Speed up question answering tests (#775)

Lightning-Universe · Sep 20, 2021 · c2095d3 · c2095d3
1 parent 81c467c
commit c2095d3
Show file tree

Hide file tree

Showing 2 changed files with 8 additions and 9 deletions.
diff --git a/flash/text/question_answering/cli.py b/flash/text/question_answering/cli.py
@@ -25,12 +25,12 @@ def from_squad(
     num_workers: int = 0,
     **preprocess_kwargs,
 ) -> QuestionAnsweringData:
-    """Downloads and loads the XSum data set."""
-    download_data("https://rajpurkar.github.io/SQuAD-explorer/dataset/train-v2.0.json", "./data/")
-    download_data("https://rajpurkar.github.io/SQuAD-explorer/dataset/dev-v2.0.json", "./data/")
+    """Downloads and loads a tiny subset of the squad V2 data set."""
+    download_data("https://pl-flash-data.s3.amazonaws.com/squad_tiny.zip", "./data/")
+
     return QuestionAnsweringData.from_squad_v2(
-        train_file="./data/train-v2.0.json",
-        val_file="./data/dev-v2.0.json",
+        train_file="./data/squad_tiny/train.json",
+        val_file="./data/squad_tiny/val.json",
         backbone=backbone,
         batch_size=batch_size,
         num_workers=num_workers,

diff --git a/flash_examples/question_answering.py b/flash_examples/question_answering.py
@@ -16,12 +16,11 @@
 from flash.text import QuestionAnsweringData, QuestionAnsweringTask
 
 # 1. Create the DataModule
-download_data("https://rajpurkar.github.io/SQuAD-explorer/dataset/train-v2.0.json", "./data/")
-download_data("https://rajpurkar.github.io/SQuAD-explorer/dataset/dev-v2.0.json", "./data/")
+download_data("https://pl-flash-data.s3.amazonaws.com/squad_tiny.zip", "./data/")
 
 datamodule = QuestionAnsweringData.from_squad_v2(
-    train_file="./data/train-v2.0.json",
-    val_file="./data/dev-v2.0.json",
+    train_file="./data/squad_tiny/train.json",
+    val_file="./data/squad_tiny/val.json",
 )
 
 # 2. Build the task