def config(self): if self._config is None: ps = self.params x = ps.config_name if ps.config_name else ps.model_name if x: y = self.AutoConfig.from_pretrained( x, cache_dir=ps.cache_dir, revision=ps.model_version, use_auth_token=True if ps.use_auth_token else None, ) else: y = XLNetConfig() log.warning("Creating new config") if ps.config_overrides is not None: log.info(f"Overriding config: {ps.config_overrides}") y.update_from_string(ps.config_overrides) log.info(f"New config: {y}") self._config = y return self._config
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. if data_args.dataset_name is not None: # Downloading and loading a dataset from the hub. raw_datasets = load_dataset(data_args.dataset_name, data_args.dataset_config_name, cache_dir=model_args.cache_dir) if "validation" not in raw_datasets.keys(): raw_datasets["validation"] = load_dataset( data_args.dataset_name, data_args.dataset_config_name, split=f"train[:{data_args.validation_split_percentage}%]", cache_dir=model_args.cache_dir, ) raw_datasets["train"] = load_dataset( data_args.dataset_name, data_args.dataset_config_name, split=f"train[{data_args.validation_split_percentage}%:]", cache_dir=model_args.cache_dir, ) else: data_files = {} if data_args.train_file is not None: data_files["train"] = data_args.train_file if data_args.validation_file is not None: data_files["validation"] = data_args.validation_file extension = data_args.train_file.split(".")[-1] if extension == "txt": extension = "text" raw_datasets = load_dataset(extension, data_files=data_files, cache_dir=model_args.cache_dir) # If no validation data is there, validation_split_percentage will be used to divide the dataset. if "validation" not in raw_datasets.keys(): raw_datasets["validation"] = load_dataset( extension, data_files=data_files, split=f"train[:{data_args.validation_split_percentage}%]", cache_dir=model_args.cache_dir, ) raw_datasets["train"] = load_dataset( extension, data_files=data_files, split=f"train[{data_args.validation_split_percentage}%:]", cache_dir=model_args.cache_dir, ) # 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 = XLNetConfig() 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 = XLNetLMHeadModel.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: logger.info("Training new model from scratch") model = XLNetLMHeadModel.from_config(config) model.resize_token_embeddings(len(tokenizer)) # Preprocessing the datasets. # First we tokenize all the texts. if training_args.do_train: column_names = raw_datasets["train"].column_names else: column_names = raw_datasets["validation"].column_names text_column_name = "text" if "text" in column_names else column_names[0] if data_args.max_seq_length > tokenizer.model_max_length: logger.warning( f"The max_seq_length passed ({data_args.max_seq_length}) is larger than the maximum length for the" f"model ({tokenizer.model_max_length}). Using max_seq_length={tokenizer.model_max_length}." ) max_seq_length = min(data_args.max_seq_length, tokenizer.model_max_length) if data_args.line_by_line: # When using line_by_line, we just tokenize each nonempty line. padding = "max_length" if data_args.pad_to_max_length else False def tokenize_function(examples): # Remove empty lines examples["text"] = [ line for line in examples["text"] if len(line) > 0 and not line.isspace() ] return tokenizer(examples["text"], padding=padding, truncation=True, max_length=max_seq_length) with training_args.main_process_first(desc="dataset map tokenization"): tokenized_datasets = raw_datasets.map( tokenize_function, batched=True, num_proc=data_args.preprocessing_num_workers, remove_columns=[text_column_name], load_from_cache_file=not data_args.overwrite_cache, desc="Running tokenizer on dataset line_by_line", ) else: # Otherwise, we tokenize every text, then concatenate them together before splitting them in smaller parts. def tokenize_function(examples): return tokenizer(examples[text_column_name]) with training_args.main_process_first(desc="dataset map tokenization"): tokenized_datasets = raw_datasets.map( tokenize_function, batched=True, num_proc=data_args.preprocessing_num_workers, remove_columns=column_names, load_from_cache_file=not data_args.overwrite_cache, desc="Running tokenizer on every text in dataset", ) # Main data processing function that will concatenate all texts from our dataset and generate chunks of # max_seq_length. def group_texts(examples): # Concatenate all texts. concatenated_examples = { k: sum(examples[k], []) for k in examples.keys() } total_length = len(concatenated_examples[list(examples.keys())[0]]) # We drop the small remainder, we could add padding if the model supported it instead of this drop, you can # customize this part to your needs. if total_length >= max_seq_length: total_length = (total_length // max_seq_length) * max_seq_length # Split by chunks of max_len. result = { k: [ t[i:i + max_seq_length] for i in range(0, total_length, max_seq_length) ] for k, t in concatenated_examples.items() } return result # Note that with `batched=True`, this map processes 1,000 texts together, so group_texts throws away a # remainder for each of those groups of 1,000 texts. You can adjust that batch_size here but a higher value # might be slower to preprocess. # # To speed up this part, we use multiprocessing. See the documentation of the map method for more information: # https://huggingface.co/docs/datasets/package_reference/main_classes.html#datasets.Dataset.map with training_args.main_process_first(desc="grouping texts together"): tokenized_datasets = tokenized_datasets.map( group_texts, batched=True, num_proc=data_args.preprocessing_num_workers, load_from_cache_file=not data_args.overwrite_cache, desc=f"Grouping texts in chunks of {max_seq_length}", ) if training_args.do_train: if "train" not in tokenized_datasets: raise ValueError("--do_train requires a train dataset") train_dataset = tokenized_datasets["train"] if data_args.max_train_samples is not None: train_dataset = train_dataset.select( range(data_args.max_train_samples)) if training_args.do_eval: if "validation" not in tokenized_datasets: raise ValueError("--do_eval requires a validation dataset") eval_dataset = tokenized_datasets["validation"] if data_args.max_eval_samples is not None: eval_dataset = eval_dataset.select( range(data_args.max_eval_samples)) # Data collator data_collator = DataCollatorForPermutationLanguageModeling( tokenizer=tokenizer, plm_probability=data_args.plm_probability, max_span_length=data_args.max_span_length, ) # 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=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) if training_args.push_to_hub: kwargs = { "finetuned_from": model_args.model_name_or_path, "tasks": "language-modeling" } 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 trainer.push_to_hub(**kwargs)