Minor tqdm and logging clean up (#4448)

* fix formatting

* set tqdm descriptions in various places

Co-authored-by: Dirk Groeneveld <[email protected]>

Author: epwalsh

allennlp/commands/train.py

@@ -236,7 +236,7 @@ def train_model(
         world_size = num_nodes * num_procs
 
         logging.info(
-            f"Switching to distributed training mode since multiple GPUs are configured"
+            f"Switching to distributed training mode since multiple GPUs are configured | "
             f"Master is at: {master_addr}:{master_port} | Rank of this node: {node_rank} | "
             f"Number of workers in this node: {num_procs} | Number of nodes: {num_nodes} | "
             f"World size: {world_size}"

allennlp/common/file_utils.py

@@ -283,7 +283,7 @@ def _http_get(url: str, temp_file: IO) -> None:
         req = session.get(url, stream=True)
         content_length = req.headers.get("Content-Length")
         total = int(content_length) if content_length is not None else None
-        progress = Tqdm.tqdm(unit="B", total=total)
+        progress = Tqdm.tqdm(unit="B", total=total, desc="downloading")
         for chunk in req.iter_content(chunk_size=1024):
             if chunk:  # filter out keep-alive new chunks
                 progress.update(len(chunk))

allennlp/data/dataset_readers/dataset_reader.py

@@ -282,7 +282,7 @@ def _instances_to_cache_file(self, cache_filename, instances) -> None:
         # Then we just copy the file over to `cache_filename`.
         with CacheFile(cache_filename, mode="w+") as cache_handle:
             logger.info("Caching instances to temp file %s", cache_handle.name)
-            for instance in Tqdm.tqdm(instances):
+            for instance in Tqdm.tqdm(instances, desc="caching instances"):
                 cache_handle.write(self.serialize_instance(instance) + "\n")
 
     def text_to_instance(self, *inputs) -> Instance:
@@ -381,7 +381,7 @@ def _multi_worker_islice(
 
         islice = itertools.islice(iterable, start_index, self.max_instances, step_size)
         if wrap_with_tqdm:
-            islice = Tqdm.tqdm(islice)
+            islice = Tqdm.tqdm(islice, desc="reading instances")
 
         if transform is not None:
             return (transform(x) for x in islice)

allennlp/data/vocabulary.py

@@ -288,7 +288,7 @@ def from_instances(
         padding_token = padding_token if padding_token is not None else DEFAULT_PADDING_TOKEN
         oov_token = oov_token if oov_token is not None else DEFAULT_OOV_TOKEN
         namespace_token_counts: Dict[str, Dict[str, int]] = defaultdict(lambda: defaultdict(int))
-        for instance in Tqdm.tqdm(instances):
+        for instance in Tqdm.tqdm(instances, desc="building vocab"):
             instance.count_vocab_items(namespace_token_counts)
 
         return cls(