diff --git a/examples/README.md b/examples/README.md index 922d5b094c6..c578a865b3b 100644 --- a/examples/README.md +++ b/examples/README.md @@ -27,7 +27,7 @@ This is still a work-in-progress – in particular documentation is still sparse | [**`summarization`**](https://github.com/huggingface/transformers/tree/master/examples/summarization) | CNN/Daily Mail | - | - | - | - | [**`translation`**](https://github.com/huggingface/transformers/tree/master/examples/translation) | WMT | - | - | - | - | [**`bertology`**](https://github.com/huggingface/transformers/tree/master/examples/bertology) | - | - | - | - | - -| [**`adversarial`**](https://github.com/huggingface/transformers/tree/master/examples/adversarial) | HANS | - | - | - | - +| [**`adversarial`**](https://github.com/huggingface/transformers/tree/master/examples/adversarial) | HANS | ✅ | - | - | -
diff --git a/examples/adversarial/run_hans.py b/examples/adversarial/run_hans.py new file mode 100644 index 00000000000..00837c12b79 --- /dev/null +++ b/examples/adversarial/run_hans.py @@ -0,0 +1,231 @@ +# coding=utf-8 +# Copyright 2018 The Google AI Language Team Authors and The HuggingFace Inc. team. +# Copyright (c) 2018, NVIDIA CORPORATION. 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. +""" Finetuning the library models for sequence classification on HANS.""" + +import logging +import os +from dataclasses import dataclass, field +from typing import Dict, List, Optional + +import numpy as np +import torch + +from transformers import ( + AutoConfig, + AutoModelForSequenceClassification, + AutoTokenizer, + HfArgumentParser, + Trainer, + TrainingArguments, + default_data_collator, + set_seed, +) +from utils_hans import HansDataset, InputFeatures, hans_processors + + +logger = logging.getLogger(__name__) + + +@dataclass +class ModelArguments: + """ + Arguments pertaining to which model/config/tokenizer we are going to fine-tune from. + """ + + model_name_or_path: str = field( + metadata={"help": "Path to pretrained model or model identifier from huggingface.co/models"} + ) + 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 s3"} + ) + + +@dataclass +class DataTrainingArguments: + """ + Arguments pertaining to what data we are going to input our model for training and eval. + """ + + task_name: str = field( + metadata={"help": "The name of the task to train selected in the list: " + ", ".join(hans_processors.keys())} + ) + data_dir: str = field( + metadata={"help": "The input data dir. Should contain the .tsv files (or other data files) for the task."} + ) + max_seq_length: int = field( + default=128, + metadata={ + "help": "The maximum total input sequence length after tokenization. Sequences longer " + "than this will be truncated, sequences shorter will be padded." + }, + ) + overwrite_cache: bool = field( + default=False, metadata={"help": "Overwrite the cached training and evaluation sets"} + ) + + +def hans_data_collator(features: List[InputFeatures]) -> Dict[str, torch.Tensor]: + """ + Data collator that removes the "pairID" key if present. + """ + batch = default_data_collator(features) + _ = batch.pop("pairID", None) + return batch + + +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 ( + 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, + ) + logger.info("Training/evaluation parameters %s", training_args) + + # Set seed + set_seed(training_args.seed) + + try: + processor = hans_processors[data_args.task_name]() + label_list = processor.get_labels() + num_labels = len(label_list) + except KeyError: + raise ValueError("Task not found: %s" % (data_args.task_name)) + + # Load pretrained model and tokenizer + # + # Distributed training: + # The .from_pretrained methods guarantee that only one local process can concurrently + # download model & vocab. + + config = AutoConfig.from_pretrained( + model_args.config_name if model_args.config_name else model_args.model_name_or_path, + num_labels=num_labels, + finetuning_task=data_args.task_name, + cache_dir=model_args.cache_dir, + ) + tokenizer = AutoTokenizer.from_pretrained( + model_args.tokenizer_name if model_args.tokenizer_name else model_args.model_name_or_path, + cache_dir=model_args.cache_dir, + ) + model = AutoModelForSequenceClassification.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, + ) + + # Get datasets + train_dataset = ( + HansDataset( + data_dir=data_args.data_dir, + tokenizer=tokenizer, + task=data_args.task_name, + max_seq_length=data_args.max_seq_length, + overwrite_cache=data_args.overwrite_cache, + ) + if training_args.do_train + else None + ) + eval_dataset = ( + HansDataset( + data_dir=data_args.data_dir, + tokenizer=tokenizer, + task=data_args.task_name, + max_seq_length=data_args.max_seq_length, + overwrite_cache=data_args.overwrite_cache, + evaluate=True, + ) + if training_args.do_eval + else None + ) + + # Initialize our Trainer + trainer = Trainer( + model=model, + args=training_args, + train_dataset=train_dataset, + eval_dataset=eval_dataset, + data_collator=hans_data_collator, + ) + + # Training + if training_args.do_train: + trainer.train( + model_path=model_args.model_name_or_path if os.path.isdir(model_args.model_name_or_path) else None + ) + 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 + if training_args.do_eval: + logger.info("*** Evaluate ***") + + output = trainer.predict(eval_dataset) + preds = output.predictions + preds = np.argmax(preds, axis=1) + + pair_ids = [ex.pairID for ex in eval_dataset] + output_eval_file = os.path.join(training_args.output_dir, "hans_predictions.txt") + if trainer.is_world_master(): + with open(output_eval_file, "w") as writer: + for pid, pred in zip(pair_ids, preds): + writer.write("ex" + str(pid) + "," + label_list[int(pred)] + "\n") + + trainer._log(output.metrics) + + +def _mp_fn(index): + # For xla_spawn (TPUs) + main() + + +if __name__ == "__main__": + main() diff --git a/examples/adversarial/test_hans.py b/examples/adversarial/test_hans.py deleted file mode 100644 index 91298811b8a..00000000000 --- a/examples/adversarial/test_hans.py +++ /dev/null @@ -1,577 +0,0 @@ -# coding=utf-8 -# Copyright 2018 The Google AI Language Team Authors and The HuggingFace Inc. team. -# Copyright (c) 2018, NVIDIA CORPORATION. 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. -""" Finetuning the library models for sequence classification on GLUE (Bert, XLM, XLNet, RoBERTa).""" - -from __future__ import absolute_import, division, print_function - -import argparse -import glob -import logging -import os -import random - -import numpy as np -import torch -from torch.utils.data import DataLoader, RandomSampler, SequentialSampler -from torch.utils.data.distributed import DistributedSampler -from tqdm import tqdm, trange - -from transformers import ( - WEIGHTS_NAME, - AdamW, - AlbertConfig, - AlbertForSequenceClassification, - AlbertTokenizer, - BertConfig, - BertForSequenceClassification, - BertTokenizer, - DistilBertConfig, - DistilBertForSequenceClassification, - DistilBertTokenizer, - RobertaConfig, - RobertaForSequenceClassification, - RobertaTokenizer, - XLMConfig, - XLMForSequenceClassification, - XLMTokenizer, - XLNetConfig, - XLNetForSequenceClassification, - XLNetTokenizer, - default_data_collator, - get_linear_schedule_with_warmup, -) -from utils_hans import HansDataset, hans_output_modes, hans_processors - - -try: - from torch.utils.tensorboard import SummaryWriter -except ImportError: - from tensorboardX import SummaryWriter - - -logger = logging.getLogger(__name__) - - -MODEL_CLASSES = { - "bert": (BertConfig, BertForSequenceClassification, BertTokenizer), - "xlnet": (XLNetConfig, XLNetForSequenceClassification, XLNetTokenizer), - "xlm": (XLMConfig, XLMForSequenceClassification, XLMTokenizer), - "roberta": (RobertaConfig, RobertaForSequenceClassification, RobertaTokenizer), - "distilbert": (DistilBertConfig, DistilBertForSequenceClassification, DistilBertTokenizer), - "albert": (AlbertConfig, AlbertForSequenceClassification, AlbertTokenizer), -} - - -def set_seed(args): - random.seed(args.seed) - np.random.seed(args.seed) - torch.manual_seed(args.seed) - if args.n_gpu > 0: - torch.cuda.manual_seed_all(args.seed) - - -def train(args, train_dataset, model, tokenizer): - """ Train the model """ - if args.local_rank in [-1, 0]: - tb_writer = SummaryWriter() - - args.train_batch_size = args.per_gpu_train_batch_size * max(1, args.n_gpu) - train_sampler = RandomSampler(train_dataset) if args.local_rank == -1 else DistributedSampler(train_dataset) - train_dataloader = DataLoader( - train_dataset, sampler=train_sampler, batch_size=args.train_batch_size, collate_fn=default_data_collator, - ) - - if args.max_steps > 0: - t_total = args.max_steps - args.num_train_epochs = args.max_steps // (len(train_dataloader) // args.gradient_accumulation_steps) + 1 - else: - t_total = len(train_dataloader) // args.gradient_accumulation_steps * args.num_train_epochs - - # Prepare optimizer and schedule (linear warmup and decay) - 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 = AdamW(optimizer_grouped_parameters, lr=args.learning_rate, eps=args.adam_epsilon) - scheduler = get_linear_schedule_with_warmup( - optimizer, num_warmup_steps=args.warmup_steps, num_training_steps=t_total - ) - if args.fp16: - try: - from apex import amp - except ImportError: - raise ImportError("Please install apex from https://www.github.com/nvidia/apex to use fp16 training.") - model, optimizer = amp.initialize(model, optimizer, opt_level=args.fp16_opt_level) - - # multi-gpu training (should be after apex fp16 initialization) - if args.n_gpu > 1: - model = torch.nn.DataParallel(model) - - # Distributed training (should be after apex fp16 initialization) - if args.local_rank != -1: - model = torch.nn.parallel.DistributedDataParallel( - model, device_ids=[args.local_rank], output_device=args.local_rank, find_unused_parameters=True - ) - - # Train! - logger.info("***** Running training *****") - logger.info(" Num examples = %d", len(train_dataset)) - logger.info(" Num Epochs = %d", args.num_train_epochs) - logger.info(" Instantaneous batch size per GPU = %d", args.per_gpu_train_batch_size) - logger.info( - " Total train batch size (w. parallel, distributed & accumulation) = %d", - args.train_batch_size - * args.gradient_accumulation_steps - * (torch.distributed.get_world_size() if args.local_rank != -1 else 1), - ) - logger.info(" Gradient Accumulation steps = %d", args.gradient_accumulation_steps) - logger.info(" Total optimization steps = %d", t_total) - - global_step = 0 - tr_loss, logging_loss = 0.0, 0.0 - model.zero_grad() - train_iterator = trange(int(args.num_train_epochs), desc="Epoch", disable=args.local_rank not in [-1, 0]) - set_seed(args) # Added here for reproductibility (even between python 2 and 3) - for _ in train_iterator: - epoch_iterator = tqdm(train_dataloader, desc="Iteration", disable=args.local_rank not in [-1, 0]) - for step, batch in enumerate(epoch_iterator): - model.train() - inputs = {k: t.to(args.device) for k, t in batch.items() if k != "pairID"} - outputs = model(**inputs) - loss = outputs[0] # model outputs are always tuple in transformers (see doc) - - if args.n_gpu > 1: - loss = loss.mean() # mean() to average on multi-gpu parallel training - if args.gradient_accumulation_steps > 1: - loss = loss / args.gradient_accumulation_steps - - if args.fp16: - with amp.scale_loss(loss, optimizer) as scaled_loss: - scaled_loss.backward() - else: - loss.backward() - - tr_loss += loss.item() - if (step + 1) % args.gradient_accumulation_steps == 0: - if args.fp16: - torch.nn.utils.clip_grad_norm_(amp.master_params(optimizer), args.max_grad_norm) - else: - torch.nn.utils.clip_grad_norm_(model.parameters(), args.max_grad_norm) - - optimizer.step() - scheduler.step() # Update learning rate schedule - model.zero_grad() - global_step += 1 - - if args.local_rank in [-1, 0] and args.logging_steps > 0 and global_step % args.logging_steps == 0: - logs = {} - if ( - args.local_rank == -1 and args.evaluate_during_training - ): # Only evaluate when single GPU otherwise metrics may not average well - results = evaluate(args, model, tokenizer) - for key, value in results.items(): - eval_key = "eval_{}".format(key) - logs[eval_key] = value - - loss_scalar = (tr_loss - logging_loss) / args.logging_steps - learning_rate_scalar = scheduler.get_lr()[0] - logs["learning_rate"] = learning_rate_scalar - logs["loss"] = loss_scalar - logging_loss = tr_loss - - for key, value in logs.items(): - tb_writer.add_scalar(key, value, global_step) - # print(json.dumps({**logs, **{'step': global_step}})) - - if args.local_rank in [-1, 0] and args.save_steps > 0 and global_step % args.save_steps == 0: - # Save model checkpoint - output_dir = os.path.join(args.output_dir, "checkpoint-{}".format(global_step)) - if not os.path.exists(output_dir): - os.makedirs(output_dir) - model_to_save = ( - model.module if hasattr(model, "module") else model - ) # Take care of distributed/parallel training - model_to_save.save_pretrained(output_dir) - torch.save(args, os.path.join(output_dir, "training_args.bin")) - logger.info("Saving model checkpoint to %s", output_dir) - - if args.max_steps > 0 and global_step > args.max_steps: - epoch_iterator.close() - break - if args.max_steps > 0 and global_step > args.max_steps: - train_iterator.close() - break - - if args.local_rank in [-1, 0]: - tb_writer.close() - - return global_step, tr_loss / global_step - - -def evaluate(args, model, tokenizer, label_list, prefix=""): - # Loop to handle MNLI double evaluation (matched, mis-matched) - eval_task_names = ("mnli", "mnli-mm") if args.task_name == "mnli" else (args.task_name,) - eval_outputs_dirs = (args.output_dir, args.output_dir + "-MM") if args.task_name == "mnli" else (args.output_dir,) - - results = {} - for eval_task, eval_output_dir in zip(eval_task_names, eval_outputs_dirs): - eval_dataset = HansDataset( - args.data_dir, - tokenizer, - args.task_name, - args.max_seq_length, - overwrite_cache=args.overwrite_cache, - evaluate=True, - ) - - if not os.path.exists(eval_output_dir) and args.local_rank in [-1, 0]: - os.makedirs(eval_output_dir) - - args.eval_batch_size = args.per_gpu_eval_batch_size * max(1, args.n_gpu) - # Note that DistributedSampler samples randomly - eval_sampler = SequentialSampler(eval_dataset) - eval_dataloader = DataLoader( - eval_dataset, sampler=eval_sampler, batch_size=args.eval_batch_size, collate_fn=default_data_collator, - ) - - # multi-gpu eval - if args.n_gpu > 1 and not isinstance(model, torch.nn.DataParallel): - model = torch.nn.DataParallel(model) - - # Eval! - logger.info("***** Running evaluation {} *****".format(prefix)) - logger.info(" Num examples = %d", len(eval_dataset)) - logger.info(" Batch size = %d", args.eval_batch_size) - eval_loss = 0.0 - nb_eval_steps = 0 - preds = None - out_label_ids = None - for batch in tqdm(eval_dataloader, desc="Evaluating"): - model.eval() - inputs = {k: t.to(args.device) for k, t in batch.items() if k != "pairID"} - pair_ids = batch.pop("pairID", None) - with torch.no_grad(): - outputs = model(**inputs) - tmp_eval_loss, logits = outputs[:2] - - eval_loss += tmp_eval_loss.mean().item() - nb_eval_steps += 1 - if preds is None: - preds = logits.detach().cpu().numpy() - out_label_ids = inputs["labels"].detach().cpu().numpy() - pair_ids = pair_ids.detach().cpu().numpy() - else: - preds = np.append(preds, logits.detach().cpu().numpy(), axis=0) - out_label_ids = np.append(out_label_ids, inputs["labels"].detach().cpu().numpy(), axis=0) - pair_ids = np.append(pair_ids, pair_ids.detach().cpu().numpy(), axis=0) - - eval_loss = eval_loss / nb_eval_steps - if args.output_mode == "classification": - preds = np.argmax(preds, axis=1) - elif args.output_mode == "regression": - preds = np.squeeze(preds) - - output_eval_file = os.path.join(eval_output_dir, "hans_predictions.txt") - with open(output_eval_file, "w") as writer: - writer.write("pairID,gld_label\n") - for pid, pred in zip(pair_ids, preds): - writer.write("ex" + str(pid) + "," + label_list[int(pred)] + "\n") - - return results - - -def main(): - parser = argparse.ArgumentParser() - - # Required parameters - parser.add_argument( - "--data_dir", - default=None, - type=str, - required=True, - help="The input data dir. Should contain the .tsv files (or other data files) for the task.", - ) - parser.add_argument( - "--model_type", - default=None, - type=str, - required=True, - help="Model type selected in the list: " + ", ".join(MODEL_CLASSES.keys()), - ) - parser.add_argument( - "--model_name_or_path", - default=None, - type=str, - required=True, - help="Path to pretrained model or model identifier from huggingface.co/models", - ) - parser.add_argument( - "--task_name", - default=None, - type=str, - required=True, - help="The name of the task to train selected in the list: " + ", ".join(hans_processors.keys()), - ) - parser.add_argument( - "--output_dir", - default=None, - type=str, - required=True, - help="The output directory where the model predictions and checkpoints will be written.", - ) - - # Other parameters - parser.add_argument( - "--config_name", default="", type=str, help="Pretrained config name or path if not the same as model_name" - ) - parser.add_argument( - "--tokenizer_name", - default="", - type=str, - help="Pretrained tokenizer name or path if not the same as model_name", - ) - parser.add_argument( - "--cache_dir", - default="", - type=str, - help="Where do you want to store the pre-trained models downloaded from s3", - ) - parser.add_argument( - "--max_seq_length", - default=128, - type=int, - help="The maximum total input sequence length after tokenization. Sequences longer " - "than this will be truncated, sequences shorter will be padded.", - ) - parser.add_argument("--do_train", action="store_true", help="Whether to run training.") - parser.add_argument("--do_eval", action="store_true", help="Whether to run eval on the dev set.") - parser.add_argument( - "--evaluate_during_training", action="store_true", help="Rul evaluation during training at each logging step." - ) - parser.add_argument( - "--do_lower_case", action="store_true", help="Set this flag if you are using an uncased model." - ) - - parser.add_argument("--per_gpu_train_batch_size", default=8, type=int, help="Batch size per GPU/CPU for training.") - parser.add_argument( - "--per_gpu_eval_batch_size", default=8, type=int, help="Batch size per GPU/CPU for evaluation." - ) - 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("--learning_rate", default=5e-5, type=float, help="The initial learning rate for Adam.") - parser.add_argument("--weight_decay", default=0.0, type=float, help="Weight decay if we apply some.") - parser.add_argument("--adam_epsilon", default=1e-8, type=float, help="Epsilon for Adam optimizer.") - parser.add_argument("--max_grad_norm", default=1.0, type=float, help="Max gradient norm.") - parser.add_argument( - "--num_train_epochs", default=3.0, type=float, help="Total number of training epochs to perform." - ) - parser.add_argument( - "--max_steps", - default=-1, - type=int, - help="If > 0: set total number of training steps to perform. Override num_train_epochs.", - ) - parser.add_argument("--warmup_steps", default=0, type=int, help="Linear warmup over warmup_steps.") - - parser.add_argument("--logging_steps", type=int, default=50, help="Log every X updates steps.") - parser.add_argument("--save_steps", type=int, default=50, help="Save checkpoint every X updates steps.") - parser.add_argument( - "--eval_all_checkpoints", - action="store_true", - help="Evaluate all checkpoints starting with the same prefix as model_name ending and ending with step number", - ) - parser.add_argument("--no_cuda", action="store_true", help="Avoid using CUDA when available") - parser.add_argument( - "--overwrite_output_dir", action="store_true", help="Overwrite the content of the output directory" - ) - parser.add_argument( - "--overwrite_cache", action="store_true", help="Overwrite the cached training and evaluation sets" - ) - parser.add_argument("--seed", type=int, default=42, help="random seed for initialization") - - parser.add_argument( - "--fp16", - action="store_true", - help="Whether to use 16-bit (mixed) precision (through NVIDIA apex) instead of 32-bit", - ) - parser.add_argument( - "--fp16_opt_level", - type=str, - default="O1", - help="For fp16: Apex AMP optimization level selected in ['O0', 'O1', 'O2', and 'O3']." - "See details at https://nvidia.github.io/apex/amp.html", - ) - parser.add_argument("--local_rank", type=int, default=-1, help="For distributed training: local_rank") - parser.add_argument("--server_ip", type=str, default="", help="For distant debugging.") - parser.add_argument("--server_port", type=str, default="", help="For distant debugging.") - args = parser.parse_args() - - if ( - os.path.exists(args.output_dir) - and os.listdir(args.output_dir) - and args.do_train - and not args.overwrite_output_dir - ): - raise ValueError( - "Output directory ({}) already exists and is not empty. Use --overwrite_output_dir to overcome.".format( - args.output_dir - ) - ) - - # Setup distant debugging if needed - if args.server_ip and args.server_port: - # Distant debugging - see https://code.visualstudio.com/docs/python/debugging#_attach-to-a-local-script - import ptvsd - - print("Waiting for debugger attach") - ptvsd.enable_attach(address=(args.server_ip, args.server_port), redirect_output=True) - ptvsd.wait_for_attach() - - # Setup CUDA, GPU & distributed training - if args.local_rank == -1 or args.no_cuda: - device = torch.device("cuda" if torch.cuda.is_available() and not args.no_cuda else "cpu") - args.n_gpu = 0 if args.no_cuda else torch.cuda.device_count() - else: # Initializes the distributed backend which will take care of sychronizing nodes/GPUs - torch.cuda.set_device(args.local_rank) - device = torch.device("cuda", args.local_rank) - torch.distributed.init_process_group(backend="nccl") - args.n_gpu = 1 - args.device = device - - # Setup logging - logging.basicConfig( - format="%(asctime)s - %(levelname)s - %(name)s - %(message)s", - datefmt="%m/%d/%Y %H:%M:%S", - level=logging.INFO if 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", - args.local_rank, - device, - args.n_gpu, - bool(args.local_rank != -1), - args.fp16, - ) - - # Set seed - set_seed(args) - - # Prepare GLUE task - args.task_name = args.task_name.lower() - if args.task_name not in hans_processors: - raise ValueError("Task not found: %s" % (args.task_name)) - processor = hans_processors[args.task_name]() - args.output_mode = hans_output_modes[args.task_name] - label_list = processor.get_labels() - num_labels = len(label_list) - - # Load pretrained model and tokenizer - if args.local_rank not in [-1, 0]: - torch.distributed.barrier() # Make sure only the first process in distributed training will download model & vocab - - args.model_type = args.model_type.lower() - config_class, model_class, tokenizer_class = MODEL_CLASSES[args.model_type] - config = config_class.from_pretrained( - args.config_name if args.config_name else args.model_name_or_path, - num_labels=num_labels, - finetuning_task=args.task_name, - cache_dir=args.cache_dir if args.cache_dir else None, - ) - tokenizer = tokenizer_class.from_pretrained( - args.tokenizer_name if args.tokenizer_name else args.model_name_or_path, - do_lower_case=args.do_lower_case, - cache_dir=args.cache_dir if args.cache_dir else None, - ) - model = model_class.from_pretrained( - args.model_name_or_path, - from_tf=bool(".ckpt" in args.model_name_or_path), - config=config, - cache_dir=args.cache_dir if args.cache_dir else None, - ) - - if args.local_rank == 0: - torch.distributed.barrier() # Make sure only the first process in distributed training will download model & vocab - - model.to(args.device) - - logger.info("Training/evaluation parameters %s", args) - - # Training - if args.do_train: - train_dataset = HansDataset( - args.data_dir, tokenizer, args.task_name, args.max_seq_length, overwrite_cache=args.overwrite_cache - ) - global_step, tr_loss = train(args, train_dataset, model, tokenizer) - logger.info(" global_step = %s, average loss = %s", global_step, tr_loss) - - # Saving best-practices: if you use defaults names for the model, you can reload it using from_pretrained() - if args.do_train and (args.local_rank == -1 or torch.distributed.get_rank() == 0): - # Create output directory if needed - if not os.path.exists(args.output_dir) and args.local_rank in [-1, 0]: - os.makedirs(args.output_dir) - - logger.info("Saving model checkpoint to %s", args.output_dir) - # Save a trained model, configuration and tokenizer using `save_pretrained()`. - # They can then be reloaded using `from_pretrained()` - model_to_save = ( - model.module if hasattr(model, "module") else model - ) # Take care of distributed/parallel training - model_to_save.save_pretrained(args.output_dir) - tokenizer.save_pretrained(args.output_dir) - - # Good practice: save your training arguments together with the trained model - torch.save(args, os.path.join(args.output_dir, "training_args.bin")) - - # Load a trained model and vocabulary that you have fine-tuned - model = model_class.from_pretrained(args.output_dir) - tokenizer = tokenizer_class.from_pretrained(args.output_dir) - model.to(args.device) - - # Evaluation - results = {} - if args.do_eval and args.local_rank in [-1, 0]: - tokenizer = tokenizer_class.from_pretrained(args.output_dir, do_lower_case=args.do_lower_case) - checkpoints = [args.output_dir] - if args.eval_all_checkpoints: - checkpoints = list( - os.path.dirname(c) for c in sorted(glob.glob(args.output_dir + "/**/" + WEIGHTS_NAME, recursive=True)) - ) - logging.getLogger("transformers.modeling_utils").setLevel(logging.WARN) # Reduce logging - logger.info("Evaluate the following checkpoints: %s", checkpoints) - for checkpoint in checkpoints: - global_step = checkpoint.split("-")[-1] if len(checkpoints) > 1 else "" - prefix = checkpoint.split("/")[-1] if checkpoint.find("checkpoint") != -1 else "" - - model = model_class.from_pretrained(checkpoint) - model.to(args.device) - result = evaluate(args, model, tokenizer, label_list, prefix=prefix) - result = dict((k + "_{}".format(global_step), v) for k, v in result.items()) - results.update(result) - - return results - - -if __name__ == "__main__": - main() diff --git a/examples/adversarial/utils_hans.py b/examples/adversarial/utils_hans.py index d99e1d8ecba..0dbc28149f4 100644 --- a/examples/adversarial/utils_hans.py +++ b/examples/adversarial/utils_hans.py @@ -22,15 +22,7 @@ from typing import List, Optional, Union import tqdm from filelock import FileLock -from transformers import ( - DataProcessor, - PreTrainedTokenizer, - RobertaTokenizer, - RobertaTokenizerFast, - XLMRobertaTokenizer, - is_tf_available, - is_torch_available, -) +from transformers import DataProcessor, PreTrainedTokenizer, is_tf_available, is_torch_available logger = logging.getLogger(__name__) @@ -106,7 +98,6 @@ if is_torch_available(): evaluate: bool = False, ): processor = hans_processors[task]() - output_mode = hans_output_modes[task] cached_features_file = os.path.join( data_dir, @@ -127,22 +118,12 @@ if is_torch_available(): logger.info(f"Creating features from dataset file at {data_dir}") label_list = processor.get_labels() - if task in ["mnli", "mnli-mm"] and tokenizer.__class__ in ( - RobertaTokenizer, - RobertaTokenizerFast, - XLMRobertaTokenizer, - ): - # HACK(label indices are swapped in RoBERTa pretrained model) - label_list[1], label_list[2] = label_list[2], label_list[1] examples = ( processor.get_dev_examples(data_dir) if evaluate else processor.get_train_examples(data_dir) ) logger.info("Training examples: %s", len(examples)) - # TODO clean up all this to leverage built-in features of tokenizers - self.features = hans_convert_examples_to_features( - examples, label_list, max_seq_length, tokenizer, output_mode - ) + self.features = hans_convert_examples_to_features(examples, label_list, max_seq_length, tokenizer) logger.info("Saving features into cached file %s", cached_features_file) torch.save(self.features, cached_features_file) @@ -174,21 +155,10 @@ if is_tf_available(): evaluate: bool = False, ): processor = hans_processors[task]() - output_mode = hans_output_modes[task] label_list = processor.get_labels() - if task in ["mnli", "mnli-mm"] and tokenizer.__class__ in ( - RobertaTokenizer, - RobertaTokenizerFast, - XLMRobertaTokenizer, - ): - # HACK(label indices are swapped in RoBERTa pretrained model) - label_list[1], label_list[2] = label_list[2], label_list[1] - examples = processor.get_dev_examples(data_dir) if evaluate else processor.get_train_examples(data_dir) - self.features = hans_convert_examples_to_features( - examples, label_list, max_seq_length, tokenizer, output_mode - ) + self.features = hans_convert_examples_to_features(examples, label_list, max_seq_length, tokenizer) def gen(): for (ex_index, ex) in tqdm.tqdm(enumerate(self.features), desc="convert examples to features"): @@ -240,15 +210,6 @@ if is_tf_available(): class HansProcessor(DataProcessor): """Processor for the HANS data set.""" - def get_example_from_tensor_dict(self, tensor_dict): - """See base class.""" - return InputExample( - tensor_dict["idx"].numpy(), - tensor_dict["premise"].numpy().decode("utf-8"), - tensor_dict["hypothesis"].numpy().decode("utf-8"), - str(tensor_dict["label"].numpy()), - ) - def get_train_examples(self, data_dir): """See base class.""" return self._create_examples(self._read_tsv(os.path.join(data_dir, "heuristics_train_set.txt")), "train") @@ -277,11 +238,7 @@ class HansProcessor(DataProcessor): def hans_convert_examples_to_features( - examples: List[InputExample], - label_list: List[str], - max_length: int, - tokenizer: PreTrainedTokenizer, - output_mode: str, + examples: List[InputExample], label_list: List[str], max_length: int, tokenizer: PreTrainedTokenizer, ): """ Loads a data file into a list of ``InputFeatures`` @@ -313,19 +270,8 @@ def hans_convert_examples_to_features( pad_to_max_length=True, return_overflowing_tokens=True, ) - if "num_truncated_tokens" in inputs and inputs["num_truncated_tokens"] > 0: - logger.info( - "Attention! you are cropping tokens (swag task is ok). " - "If you are training ARC and RACE and you are poping question + options," - "you need to try to use a bigger max seq length!" - ) - if output_mode == "classification": - label = label_map[example.label] if example.label in label_map else 0 - elif output_mode == "regression": - label = float(example.label) - else: - raise KeyError(output_mode) + label = label_map[example.label] if example.label in label_map else 0 pairID = int(example.pairID) @@ -346,7 +292,3 @@ hans_tasks_num_labels = { hans_processors = { "hans": HansProcessor, } - -hans_output_modes = { - "hans": "classification", -}