#!/usr/bin/env python # coding=utf-8 # Copyright The HuggingFace Team and 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 a 🤗 Transformers model on multiple choice relying on the accelerate library without using a Trainer. """ # You can also adapt this script on your own multiple choice task. Pointers for this are left as comments. import argparse import json import logging import math import os import random from dataclasses import dataclass from itertools import chain from pathlib import Path from typing import Optional, Union import datasets import evaluate import torch from accelerate import Accelerator from accelerate.logging import get_logger from accelerate.utils import set_seed from datasets import load_dataset from huggingface_hub import Repository, create_repo from torch.utils.data import DataLoader from tqdm.auto import tqdm import transformers from transformers import ( CONFIG_MAPPING, MODEL_MAPPING, AutoConfig, AutoModelForMultipleChoice, AutoTokenizer, PreTrainedTokenizerBase, SchedulerType, default_data_collator, get_scheduler, ) from transformers.utils import PaddingStrategy, check_min_version, send_example_telemetry # Will error if the minimal version of Transformers is not installed. Remove at your own risks. check_min_version("4.34.0.dev0") logger = get_logger(__name__) # You should update this to your particular problem to have better documentation of `model_type` MODEL_CONFIG_CLASSES = list(MODEL_MAPPING.keys()) MODEL_TYPES = tuple(conf.model_type for conf in MODEL_CONFIG_CLASSES) def parse_args(): parser = argparse.ArgumentParser(description="Finetune a transformers model on a multiple choice task") parser.add_argument( "--dataset_name", type=str, default=None, help="The name of the dataset to use (via the datasets library).", ) parser.add_argument( "--dataset_config_name", type=str, default=None, help="The configuration name of the dataset to use (via the datasets library).", ) parser.add_argument( "--train_file", type=str, default=None, help="A csv or a json file containing the training data." ) parser.add_argument( "--validation_file", type=str, default=None, help="A csv or a json file containing the validation data." ) parser.add_argument( "--max_seq_length", type=int, default=128, help=( "The maximum total input sequence length after tokenization. Sequences longer than this will be truncated," " sequences shorter will be padded if `--pad_to_max_lengh` is passed." ), ) parser.add_argument( "--pad_to_max_length", action="store_true", help="If passed, pad all samples to `max_length`. Otherwise, dynamic padding is used.", ) parser.add_argument( "--model_name_or_path", type=str, help="Path to pretrained model or model identifier from huggingface.co/models.", required=False, ) parser.add_argument( "--config_name", type=str, default=None, help="Pretrained config name or path if not the same as model_name", ) parser.add_argument( "--tokenizer_name", type=str, default=None, help="Pretrained tokenizer name or path if not the same as model_name", ) parser.add_argument( "--use_slow_tokenizer", action="store_true", help="If passed, will use a slow tokenizer (not backed by the 🤗 Tokenizers library).", ) parser.add_argument( "--per_device_train_batch_size", type=int, default=8, help="Batch size (per device) for the training dataloader.", ) parser.add_argument( "--per_device_eval_batch_size", type=int, default=8, help="Batch size (per device) for the evaluation dataloader.", ) parser.add_argument( "--learning_rate", type=float, default=5e-5, help="Initial learning rate (after the potential warmup period) to use.", ) parser.add_argument("--weight_decay", type=float, default=0.0, help="Weight decay to use.") parser.add_argument("--num_train_epochs", type=int, default=3, help="Total number of training epochs to perform.") parser.add_argument( "--max_train_steps", type=int, default=None, help="Total number of training steps to perform. If provided, overrides num_train_epochs.", ) parser.add_argument( "--gradient_accumulation_steps", type=int, default=1, help="Number of updates steps to accumulate before performing a backward/update pass.", ) parser.add_argument( "--lr_scheduler_type", type=SchedulerType, default="linear", help="The scheduler type to use.", choices=["linear", "cosine", "cosine_with_restarts", "polynomial", "constant", "constant_with_warmup"], ) parser.add_argument( "--num_warmup_steps", type=int, default=0, help="Number of steps for the warmup in the lr scheduler." ) parser.add_argument("--output_dir", type=str, default=None, help="Where to store the final model.") parser.add_argument("--seed", type=int, default=None, help="A seed for reproducible training.") parser.add_argument( "--model_type", type=str, default=None, help="Model type to use if training from scratch.", choices=MODEL_TYPES, ) parser.add_argument( "--debug", action="store_true", help="Activate debug mode and run training only with a subset of data.", ) parser.add_argument("--push_to_hub", action="store_true", help="Whether or not to push the model to the Hub.") parser.add_argument( "--hub_model_id", type=str, help="The name of the repository to keep in sync with the local `output_dir`." ) parser.add_argument("--hub_token", type=str, help="The token to use to push to the Model Hub.") parser.add_argument( "--trust_remote_code", type=bool, default=False, help=( "Whether or not to allow for custom models defined on the Hub in their own modeling files. This option" "should only be set to `True` for repositories you trust and in which you have read the code, as it will" "execute code present on the Hub on your local machine." ), ) parser.add_argument( "--checkpointing_steps", type=str, default=None, help="Whether the various states should be saved at the end of every n steps, or 'epoch' for each epoch.", ) parser.add_argument( "--resume_from_checkpoint", type=str, default=None, help="If the training should continue from a checkpoint folder.", ) parser.add_argument( "--with_tracking", action="store_true", help="Whether to enable experiment trackers for logging.", ) parser.add_argument( "--report_to", type=str, default="all", help=( 'The integration to report the results and logs to. Supported platforms are `"tensorboard"`,' ' `"wandb"`, `"comet_ml"` and `"clearml"`. Use `"all"` (default) to report to all integrations.' "Only applicable when `--with_tracking` is passed." ), ) args = parser.parse_args() if args.push_to_hub: assert args.output_dir is not None, "Need an `output_dir` to create a repo when `--push_to_hub` is passed." return args @dataclass class DataCollatorForMultipleChoice: """ Data collator that will dynamically pad the inputs for multiple choice received. Args: tokenizer ([`PreTrainedTokenizer`] or [`PreTrainedTokenizerFast`]): The tokenizer used for encoding the data. padding (`bool`, `str` or [`~utils.PaddingStrategy`], *optional*, defaults to `True`): Select a strategy to pad the returned sequences (according to the model's padding side and padding index) among: - `True` or `'longest'`: Pad to the longest sequence in the batch (or no padding if only a single sequence if provided). - `'max_length'`: Pad to a maximum length specified with the argument `max_length` or to the maximum acceptable input length for the model if that argument is not provided. - `False` or `'do_not_pad'` (default): No padding (i.e., can output a batch with sequences of different lengths). max_length (`int`, *optional*): Maximum length of the returned list and optionally padding length (see above). pad_to_multiple_of (`int`, *optional*): If set will pad the sequence to a multiple of the provided value. This is especially useful to enable the use of Tensor Cores on NVIDIA hardware with compute capability >= 7.5 (Volta). """ tokenizer: PreTrainedTokenizerBase padding: Union[bool, str, PaddingStrategy] = True max_length: Optional[int] = None pad_to_multiple_of: Optional[int] = None def __call__(self, features): label_name = "label" if "label" in features[0].keys() else "labels" labels = [feature.pop(label_name) for feature in features] batch_size = len(features) num_choices = len(features[0]["input_ids"]) flattened_features = [ [{k: v[i] for k, v in feature.items()} for i in range(num_choices)] for feature in features ] flattened_features = list(chain(*flattened_features)) batch = self.tokenizer.pad( flattened_features, padding=self.padding, max_length=self.max_length, pad_to_multiple_of=self.pad_to_multiple_of, return_tensors="pt", ) # Un-flatten batch = {k: v.view(batch_size, num_choices, -1) for k, v in batch.items()} # Add back labels batch["labels"] = torch.tensor(labels, dtype=torch.int64) return batch def main(): args = parse_args() # Sending telemetry. Tracking the example usage helps us better allocate resources to maintain them. The # information sent is the one passed as arguments along with your Python/PyTorch versions. send_example_telemetry("run_swag_no_trainer", args) # Initialize the accelerator. We will let the accelerator handle device placement for us in this example. # If we're using tracking, we also need to initialize it here and it will by default pick up all supported trackers # in the environment accelerator_log_kwargs = {} if args.with_tracking: accelerator_log_kwargs["log_with"] = args.report_to accelerator_log_kwargs["project_dir"] = args.output_dir accelerator = Accelerator(gradient_accumulation_steps=args.gradient_accumulation_steps, **accelerator_log_kwargs) # Make one log on every process with the configuration for debugging. logging.basicConfig( format="%(asctime)s - %(levelname)s - %(name)s - %(message)s", datefmt="%m/%d/%Y %H:%M:%S", level=logging.INFO, ) logger.info(accelerator.state, main_process_only=False) if accelerator.is_local_main_process: datasets.utils.logging.set_verbosity_warning() transformers.utils.logging.set_verbosity_info() else: datasets.utils.logging.set_verbosity_error() transformers.utils.logging.set_verbosity_error() # If passed along, set the training seed now. if args.seed is not None: set_seed(args.seed) # Handle the repository creation if accelerator.is_main_process: if args.push_to_hub: # Retrieve of infer repo_name repo_name = args.hub_model_id if repo_name is None: repo_name = Path(args.output_dir).absolute().name # Create repo and retrieve repo_id repo_id = create_repo(repo_name, exist_ok=True, token=args.hub_token).repo_id # Clone repo locally repo = Repository(args.output_dir, clone_from=repo_id, token=args.hub_token) with open(os.path.join(args.output_dir, ".gitignore"), "w+") as gitignore: if "step_*" not in gitignore: gitignore.write("step_*\n") if "epoch_*" not in gitignore: gitignore.write("epoch_*\n") elif args.output_dir is not None: os.makedirs(args.output_dir, exist_ok=True) accelerator.wait_for_everyone() # 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. if args.dataset_name is not None: # Downloading and loading a dataset from the hub. raw_datasets = load_dataset(args.dataset_name, args.dataset_config_name) else: data_files = {} if args.train_file is not None: data_files["train"] = args.train_file if args.validation_file is not None: data_files["validation"] = args.validation_file extension = args.train_file.split(".")[-1] raw_datasets = load_dataset(extension, data_files=data_files) # Trim a number of training examples if args.debug: for split in raw_datasets.keys(): raw_datasets[split] = raw_datasets[split].select(range(100)) # 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. if raw_datasets["train"] is not None: column_names = raw_datasets["train"].column_names else: column_names = raw_datasets["validation"].column_names # When using your own dataset or a different dataset from swag, you will probably need to change this. ending_names = [f"ending{i}" for i in range(4)] context_name = "sent1" question_header_name = "sent2" label_column_name = "label" if "label" in column_names else "labels" # Load pretrained model and tokenizer # # In distributed training, the .from_pretrained methods guarantee that only one local process can concurrently # download model & vocab. if args.config_name: config = AutoConfig.from_pretrained(args.model_name_or_path, trust_remote_code=args.trust_remote_code) elif args.model_name_or_path: config = AutoConfig.from_pretrained(args.model_name_or_path, trust_remote_code=args.trust_remote_code) else: config = CONFIG_MAPPING[args.model_type]() logger.warning("You are instantiating a new config instance from scratch.") if args.tokenizer_name: tokenizer = AutoTokenizer.from_pretrained( args.tokenizer_name, use_fast=not args.use_slow_tokenizer, trust_remote_code=args.trust_remote_code ) elif args.model_name_or_path: tokenizer = AutoTokenizer.from_pretrained( args.model_name_or_path, use_fast=not args.use_slow_tokenizer, trust_remote_code=args.trust_remote_code ) 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 args.model_name_or_path: model = AutoModelForMultipleChoice.from_pretrained( args.model_name_or_path, from_tf=bool(".ckpt" in args.model_name_or_path), config=config, trust_remote_code=args.trust_remote_code, ) else: logger.info("Training new model from scratch") model = AutoModelForMultipleChoice.from_config(config, trust_remote_code=args.trust_remote_code) # We resize the embeddings only when necessary to avoid index errors. If you are creating a model from scratch # on a small vocab and want a smaller embedding size, remove this test. embedding_size = model.get_input_embeddings().weight.shape[0] if len(tokenizer) > embedding_size: model.resize_token_embeddings(len(tokenizer)) # Preprocessing the datasets. # First we tokenize all the texts. padding = "max_length" if args.pad_to_max_length else False def preprocess_function(examples): first_sentences = [[context] * 4 for context in examples[context_name]] question_headers = examples[question_header_name] second_sentences = [ [f"{header} {examples[end][i]}" for end in ending_names] for i, header in enumerate(question_headers) ] labels = examples[label_column_name] # Flatten out first_sentences = list(chain(*first_sentences)) second_sentences = list(chain(*second_sentences)) # Tokenize tokenized_examples = tokenizer( first_sentences, second_sentences, max_length=args.max_seq_length, padding=padding, truncation=True, ) # Un-flatten tokenized_inputs = {k: [v[i : i + 4] for i in range(0, len(v), 4)] for k, v in tokenized_examples.items()} tokenized_inputs["labels"] = labels return tokenized_inputs with accelerator.main_process_first(): processed_datasets = raw_datasets.map( preprocess_function, batched=True, remove_columns=raw_datasets["train"].column_names ) train_dataset = processed_datasets["train"] eval_dataset = processed_datasets["validation"] # Log a few random samples from the training set: for index in random.sample(range(len(train_dataset)), 3): logger.info(f"Sample {index} of the training set: {train_dataset[index]}.") # DataLoaders creation: if args.pad_to_max_length: # If padding was already done ot max length, we use the default data collator that will just convert everything # to tensors. data_collator = default_data_collator else: # Otherwise, `DataCollatorWithPadding` will apply dynamic padding for us (by padding to the maximum length of # the samples passed). When using mixed precision, we add `pad_to_multiple_of=8` to pad all tensors to multiple # of 8s, which will enable the use of Tensor Cores on NVIDIA hardware with compute capability >= 7.5 (Volta). data_collator = DataCollatorForMultipleChoice( tokenizer, pad_to_multiple_of=(8 if accelerator.use_fp16 else None) ) train_dataloader = DataLoader( train_dataset, shuffle=True, collate_fn=data_collator, batch_size=args.per_device_train_batch_size ) eval_dataloader = DataLoader(eval_dataset, collate_fn=data_collator, batch_size=args.per_device_eval_batch_size) # Optimizer # Split weights in two groups, one with weight decay and the other not. no_decay = ["bias", "LayerNorm.weight"] optimizer_grouped_parameters = [ { "params": [p for n, p in model.named_parameters() if not any(nd in n for nd in no_decay)], "weight_decay": args.weight_decay, }, { "params": [p for n, p in model.named_parameters() if any(nd in n for nd in no_decay)], "weight_decay": 0.0, }, ] optimizer = torch.optim.AdamW(optimizer_grouped_parameters, lr=args.learning_rate) # Use the device given by the `accelerator` object. device = accelerator.device model.to(device) # Scheduler and math around the number of training steps. overrode_max_train_steps = False num_update_steps_per_epoch = math.ceil(len(train_dataloader) / args.gradient_accumulation_steps) if args.max_train_steps is None: args.max_train_steps = args.num_train_epochs * num_update_steps_per_epoch overrode_max_train_steps = True lr_scheduler = get_scheduler( name=args.lr_scheduler_type, optimizer=optimizer, num_warmup_steps=args.num_warmup_steps * args.gradient_accumulation_steps, num_training_steps=args.max_train_steps * args.gradient_accumulation_steps, ) # Prepare everything with our `accelerator`. model, optimizer, train_dataloader, eval_dataloader, lr_scheduler = accelerator.prepare( model, optimizer, train_dataloader, eval_dataloader, lr_scheduler ) # We need to recalculate our total training steps as the size of the training dataloader may have changed. num_update_steps_per_epoch = math.ceil(len(train_dataloader) / args.gradient_accumulation_steps) if overrode_max_train_steps: args.max_train_steps = args.num_train_epochs * num_update_steps_per_epoch # Afterwards we recalculate our number of training epochs args.num_train_epochs = math.ceil(args.max_train_steps / num_update_steps_per_epoch) # Figure out how many steps we should save the Accelerator states checkpointing_steps = args.checkpointing_steps if checkpointing_steps is not None and checkpointing_steps.isdigit(): checkpointing_steps = int(checkpointing_steps) # We need to initialize the trackers we use, and also store our configuration. # The trackers initializes automatically on the main process. if args.with_tracking: experiment_config = vars(args) # TensorBoard cannot log Enums, need the raw value experiment_config["lr_scheduler_type"] = experiment_config["lr_scheduler_type"].value accelerator.init_trackers("swag_no_trainer", experiment_config) # Metrics metric = evaluate.load("accuracy") # Train! total_batch_size = args.per_device_train_batch_size * accelerator.num_processes * args.gradient_accumulation_steps logger.info("***** Running training *****") logger.info(f" Num examples = {len(train_dataset)}") logger.info(f" Num Epochs = {args.num_train_epochs}") logger.info(f" Instantaneous batch size per device = {args.per_device_train_batch_size}") logger.info(f" Total train batch size (w. parallel, distributed & accumulation) = {total_batch_size}") logger.info(f" Gradient Accumulation steps = {args.gradient_accumulation_steps}") logger.info(f" Total optimization steps = {args.max_train_steps}") # Only show the progress bar once on each machine. progress_bar = tqdm(range(args.max_train_steps), disable=not accelerator.is_local_main_process) completed_steps = 0 starting_epoch = 0 # Potentially load in the weights and states from a previous save if args.resume_from_checkpoint: if args.resume_from_checkpoint is not None or args.resume_from_checkpoint != "": checkpoint_path = args.resume_from_checkpoint path = os.path.basename(args.resume_from_checkpoint) else: # Get the most recent checkpoint dirs = [f.name for f in os.scandir(os.getcwd()) if f.is_dir()] dirs.sort(key=os.path.getctime) path = dirs[-1] # Sorts folders by date modified, most recent checkpoint is the last checkpoint_path = path path = os.path.basename(checkpoint_path) accelerator.print(f"Resumed from checkpoint: {checkpoint_path}") accelerator.load_state(path) # Extract `epoch_{i}` or `step_{i}` training_difference = os.path.splitext(path)[0] if "epoch" in training_difference: starting_epoch = int(training_difference.replace("epoch_", "")) + 1 resume_step = None completed_steps = starting_epoch * num_update_steps_per_epoch else: # need to multiply `gradient_accumulation_steps` to reflect real steps resume_step = int(training_difference.replace("step_", "")) * args.gradient_accumulation_steps starting_epoch = resume_step // len(train_dataloader) completed_steps = resume_step // args.gradient_accumulation_steps resume_step -= starting_epoch * len(train_dataloader) # update the progress_bar if load from checkpoint progress_bar.update(completed_steps) for epoch in range(starting_epoch, args.num_train_epochs): model.train() if args.with_tracking: total_loss = 0 if args.resume_from_checkpoint and epoch == starting_epoch and resume_step is not None: # We skip the first `n` batches in the dataloader when resuming from a checkpoint active_dataloader = accelerator.skip_first_batches(train_dataloader, resume_step) else: active_dataloader = train_dataloader for step, batch in enumerate(active_dataloader): with accelerator.accumulate(model): outputs = model(**batch) loss = outputs.loss # We keep track of the loss at each epoch if args.with_tracking: total_loss += loss.detach().float() accelerator.backward(loss) optimizer.step() lr_scheduler.step() optimizer.zero_grad() # Checks if the accelerator has performed an optimization step behind the scenes if accelerator.sync_gradients: progress_bar.update(1) completed_steps += 1 if isinstance(checkpointing_steps, int): if completed_steps % checkpointing_steps == 0: output_dir = f"step_{completed_steps}" if args.output_dir is not None: output_dir = os.path.join(args.output_dir, output_dir) accelerator.save_state(output_dir) if completed_steps >= args.max_train_steps: break model.eval() for step, batch in enumerate(eval_dataloader): with torch.no_grad(): outputs = model(**batch) predictions = outputs.logits.argmax(dim=-1) predictions, references = accelerator.gather_for_metrics((predictions, batch["labels"])) metric.add_batch( predictions=predictions, references=references, ) eval_metric = metric.compute() accelerator.print(f"epoch {epoch}: {eval_metric}") if args.with_tracking: accelerator.log( { "accuracy": eval_metric, "train_loss": total_loss.item() / len(train_dataloader), "epoch": epoch, "step": completed_steps, }, step=completed_steps, ) if args.push_to_hub and epoch < args.num_train_epochs - 1: accelerator.wait_for_everyone() unwrapped_model = accelerator.unwrap_model(model) unwrapped_model.save_pretrained( args.output_dir, is_main_process=accelerator.is_main_process, save_function=accelerator.save ) if accelerator.is_main_process: tokenizer.save_pretrained(args.output_dir) repo.push_to_hub( commit_message=f"Training in progress epoch {epoch}", blocking=False, auto_lfs_prune=True ) if args.checkpointing_steps == "epoch": output_dir = f"epoch_{epoch}" if args.output_dir is not None: output_dir = os.path.join(args.output_dir, output_dir) accelerator.save_state(output_dir) if args.with_tracking: accelerator.end_training() if args.output_dir is not None: accelerator.wait_for_everyone() unwrapped_model = accelerator.unwrap_model(model) unwrapped_model.save_pretrained( args.output_dir, is_main_process=accelerator.is_main_process, save_function=accelerator.save ) if accelerator.is_main_process: tokenizer.save_pretrained(args.output_dir) if args.push_to_hub: repo.push_to_hub(commit_message="End of training", auto_lfs_prune=True) all_results = {f"eval_{k}": v for k, v in eval_metric.items()} with open(os.path.join(args.output_dir, "all_results.json"), "w") as f: json.dump(all_results, f) if __name__ == "__main__": main()