[Docs] Fix spelling and grammar mistakes (#28825)

* Fix typos and grammar mistakes in docs and examples

* Fix typos in docstrings and comments

* Fix spelling of `tokenizer` in model tests

* Remove erroneous spaces in decorators

* Remove extra spaces in Markdown link texts

examples/legacy/question-answering/run_squad.py

@@ -148,7 +148,7 @@ def train(args, train_dataset, model, tokenizer):
     # Check if continuing training from a checkpoint
     if os.path.exists(args.model_name_or_path):
         try:
-            # set global_step to gobal_step of last saved checkpoint from model path
+            # set global_step to global_step of last saved checkpoint from model path
             checkpoint_suffix = args.model_name_or_path.split("-")[-1].split("/")[0]
             global_step = int(checkpoint_suffix)
             epochs_trained = global_step // (len(train_dataloader) // args.gradient_accumulation_steps)
@@ -166,7 +166,7 @@ def train(args, train_dataset, model, tokenizer):
     train_iterator = trange(
         epochs_trained, int(args.num_train_epochs), desc="Epoch", disable=args.local_rank not in [-1, 0]
     )
-    # Added here for reproductibility
+    # Added here for reproducibility
     set_seed(args)
 
     for _ in train_iterator:
@@ -705,7 +705,7 @@ def main():
     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
+    else:  # Initializes the distributed backend which will take care of synchronizing nodes/GPUs
         torch.cuda.set_device(args.local_rank)
         device = torch.device("cuda", args.local_rank)
         torch.distributed.init_process_group(backend="nccl")

examples/legacy/run_swag.py

@@ -338,7 +338,7 @@ def train(args, train_dataset, model, tokenizer):
     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
+    set_seed(args)  # Added here for reproducibility
     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):
@@ -538,7 +538,7 @@ def main():
         default=1,
         help="Number of updates steps to accumulate before performing a backward/update pass.",
     )
-    parser.add_argument("--weight_decay", default=0.0, type=float, help="Weight deay if we apply some.")
+    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(
@@ -612,7 +612,7 @@ def main():
     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
+    else:  # Initializes the distributed backend which will take care of synchronizing nodes/GPUs
         torch.cuda.set_device(args.local_rank)
         device = torch.device("cuda", args.local_rank)
         torch.distributed.init_process_group(backend="nccl")

examples/legacy/seq2seq/README.md

@@ -321,7 +321,7 @@ For example,
 ./save_len_file.py Helsinki-NLP/opus-mt-en-ro  wmt_en_ro
 ./dynamic_bs_example.sh --max_tokens_per_batch=2000 --output_dir benchmark_dynamic_bs
 ```
-splits `wmt_en_ro/train` into 11,197 uneven lengthed batches and can finish 1 epoch in 8 minutes on a v100.
+splits `wmt_en_ro/train` into 11,197 uneven length batches and can finish 1 epoch in 8 minutes on a v100.
 
 For comparison,
 ```bash

examples/legacy/seq2seq/run_distributed_eval.py

@@ -154,7 +154,7 @@ def run_generate():
     parser.add_argument("--src_lang", type=str, default=None, required=False)
     parser.add_argument("--tgt_lang", type=str, default=None, required=False)
     parser.add_argument(
-        "--prefix", type=str, required=False, default=None, help="will be added to the begininng of src examples"
+        "--prefix", type=str, required=False, default=None, help="will be added to the beginning of src examples"
     )
     parser.add_argument("--fp16", action="store_true")
     parser.add_argument("--debug", action="store_true")

examples/legacy/seq2seq/run_eval.py

@@ -107,7 +107,7 @@ def run_generate(verbose=True):
     parser.add_argument("--score_path", type=str, required=False, default="metrics.json", help="where to save metrics")
     parser.add_argument("--device", type=str, required=False, default=DEFAULT_DEVICE, help="cuda, cuda:1, cpu etc.")
     parser.add_argument(
-        "--prefix", type=str, required=False, default=None, help="will be added to the begininng of src examples"
+        "--prefix", type=str, required=False, default=None, help="will be added to the beginning of src examples"
     )
     parser.add_argument("--task", type=str, default="summarization", help="used for task_specific_params + metrics")
     parser.add_argument("--bs", type=int, default=8, required=False, help="batch size")

examples/legacy/seq2seq/seq2seq_trainer.py

@@ -65,7 +65,7 @@ class Seq2SeqTrainer(Trainer):
 
         if self.args.label_smoothing != 0 or (self.data_args is not None and self.data_args.ignore_pad_token_for_loss):
             assert self.config.pad_token_id is not None, (
-                "Make sure that `config.pad_token_id` is correcly defined when ignoring `pad_token` for loss"
+                "Make sure that `config.pad_token_id` is correctly defined when ignoring `pad_token` for loss"
                 " calculation or doing label smoothing."
             )
 

examples/legacy/seq2seq/seq2seq_training_args.py

@@ -31,7 +31,7 @@ class Seq2SeqTrainingArguments(TrainingArguments):
         label_smoothing (:obj:`float`, `optional`, defaults to 0):
             The label smoothing epsilon to apply (if not zero).
         sortish_sampler (:obj:`bool`, `optional`, defaults to :obj:`False`):
-            Whether to SortishSamler or not. It sorts the inputs according to lengths in-order to minimizing the padding size.
+            Whether to SortishSampler or not. It sorts the inputs according to lengths in-order to minimizing the padding size.
         predict_with_generate (:obj:`bool`, `optional`, defaults to :obj:`False`):
             Whether to use generate to calculate generative metrics (ROUGE, BLEU).
     """
@@ -39,7 +39,7 @@ class Seq2SeqTrainingArguments(TrainingArguments):
     label_smoothing: Optional[float] = field(
         default=0.0, metadata={"help": "The label smoothing epsilon to apply (if not zero)."}
     )
-    sortish_sampler: bool = field(default=False, metadata={"help": "Whether to SortishSamler or not."})
+    sortish_sampler: bool = field(default=False, metadata={"help": "Whether to SortishSampler or not."})
     predict_with_generate: bool = field(
         default=False, metadata={"help": "Whether to use generate to calculate generative metrics (ROUGE, BLEU)."}
     )