Updated some lingering references to old configs (EleutherAI#830)

* Updated some lingering references to old configs

* Update NeoXArgs docs automatically

* Update NeoXArgs docs automatically

* Update NeoXArgs docs automatically

---------

Co-authored-by: github-actions <[email protected]>
Co-authored-by: Stella Biderman <[email protected]>

README-MUP.md

@@ -42,7 +42,7 @@
 
 ## Tune mup hyperparameters and LR
 
-The values under `mup hp search` were added and correspond to appendix F.4 from https://arxiv.org/pdf/2203.03466.pdf. These and LR are tuned with a random search using the scaled-up config (tested with 6-7B.yml) but with hidden-size set to the value from the scaled-down config (small.yml).
+The values under `mup hp search` were added and correspond to appendix F.4 from https://arxiv.org/pdf/2203.03466.pdf. These and LR are tuned with a random search using the scaled-up config (tested with 6-7B.yml) but with hidden-size set to the value from the scaled-down config (125M.yml).
 
 ## Transfer
 

README.md

@@ -238,12 +238,12 @@ You can also optionally pass in a config prefix, which will assume all your conf
 E.G:
 
 ```bash
-python ./deepy.py train.py -d configs small.yml local_setup.yml
+python ./deepy.py train.py -d configs 125M.yml local_setup.yml
 ```
 
 This will deploy the `train.py` script on all nodes with one process per GPU. The worker nodes and number of GPUs are specified in the `/job/hostfile` file (see [parameter documentation](configs/README.md)), or can simply be passed in as the `num_gpus` arg if running on a single node setup.
 
-Although this is not strictly necessary, we find it useful to define the model parameters in one config file (e.g `configs/small.yml`) and the data path parameters in another (e.g `configs/local_setup.yml`).
+Although this is not strictly necessary, we find it useful to define the model parameters in one config file (e.g `configs/125M.yml`) and the data path parameters in another (e.g `configs/local_setup.yml`).
 
 
 ## Pretrained Models
@@ -293,7 +293,7 @@ We support three types of generation from a pretrained model:
 2. Conditional generation based on an input read from a file
 3. Interactive generation, which allows for multiple rounds of back-and-forth between a user and the language model via a command line interface
 
-All three types of text generation can be launched via `python ./deepy.py generate.py -d configs small.yml local_setup.yml text_generation.yml` with the appropriate values set in `configs/text_generation.yml`.
+All three types of text generation can be launched via `python ./deepy.py generate.py -d configs 125M.yml local_setup.yml text_generation.yml` with the appropriate values set in `configs/text_generation.yml`.
 
 # Evaluation
 

configs/neox_arguments.md

@@ -111,7 +111,7 @@ Logging Arguments
 
 - **git_hash**: str
 
- Default = ed27de5
+ Default = ebaeec1
 
  current git hash of repository
 

megatron/neox_arguments/arguments.py

@@ -352,7 +352,7 @@ def consume_deepy_args(cls):
  if args_parsed.conf_dir:
  conf_files = [os.path.join(args_parsed.conf_dir, f) for f in conf_files]
 
- # enables us to pass in `small` instead of `small.yml`
+ # enables us to pass in `125M` instead of `125M.yml`
  conf_files = [
  (cf if (cf.endswith(".yml") or cf.endswith(".json")) else cf + ".yml")
  for cf in conf_files

tests/neox_args/test_neoxargs_commandline.py

@@ -34,13 +34,13 @@ def test_neoxargs_consume_deepy_args_with_config_dir():
  with patch(
  "sys.argv",
  [str(get_root_directory() / "deepy.py"), "train.py"]
- + get_configs_with_path(["small.yml", "local_setup.yml"]),
+ + get_configs_with_path(["125M.yml", "local_setup.yml"]),
  ):
  args_loaded_consume = NeoXArgs.consume_deepy_args()
 
  # load neox args directly from yaml files
  args_loaded_yamls = NeoXArgs.from_ymls(
- get_configs_with_path(["small.yml", "local_setup.yml"])
+ get_configs_with_path(["125M.yml", "local_setup.yml"])
  )
 
  # update values from yaml files that cannot otherwise be matched
@@ -62,13 +62,13 @@ def test_neoxargs_consume_deepy_args_without_yml_suffix():
  with patch(
  "sys.argv",
  [str(get_root_directory() / "deepy.py"), "train.py"]
- + get_configs_with_path(["small", "local_setup", "cpu_mock_config.yml"]),
+ + get_configs_with_path(["125M", "local_setup", "cpu_mock_config.yml"]),
  ):
  args_loaded_consume = NeoXArgs.consume_deepy_args()
 
  # load neox args directly from yaml files
  args_loaded_yamls = NeoXArgs.from_ymls(
- get_configs_with_path(["small.yml", "local_setup.yml", "cpu_mock_config.yml"])
+ get_configs_with_path(["125M.yml", "local_setup.yml", "cpu_mock_config.yml"])
  )
 
  # update values from yaml files that cannot otherwise be matched
@@ -91,14 +91,14 @@ def test_neoxargs_consume_deepy_args_with_hostfile_param():
  with patch(
  "sys.argv",
  [str(get_root_directory() / "deepy.py"), "train.py"]
- + get_configs_with_path(["small", "local_setup", "cpu_mock_config.yml"])
+ + get_configs_with_path(["125M", "local_setup", "cpu_mock_config.yml"])
  + ["--hostfile=/mock_path"],
  ):
  args_loaded_consume = NeoXArgs.consume_deepy_args()
 
  # load neox args directly from yaml files
  args_loaded_yamls = NeoXArgs.from_ymls(
- get_configs_with_path(["small.yml", "local_setup.yml", "cpu_mock_config.yml"])
+ get_configs_with_path(["125M.yml", "local_setup.yml", "cpu_mock_config.yml"])
  )
 
  # update values from yaml files that cannot otherwise be matched
@@ -125,13 +125,13 @@ def test_neoxargs_consume_deepy_args_with_config_dir():
  "-d",
  str(get_config_directory()),
  ]
- + ["small.yml", "local_setup.yml", "cpu_mock_config.yml"],
+ + ["125M.yml", "local_setup.yml", "cpu_mock_config.yml"],
  ):
  args_loaded_consume = NeoXArgs.consume_deepy_args()
 
  # load neox args directly from yaml files
  args_loaded_yamls = NeoXArgs.from_ymls(
- get_configs_with_path(["small.yml", "local_setup.yml", "cpu_mock_config.yml"])
+ get_configs_with_path(["125M.yml", "local_setup.yml", "cpu_mock_config.yml"])
  )
 
  # update values from yaml files that cannot otherwise be matched
@@ -150,7 +150,7 @@ def test_neoxargs_consume_neox_args():
 
  # intitially load config from files as would be the case in deepy.py
  yaml_list = get_configs_with_path(
- ["small.yml", "local_setup.yml", "cpu_mock_config.yml"]
+ ["125M.yml", "local_setup.yml", "cpu_mock_config.yml"]
  )
  args_baseline = NeoXArgs.from_ymls(yaml_list)
  args_baseline.update_value("user_script", str(get_root_directory() / "train.py"))

tests/neox_args/test_neoxargs_load.py

@@ -63,37 +63,37 @@ def run_neox_args_load_test(yaml_files):
 
 
 @pytest.mark.cpu
-def test_neoxargs_load_arguments_small_local_setup():
+def test_neoxargs_load_arguments_125M_local_setup():
  """
- verify small.yml can be loaded without raising validation errors
+ verify 125M.yml can be loaded without raising validation errors
  """
- run_neox_args_load_test(["small.yml", "local_setup.yml", "cpu_mock_config.yml"])
+ run_neox_args_load_test(["125M.yml", "local_setup.yml", "cpu_mock_config.yml"])
 
 
 @pytest.mark.cpu
-def test_neoxargs_load_arguments_small_local_setup_text_generation():
+def test_neoxargs_load_arguments_125M_local_setup_text_generation():
  """
- verify small.yml can be loaded together with text generation without raising validation errors
+ verify 125M.yml can be loaded together with text generation without raising validation errors
  """
  run_neox_args_load_test(
- ["small.yml", "local_setup.yml", "text_generation.yml", "cpu_mock_config.yml"]
+ ["125M.yml", "local_setup.yml", "text_generation.yml", "cpu_mock_config.yml"]
  )
 
 
 @pytest.mark.cpu
-def test_neoxargs_load_arguments_medium_local_setup():
+def test_neoxargs_load_arguments_350M_local_setup():
  """
- verify medium.yml can be loaded without raising validation errors
+ verify 350M.yml can be loaded without raising validation errors
  """
- run_neox_args_load_test(["medium.yml", "local_setup.yml", "cpu_mock_config.yml"])
+ run_neox_args_load_test(["350M.yml", "local_setup.yml", "cpu_mock_config.yml"])
 
 
 @pytest.mark.cpu
-def test_neoxargs_load_arguments_large_local_setup():
+def test_neoxargs_load_arguments_760M_local_setup():
  """
- verify large.yml can be loaded without raising validation errors
+ verify 760M.yml can be loaded without raising validation errors
  """
- run_neox_args_load_test(["large.yml", "local_setup.yml", "cpu_mock_config.yml"])
+ run_neox_args_load_test(["760M.yml", "local_setup.yml", "cpu_mock_config.yml"])
 
 
 @pytest.mark.cpu
@@ -121,11 +121,11 @@ def test_neoxargs_load_arguments_13B_local_setup():
 
 
 @pytest.mark.cpu
-def test_neoxargs_load_arguments_XL_local_setup():
+def test_neoxargs_load_arguments_1_3B_local_setup():
  """
- verify XL.yml can be loaded without raising validation errors
+ verify 1-3B.yml can be loaded without raising validation errors
  """
- run_neox_args_load_test(["XL.yml", "local_setup.yml", "cpu_mock_config.yml"])
+ run_neox_args_load_test(["1-3B.yml", "local_setup.yml", "cpu_mock_config.yml"])
 
 
 @pytest.mark.cpu