evaluation examples to this "
|
||||
"value if set."
|
||||
},
|
||||
)
|
||||
|
||||
block_size: Optional[int] = field(
|
||||
default=None,
|
||||
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"}
|
||||
)
|
||||
validation_split_percentage: Optional[int] = field(
|
||||
default=5,
|
||||
metadata={
|
||||
"help": "The percentage of the train set used as validation set in case there's no validation split"
|
||||
},
|
||||
)
|
||||
preprocessing_num_workers: Optional[int] = field(
|
||||
default=None,
|
||||
metadata={"help": "The number of processes to use for the preprocessing."},
|
||||
)
|
||||
keep_linebreaks: bool = field(
|
||||
default=True, metadata={"help": "Whether to keep line breaks when using TXT files or not."}
|
||||
)
|
||||
|
||||
#def __post_init__(self):
|
||||
# if self.dataset_name is None and self.train_file is None and self.validation_file is None:
|
||||
# raise ValueError("Need either a dataset name or a training/validation file.")
|
||||
# else:
|
||||
# if self.train_file is not None:
|
||||
# extension = self.train_file.split(".")[-1]
|
||||
# assert extension in ["csv", "json", "txt"], "`train_file` should be a csv, a json or a txt file."
|
||||
# if self.validation_file is not None:
|
||||
# extension = self.validation_file.split(".")[-1]
|
||||
# assert extension in ["csv", "json", "txt"], "`validation_file` should be a csv, a json or a txt 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))
|
||||
if len(sys.argv) == 2 and sys.argv[1].endswith(".json"):
|
||||
# If we pass only one argument to the script and it's the path to a json file,
|
||||
# let's parse it to get our arguments.
|
||||
model_args, data_args, training_args = parser.parse_json_file(json_file=os.path.abspath(sys.argv[1]))
|
||||
else:
|
||||
model_args, data_args, training_args = parser.parse_args_into_dataclasses()
|
||||
|
||||
# Setup logging
|
||||
logging.basicConfig(
|
||||
format="%(asctime)s - %(levelname)s - %(name)s - %(message)s",
|
||||
datefmt="%m/%d/%Y %H:%M:%S",
|
||||
handlers=[logging.StreamHandler(sys.stdout)],
|
||||
)
|
||||
|
||||
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}"
|
||||
)
|
||||
logger.info(f"Training/evaluation parameters {training_args}")
|
||||
|
||||
# Detecting last checkpoint.
|
||||
last_checkpoint = None
|
||||
if os.path.isdir(training_args.output_dir) and training_args.do_train and not training_args.overwrite_output_dir:
|
||||
last_checkpoint = get_last_checkpoint(training_args.output_dir)
|
||||
if last_checkpoint is None and len(os.listdir(training_args.output_dir)) > 0:
|
||||
raise ValueError(
|
||||
f"Output directory ({training_args.output_dir}) already exists and is not empty. "
|
||||
"Use --overwrite_output_dir to overcome."
|
||||
)
|
||||
elif last_checkpoint is not None and training_args.resume_from_checkpoint is None:
|
||||
logger.info(
|
||||
f"Checkpoint detected, resuming training at {last_checkpoint}. To avoid this behavior, change "
|
||||
"the `--output_dir` or add `--overwrite_output_dir` to train from scratch."
|
||||
)
|
||||
|
||||
# Set seed before initializing model.
|
||||
set_seed(training_args.seed)
|
||||
|
||||
# Get the datasets: you can either provide your own CSV/JSON/TXT training and evaluation files (see below)
|
||||
# or just provide the name of one of the public datasets available on the hub at https://huggingface.co/datasets/
|
||||
# (the dataset will be downloaded automatically from the datasets Hub).
|
||||
#
|
||||
# For CSV/JSON files, this script will use the column called 'text' or the first column if no column called
|
||||
# 'text' is found. You can easily tweak this behavior (see below).
|
||||
#
|
||||
# In distributed training, the load_dataset function guarantee that only one local process can concurrently
|
||||
# download the dataset.
|
||||
|
||||
# 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.
|
||||
|
||||
# Load pretrained model and tokenizer
|
||||
#
|
||||
# Distributed training:
|
||||
# The .from_pretrained methods guarantee that only one local process can concurrently
|
||||
# download model & vocab.
|
||||
|
||||
config_kwargs = {
|
||||
"cache_dir": model_args.cache_dir,
|
||||
"revision": model_args.model_revision,
|
||||
"use_auth_token": True if model_args.use_auth_token else None,
|
||||
}
|
||||
if model_args.config_name:
|
||||
config = AutoConfig.from_pretrained(model_args.config_name, **config_kwargs)
|
||||
elif model_args.model_name_or_path:
|
||||
config = AutoConfig.from_pretrained(model_args.model_name_or_path, **config_kwargs)
|
||||
else:
|
||||
config = CONFIG_MAPPING[model_args.model_type]()
|
||||
logger.warning("You are instantiating a new config instance from scratch.")
|
||||
if model_args.config_overrides is not None:
|
||||
logger.info(f"Overriding config: {model_args.config_overrides}")
|
||||
config.update_from_string(model_args.config_overrides)
|
||||
|
||||
tokenizer_kwargs = {
|
||||
"cache_dir": model_args.cache_dir,
|
||||
"use_fast": model_args.use_fast_tokenizer,
|
||||
"revision": model_args.model_revision,
|
||||
"use_auth_token": True if model_args.use_auth_token else None,
|
||||
}
|
||||
if model_args.tokenizer_name:
|
||||
tokenizer = AutoTokenizer.from_pretrained(model_args.tokenizer_name, **tokenizer_kwargs)
|
||||
elif model_args.model_name_or_path:
|
||||
tokenizer = AutoTokenizer.from_pretrained(model_args.model_name_or_path, **tokenizer_kwargs)
|
||||
else:
|
||||
raise ValueError(
|
||||
"You are instantiating a new tokenizer from scratch. This is not supported by this script."
|
||||
"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 = AutoModelForCausalLM.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,
|
||||
revision=model_args.model_revision,
|
||||
use_auth_token=True if model_args.use_auth_token else None,
|
||||
)
|
||||
else:
|
||||
model = AutoModelForCausalLM.from_config(config)
|
||||
n_params = sum(dict((p.data_ptr(), p.numel()) for p in model.parameters()).values())
|
||||
logger.info(f"Training new model from scratch - Total size={n_params/2**20:.2f}M params")
|
||||
|
||||
model.resize_token_embeddings(len(tokenizer))
|
||||
|
||||
train_dataset = load_from_disk('dataset/train2')
|
||||
eval_dataset = load_from_disk('dataset/eval2')
|
||||
|
||||
# Initialize our Trainer
|
||||
trainer = Trainer(
|
||||
model=model,
|
||||
args=training_args,
|
||||
train_dataset=train_dataset if training_args.do_train else None,
|
||||
eval_dataset=eval_dataset if training_args.do_eval else None,
|
||||
tokenizer=tokenizer,
|
||||
# Data collator will default to DataCollatorWithPadding, so we change it.
|
||||
data_collator=default_data_collator,
|
||||
)
|
||||
|
||||
# Training
|
||||
if training_args.do_train:
|
||||
checkpoint = None
|
||||
if training_args.resume_from_checkpoint is not None:
|
||||
checkpoint = training_args.resume_from_checkpoint
|
||||
elif last_checkpoint is not None:
|
||||
checkpoint = last_checkpoint
|
||||
train_result = trainer.train(resume_from_checkpoint=checkpoint)
|
||||
trainer.save_model() # Saves the tokenizer too for easy upload
|
||||
|
||||
metrics = train_result.metrics
|
||||
|
||||
max_train_samples = (
|
||||
data_args.max_train_samples if data_args.max_train_samples is not None else len(train_dataset)
|
||||
)
|
||||
metrics["train_samples"] = min(max_train_samples, len(train_dataset))
|
||||
|
||||
trainer.log_metrics("train", metrics)
|
||||
trainer.save_metrics("train", metrics)
|
||||
trainer.save_state()
|
||||
|
||||
# Evaluation
|
||||
if training_args.do_eval:
|
||||
logger.info("*** Evaluate ***")
|
||||
|
||||
metrics = trainer.evaluate()
|
||||
|
||||
max_eval_samples = data_args.max_eval_samples if data_args.max_eval_samples is not None else len(eval_dataset)
|
||||
metrics["eval_samples"] = min(max_eval_samples, len(eval_dataset))
|
||||
try:
|
||||
perplexity = math.exp(metrics["eval_loss"])
|
||||
except OverflowError:
|
||||
perplexity = float("inf")
|
||||
metrics["perplexity"] = perplexity
|
||||
|
||||
trainer.log_metrics("eval", metrics)
|
||||
trainer.save_metrics("eval", metrics)
|
||||
|
||||
kwargs = {"finetuned_from": model_args.model_name_or_path, "tasks": "text-generation"}
|
||||
if data_args.dataset_name is not None:
|
||||
kwargs["dataset_tags"] = data_args.dataset_name
|
||||
if data_args.dataset_config_name is not None:
|
||||
kwargs["dataset_args"] = data_args.dataset_config_name
|
||||
kwargs["dataset"] = f"{data_args.dataset_name} {data_args.dataset_config_name}"
|
||||
else:
|
||||
kwargs["dataset"] = data_args.dataset_name
|
||||
|
||||
if training_args.push_to_hub:
|
||||
trainer.push_to_hub(**kwargs)
|
||||
else:
|
||||
trainer.create_model_card(**kwargs)
|
||||
|
||||
|
||||
def _mp_fn(index):
|
||||
# For xla_spawn (TPUs)
|
||||
main()
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
|
||||
Reference in New Issue
Block a user