BIG Reorganize examples (#4213)

* Created using Colaboratory

* [examples] reorganize files

* remove run_tpu_glue.py as superseded by TPU support in Trainer

* Bugfix: int, not tuple

* move files around

tests/test_trainer.py

@@ -28,7 +28,7 @@ class DataCollatorIntegrationTest(unittest.TestCase):
         MODEL_ID = "bert-base-cased-finetuned-mrpc"
         tokenizer = AutoTokenizer.from_pretrained(MODEL_ID)
         data_args = GlueDataTrainingArguments(
-            task_name="mrpc", data_dir="./examples/tests_samples/MRPC", overwrite_cache=True
+            task_name="mrpc", data_dir="./tests/fixtures/tests_samples/MRPC", overwrite_cache=True
         )
         dataset = GlueDataset(data_args, tokenizer=tokenizer, evaluate=True)
         data_collator = DefaultDataCollator()
@@ -39,7 +39,7 @@ class DataCollatorIntegrationTest(unittest.TestCase):
         MODEL_ID = "distilroberta-base"
         tokenizer = AutoTokenizer.from_pretrained(MODEL_ID)
         data_args = GlueDataTrainingArguments(
-            task_name="sts-b", data_dir="./examples/tests_samples/STS-B", overwrite_cache=True
+            task_name="sts-b", data_dir="./tests/fixtures/tests_samples/STS-B", overwrite_cache=True
         )
         dataset = GlueDataset(data_args, tokenizer=tokenizer, evaluate=True)
         data_collator = DefaultDataCollator()
@@ -91,7 +91,7 @@ class TrainerIntegrationTest(unittest.TestCase):
         tokenizer = AutoTokenizer.from_pretrained(MODEL_ID)
         model = AutoModelForSequenceClassification.from_pretrained(MODEL_ID)
         data_args = GlueDataTrainingArguments(
-            task_name="mrpc", data_dir="./examples/tests_samples/MRPC", overwrite_cache=True
+            task_name="mrpc", data_dir="./tests/fixtures/tests_samples/MRPC", overwrite_cache=True
         )
         eval_dataset = GlueDataset(data_args, tokenizer=tokenizer, evaluate=True)
 

valohai.yaml

 ---
 
 - step:
-    name: Execute python examples/run_glue.py
+    name: Execute python examples/text-classification/run_glue.py
     image: pytorch/pytorch:nightly-devel-cuda10.0-cudnn7
     command:
       - python /valohai/repository/utils/download_glue_data.py --data_dir=/glue_data
       - pip install -e .
       - pip install -r examples/requirements.txt
-      - python examples/run_glue.py --do_train --data_dir=/glue_data/{parameter-value:task_name} {parameters}
+      - python examples/text-classification/run_glue.py --do_train --data_dir=/glue_data/{parameter-value:task_name} {parameters}
     parameters:
       - name: model_type
         pass-as: --model_type={v}