[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/pytorch/translation/run_translation_no_trainer.py

@@ -175,7 +175,7 @@ def parse_args():
         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."
+            " sequences shorter will be padded if `--pad_to_max_length` is passed."
         ),
     )
     parser.add_argument(

examples/research_projects/bert-loses-patience/run_glue_with_pabee.py

@@ -148,7 +148,7 @@ def train(args, train_dataset, model, tokenizer):
     steps_trained_in_current_epoch = 0
     # Check if continuing training from a checkpoint
     if os.path.exists(args.model_name_or_path):
-        # 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
         global_step = int(args.model_name_or_path.split("-")[-1].split("/")[0])
         epochs_trained = global_step // (len(train_dataloader) // args.gradient_accumulation_steps)
         steps_trained_in_current_epoch = global_step % (len(train_dataloader) // args.gradient_accumulation_steps)
@@ -169,7 +169,7 @@ def train(args, train_dataset, model, tokenizer):
         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):
@@ -614,7 +614,7 @@ 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 = 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/research_projects/codeparrot/scripts/preprocessing.py

@@ -60,7 +60,7 @@ def is_autogenerated(example, scan_width=5):
 def is_config_or_test(example, scan_width=5, coeff=0.05):
     """Check if file is a configuration file or a unit test by :
     1- looking for keywords in the first few lines of the file.
-    2- counting number of occurence of the words 'config' and 'test' with respect to number of lines.
+    2- counting number of occurrence of the words 'config' and 'test' with respect to number of lines.
     """
 
     keywords = ["unit tests", "test file", "configuration file"]

examples/research_projects/deebert/run_glue_deebert.py

@@ -162,7 +162,7 @@ def train(args, train_dataset, model, tokenizer, train_highway=False):
     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)
+    set_seed(args)  # Added here for reproducibility (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):
@@ -491,7 +491,7 @@ def main():
         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 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(
@@ -566,7 +566,7 @@ 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 = 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/research_projects/distillation/run_squad_w_distillation.py

@@ -165,7 +165,7 @@ def train(args, train_dataset, model, tokenizer, teacher=None):
     # 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)
@@ -183,7 +183,7 @@ def train(args, train_dataset, model, tokenizer, teacher=None):
     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:
@@ -731,7 +731,7 @@ 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/research_projects/mm-imdb/run_mmimdb.py

@@ -134,7 +134,7 @@ def train(args, train_dataset, model, tokenizer, criterion):
     best_f1, n_no_improve = 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):
@@ -384,7 +384,7 @@ def main():
         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 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(
@@ -460,7 +460,7 @@ 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/research_projects/quantization-qdqbert/evaluate-hf-trt-qa.py

@@ -275,7 +275,7 @@ else:
 # https://huggingface.co/docs/datasets/loading_datasets.
 
 # Preprocessing the datasets.
-# Preprocessing is slighlty different for training and evaluation.
+# Preprocessing is slightly different for training and evaluation.
 
 column_names = raw_datasets["validation"].column_names
 

examples/research_projects/quantization-qdqbert/run_quant_qa.py

@@ -349,7 +349,7 @@ def main():
         )
 
     # Preprocessing the datasets.
-    # Preprocessing is slighlty different for training and evaluation.
+    # Preprocessing is slightly different for training and evaluation.
     if training_args.do_train or model_args.do_calib:
         column_names = raw_datasets["train"].column_names
     elif training_args.do_eval or model_args.save_onnx:
@@ -448,7 +448,7 @@ def main():
             raise ValueError("--do_train requires a train dataset")
         train_dataset = raw_datasets["train"]
         if data_args.max_train_samples is not None:
-            # We will select sample from whole data if agument is specified
+            # We will select sample from whole data if argument is specified
             max_train_samples = min(len(train_dataset), data_args.max_train_samples)
             train_dataset = train_dataset.select(range(max_train_samples))
         # Create train feature from dataset

examples/research_projects/seq2seq-distillation/README.md

@@ -239,7 +239,7 @@ 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/research_projects/seq2seq-distillation/run_eval.py

@@ -94,7 +94,7 @@ 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/research_projects/wav2vec2/run_common_voice.py

@@ -69,12 +69,12 @@ class ModelArguments:
     hidden_dropout: Optional[float] = field(
         default=0.1,
         metadata={
-            "help": "The dropout probabilitiy for all fully connected layers in the embeddings, encoder, and pooler."
+            "help": "The dropout probability for all fully connected layers in the embeddings, encoder, and pooler."
         },
     )
     feat_proj_dropout: Optional[float] = field(
         default=0.1,
-        metadata={"help": "The dropout probabilitiy for all 1D convolutional layers in feature extractor."},
+        metadata={"help": "The dropout probability for all 1D convolutional layers in feature extractor."},
     )
     mask_time_prob: Optional[float] = field(
         default=0.05,

examples/tensorflow/contrastive-image-text/run_clip.py

@@ -311,7 +311,7 @@ def main():
     # Log on each process the small summary:
     logger.info(f"Training/evaluation parameters {training_args}")
 
-    # 3. Detecting last checkpoint and eventualy continue from last checkpoint
+    # 3. Detecting last checkpoint and eventually continue from 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:
         if last_checkpoint is None and len(os.listdir(training_args.output_dir)) > 0:

examples/tensorflow/image-classification/README.md

@@ -107,10 +107,10 @@ from datasets import load_dataset
 # example 1: local folder
 dataset = load_dataset("imagefolder", data_dir="path_to_your_folder")
 
-# example 2: local files (suppoted formats are tar, gzip, zip, xz, rar, zstd)
+# example 2: local files (supported formats are tar, gzip, zip, xz, rar, zstd)
 dataset = load_dataset("imagefolder", data_files="path_to_zip_file")
 
-# example 3: remote files (suppoted formats are tar, gzip, zip, xz, rar, zstd)
+# example 3: remote files (supported formats are tar, gzip, zip, xz, rar, zstd)
 dataset = load_dataset("imagefolder", data_files="https://download.microsoft.com/download/3/E/1/3E1C3F21-ECDB-4869-8368-6DEBA77B919F/kagglecatsanddogs_3367a.zip")
 
 # example 4: providing several splits

examples/tensorflow/language-modeling-tpu/train_unigram.py

@@ -109,7 +109,7 @@ def main(args):
     tokenizer.decoder = decoders.Metaspace()
 
     if args.export_to_hub:
-        logger.info("Exporting the trained tokenzier to Hub.")
+        logger.info("Exporting the trained tokenizer to Hub.")
         new_tokenizer = AlbertTokenizerFast(tokenizer_object=tokenizer)
         new_tokenizer.push_to_hub("unigram-tokenizer-dataset")
 

examples/tensorflow/question-answering/run_qa.py

@@ -512,7 +512,7 @@ def main():
             raise ValueError("--do_train requires a train dataset")
         train_dataset = datasets["train"]
         if data_args.max_train_samples is not None:
-            # We will select sample from whole data if agument is specified
+            # We will select sample from whole data if argument is specified
             max_train_samples = min(len(train_dataset), data_args.max_train_samples)
             train_dataset = train_dataset.select(range(max_train_samples))
         # Create train feature from dataset

src/transformers/modeling_flax_utils.py

@@ -211,7 +211,7 @@ class FlaxPreTrainedModel(PushToHubMixin, FlaxGenerationMixin):
         self.input_shape = input_shape
         self.generation_config = GenerationConfig.from_model_config(config) if self.can_generate() else None
 
-        # To check if the model was intialized automatically.
+        # To check if the model was initialized automatically.
         self._is_initialized = _do_init
 
         if _do_init:

src/transformers/modeling_utils.py

@@ -3736,7 +3736,7 @@ class PreTrainedModel(nn.Module, ModuleUtilsMixin, GenerationMixin, PushToHubMix
                     else:
                         hf_quantizer.create_quantized_param(model, value, key, "cpu", state_dict)
 
-        # retrieve unintialized modules and initialize before maybe overriding that with the pretrained weights.
+        # retrieve uninitialized modules and initialize before maybe overriding that with the pretrained weights.
         if _fast_init:
             if not ignore_mismatched_sizes:
                 if remove_prefix_from_model:

src/transformers/models/big_bird/configuration_big_bird.py

@@ -58,7 +58,7 @@ class BigBirdConfig(PretrainedConfig):
             The non-linear activation function (function or string) in the encoder and pooler. If string, `"gelu"`,
             `"relu"`, `"selu"` and `"gelu_new"` are supported.
         hidden_dropout_prob (`float`, *optional*, defaults to 0.1):
-            The dropout probabilitiy for all fully connected layers in the embeddings, encoder, and pooler.
+            The dropout probability for all fully connected layers in the embeddings, encoder, and pooler.
         attention_probs_dropout_prob (`float`, *optional*, defaults to 0.1):
             The dropout ratio for the attention probabilities.
         max_position_embeddings (`int`, *optional*, defaults to 4096):

src/transformers/models/biogpt/configuration_biogpt.py

@@ -53,7 +53,7 @@ class BioGptConfig(PretrainedConfig):
             The non-linear activation function (function or string) in the encoder and pooler. If string, `"gelu"`,
             `"relu"`, `"selu"` and `"gelu_new"` are supported.
         hidden_dropout_prob (`float`, *optional*, defaults to 0.1):
-            The dropout probabilitiy for all fully connected layers in the embeddings, encoder, and pooler.
+            The dropout probability for all fully connected layers in the embeddings, encoder, and pooler.
         attention_probs_dropout_prob (`float`, *optional*, defaults to 0.1):
             The dropout ratio for the attention probabilities.
         max_position_embeddings (`int`, *optional*, defaults to 1024):

src/transformers/models/canine/configuration_canine.py

@@ -50,7 +50,7 @@ class CanineConfig(PretrainedConfig):
             The non-linear activation function (function or string) in the encoder and pooler. If string, `"gelu"`,
             `"relu"`, `"selu"` and `"gelu_new"` are supported.
         hidden_dropout_prob (`float`, *optional*, defaults to 0.1):
-            The dropout probabilitiy for all fully connected layers in the embeddings, encoders, and pooler.
+            The dropout probability for all fully connected layers in the embeddings, encoders, and pooler.
         attention_probs_dropout_prob (`float`, *optional*, defaults to 0.1):
             The dropout ratio for the attention probabilities.
         max_position_embeddings (`int`, *optional*, defaults to 16384):