[examples] Generate argparsers from type hints on dataclasses (#3669)

* [examples] Generate argparsers from type hints on dataclasses

* [HfArgumentParser] way simpler API

* Restore run_language_modeling.py for easier diff

* [HfArgumentParser] final tweaks from code review

examples/run_glue.py

@@ -22,6 +22,8 @@ import json
 import logging
 import os
 import random
+from dataclasses import dataclass, field
+from typing import Optional
 
 import numpy as np
 import torch
@@ -36,6 +38,8 @@ from transformers import (
     AutoConfig,
     AutoModelForSequenceClassification,
     AutoTokenizer,
+    HfArgumentParser,
+    TrainingArguments,
     get_linear_schedule_with_warmup,
 )
 from transformers import glue_compute_metrics as compute_metrics
@@ -376,137 +380,54 @@ def load_and_cache_examples(args, task, tokenizer, evaluate=False):
     return dataset
 
 
-def main():
-    parser = argparse.ArgumentParser()
+@dataclass
+class ModelArguments:
+    """
+    Arguments pertaining to which model/config/tokenizer we are going to fine-tune from.
+    """
 
-    # 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.",
+    model_name_or_path: str = field(
+        metadata={"help": "Path to pre-trained model or shortcut name selected in the list: " + ", ".join(ALL_MODELS)}
     )
-    parser.add_argument(
-        "--model_type",
-        default=None,
-        type=str,
-        required=True,
-        help="Model type selected in the list: " + ", ".join(MODEL_TYPES),
+    model_type: str = field(metadata={"help": "Model type selected in 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"}
     )
-    parser.add_argument(
-        "--model_name_or_path",
-        default=None,
-        type=str,
-        required=True,
-        help="Path to pre-trained model or shortcut name selected in the list: " + ", ".join(ALL_MODELS),
+    tokenizer_name: Optional[str] = field(
+        default=None, metadata={"help": "Pretrained tokenizer name or path if not the same as model_name"}
     )
-    parser.add_argument(
-        "--task_name",
-        default=None,
-        type=str,
-        required=True,
-        help="The name of the task to train selected in the list: " + ", ".join(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.",
+    cache_dir: Optional[str] = field(
+        default=None, metadata={"help": "Where do you want to store the pre-trained models downloaded from s3"}
     )
 
-    # Other parameters
-    parser.add_argument(
-        "--config_name", default="", type=str, help="Pretrained config name or path if not the same as model_name",
+
+@dataclass
+class DataProcessingArguments:
+    task_name: str = field(
+        metadata={"help": "The name of the task to train selected in the list: " + ", ".join(processors.keys())}
     )
-    parser.add_argument(
-        "--tokenizer_name",
-        default="",
-        type=str,
-        help="Pretrained tokenizer name or path if not the same as model_name",
+    data_dir: str = field(
+        metadata={"help": "The input data dir. Should contain the .tsv files (or other data files) for the task."}
     )
-    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",
+    max_seq_length: int = field(
         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.",
+        metadata={
+            "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="Run 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.",
+    overwrite_cache: bool = field(
+        default=False, metadata={"help": "Overwrite the cached training and evaluation sets"}
     )
 
-    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=500, help="Log every X updates steps.")
-    parser.add_argument("--save_steps", type=int, default=500, 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")
+def main():
+    parser = HfArgumentParser((ModelArguments, DataProcessingArguments, TrainingArguments))
+    model_args, dataprocessing_args, training_args = parser.parse_args_into_dataclasses()
 
-    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()
+    # For now, let's merge all the sets of args into one,
+    # but soon, we'll keep distinct sets of args, with a cleaner separation of concerns.
+    args = argparse.Namespace(**vars(model_args), **vars(dataprocessing_args), **vars(training_args))
 
     if (
         os.path.exists(args.output_dir)
@@ -515,20 +436,9 @@ def main():
         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
-            )
+            f"Output directory ({args.output_dir}) already exists and is not empty. Use --overwrite_output_dir to overcome."
         )
 
-    # 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")
@@ -576,18 +486,16 @@ def main():
         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,
+        cache_dir=args.cache_dir,
     )
     tokenizer = AutoTokenizer.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,
+        args.tokenizer_name if args.tokenizer_name else args.model_name_or_path, cache_dir=args.cache_dir,
     )
     model = AutoModelForSequenceClassification.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,
+        cache_dir=args.cache_dir,
     )
 
     if args.local_rank == 0:
@@ -629,7 +537,7 @@ def main():
     # Evaluation
     results = {}
     if args.do_eval and args.local_rank in [-1, 0]:
-        tokenizer = AutoTokenizer.from_pretrained(args.output_dir, do_lower_case=args.do_lower_case)
+        tokenizer = AutoTokenizer.from_pretrained(args.output_dir)
         checkpoints = [args.output_dir]
         if args.eval_all_checkpoints:
             checkpoints = list(