Remove unused variables in examples.

examples/contrib/run_openai_gpt.py

@@ -44,13 +44,10 @@ from transformers import (
     AdamW,
     OpenAIGPTDoubleHeadsModel,
     OpenAIGPTTokenizer,
-    cached_path,
     get_linear_schedule_with_warmup,
 )
 
 
-ROCSTORIES_URL = "https://s3.amazonaws.com/datasets.huggingface.co/ROCStories.tar.gz"
-
 logging.basicConfig(
     format="%(asctime)s - %(levelname)s - %(name)s -   %(message)s", datefmt="%m/%d/%Y %H:%M:%S", level=logging.INFO
 )
@@ -182,9 +179,6 @@ def main():
     model.to(device)
 
     # Load and encode the datasets
-    if not args.train_dataset and not args.eval_dataset:
-        roc_stories = cached_path(ROCSTORIES_URL)
-
     def tokenize_and_encode(obj):
         """ Tokenize and encode a nested object """
         if isinstance(obj, str):

examples/contrib/run_transfo_xl.py

@@ -28,7 +28,7 @@ import time
 
 import torch
 
-from transformers import TransfoXLCorpus, TransfoXLLMHeadModel, TransfoXLTokenizer
+from transformers import TransfoXLCorpus, TransfoXLLMHeadModel
 
 
 logging.basicConfig(
@@ -73,9 +73,7 @@ def main():
     # The pre-processing involve computing word frequencies to prepare the Adaptive input and SoftMax
     # and tokenizing the dataset
     # The pre-processed corpus is a convertion (using the conversion script )
-    tokenizer = TransfoXLTokenizer.from_pretrained(args.model_name)
     corpus = TransfoXLCorpus.from_pretrained(args.model_name)
-    ntokens = len(corpus.vocab)
 
     va_iter = corpus.get_iterator("valid", args.batch_size, args.tgt_len, device=device, ext_len=args.ext_len)
     te_iter = corpus.get_iterator("test", args.batch_size, args.tgt_len, device=device, ext_len=args.ext_len)

examples/run_multiple_choice.py

@@ -141,7 +141,7 @@ def train(args, train_dataset, model, tokenizer):
 
     global_step = 0
     tr_loss, logging_loss = 0.0, 0.0
-    best_dev_acc, best_dev_loss = 0.0, 99999999999.0
+    best_dev_acc = 0.0
     best_steps = 0
     model.zero_grad()
     train_iterator = trange(int(args.num_train_epochs), desc="Epoch", disable=args.local_rank not in [-1, 0])
@@ -193,7 +193,6 @@ def train(args, train_dataset, model, tokenizer):
                             tb_writer.add_scalar("eval_{}".format(key), value, global_step)
                         if results["eval_acc"] > best_dev_acc:
                             best_dev_acc = results["eval_acc"]
-                            best_dev_loss = results["eval_loss"]
                             best_steps = global_step
                             if args.do_test:
                                 results_test = evaluate(args, model, tokenizer, test=True)

examples/summarization/modeling_bertabs.py

@@ -446,8 +446,6 @@ class MultiHeadedAttention(nn.Module):
         batch_size = key.size(0)
         dim_per_head = self.dim_per_head
         head_count = self.head_count
-        key_len = key.size(1)
-        query_len = query.size(1)
 
         def shape(x):
             """  projection """
@@ -504,9 +502,6 @@ class MultiHeadedAttention(nn.Module):
 
         query = shape(query)
 
-        key_len = key.size(2)
-        query_len = query.size(2)
-
         # 2) Calculate and scale scores.
         query = query / math.sqrt(dim_per_head)
         scores = torch.matmul(query, key.transpose(2, 3))