Initial Commit

Browse files

Files changed (13) hide show

README.md +40 -24
args.yml +65 -0
config.yml +25 -0
env_kwargs.yml +1 -0
ppo-Pendulum-v1.zip +2 -2
ppo-Pendulum-v1/_stable_baselines3_version +1 -1
ppo-Pendulum-v1/data +39 -39
ppo-Pendulum-v1/policy.optimizer.pth +1 -1
ppo-Pendulum-v1/policy.pth +1 -1
ppo-Pendulum-v1/system_info.txt +4 -4
replay.mp4 +2 -2
results.json +1 -1
train_eval_metrics.zip +3 -0

README.md CHANGED Viewed

@@ -10,7 +10,7 @@ model-index:
   results:
   - metrics:
     - type: mean_reward
-      value: -272.21 +/- 159.73
       name: mean_reward
     task:
       type: reinforcement-learning
@@ -20,31 +20,47 @@ model-index:
       type: Pendulum-v1
 ---
-  # **PPO** Agent playing **Pendulum-v1**
-  This is a trained model of a **PPO** agent playing **Pendulum-v1** using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
-  ## Usage (with Stable-baselines3)
-```python
-from stable_baselines3 import PPO
-from stable_baselines3.common.env_util import make_vec_env
-# Create the environment
-env_id = "Pendulum-v1"
-env = make_vec_env(env_id, n_envs=1)
-# Instantiate the agent
-model = PPO(
-    "MlpPolicy",
-    env,
-    gamma=0.98,
-    use_sde=True,
-    sde_sample_freq=4,
-    learning_rate=1e-3,
-    verbose=1,
-)
-# Train the agent
-model.learn(total_timesteps=int(1e5))
 ```

   results:
   - metrics:
     - type: mean_reward
+      value: -230.42 +/- 142.54
       name: mean_reward
     task:
       type: reinforcement-learning
       type: Pendulum-v1
 ---
+# **PPO** Agent playing **Pendulum-v1**
+This is a trained model of a **PPO** agent playing **Pendulum-v1**
+using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3)
+and the [RL Zoo](https://github.com/DLR-RM/rl-baselines3-zoo).
+The RL Zoo is a training framework for Stable Baselines3
+reinforcement learning agents,
+with hyperparameter optimization and pre-trained agents included.
+## Usage (with SB3 RL Zoo)
+RL Zoo: https://github.com/DLR-RM/rl-baselines3-zoo<br/>
+SB3: https://github.com/DLR-RM/stable-baselines3<br/>
+SB3 Contrib: https://github.com/Stable-Baselines-Team/stable-baselines3-contrib
+```
+# Download model and save it into the logs/ folder
+python -m utils.load_from_hub --algo ppo --env Pendulum-v1 -orga sb3 -f logs/
+python enjoy.py --algo ppo --env Pendulum-v1  -f logs/
+```
+## Training (with the RL Zoo)
+```
+python train.py --algo ppo --env Pendulum-v1 -f logs/
+# Upload the model and generate video (when possible)
+python -m utils.push_to_hub --algo ppo --env Pendulum-v1 -f logs/ -orga sb3
+```
+## Hyperparameters
+```python
+OrderedDict([('clip_range', 0.2),
+             ('ent_coef', 0.0),
+             ('gae_lambda', 0.95),
+             ('gamma', 0.9),
+             ('learning_rate', 0.001),
+             ('n_envs', 4),
+             ('n_epochs', 10),
+             ('n_steps', 1024),
+             ('n_timesteps', 100000.0),
+             ('policy', 'MlpPolicy'),
+             ('sde_sample_freq', 4),
+             ('use_sde', True),
+             ('normalize', False)])
 ```

args.yml ADDED Viewed

	@@ -0,0 +1,65 @@

+!!python/object/apply:collections.OrderedDict
+- - - algo
+    - ppo
+  - - env
+    - Pendulum-v0
+  - - env_kwargs
+    - null
+  - - eval_episodes
+    - 20
+  - - eval_freq
+    - 10000
+  - - gym_packages
+    - []
+  - - hyperparams
+    - null
+  - - log_folder
+    - logs
+  - - log_interval
+    - -1
+  - - n_eval_envs
+    - 10
+  - - n_evaluations
+    - 20
+  - - n_jobs
+    - 1
+  - - n_startup_trials
+    - 10
+  - - n_timesteps
+    - -1
+  - - n_trials
+    - 10
+  - - no_optim_plots
+    - false
+  - - num_threads
+    - 2
+  - - optimization_log_path
+    - null
+  - - optimize_hyperparameters
+    - false
+  - - pruner
+    - median
+  - - sampler
+    - tpe
+  - - save_freq
+    - -1
+  - - save_replay_buffer
+    - false
+  - - seed
+    - 620965731
+  - - storage
+    - null
+  - - study_name
+    - null
+  - - tensorboard_log
+    - ''
+  - - trained_agent
+    - ''
+  - - truncate_last_trajectory
+    - true
+  - - uuid
+    - false
+  - - vec_env
+    - dummy
+  - - verbose
+    - 1

config.yml ADDED Viewed

	@@ -0,0 +1,25 @@

+!!python/object/apply:collections.OrderedDict
+- - - clip_range
+    - 0.2
+  - - ent_coef
+    - 0.0
+  - - gae_lambda
+    - 0.95
+  - - gamma
+    - 0.9
+  - - learning_rate
+    - 0.001
+  - - n_envs
+    - 4
+  - - n_epochs
+    - 10
+  - - n_steps
+    - 1024
+  - - n_timesteps
+    - 100000.0
+  - - policy
+    - MlpPolicy
+  - - sde_sample_freq
+    - 4
+  - - use_sde
+    - true

env_kwargs.yml ADDED Viewed

	@@ -0,0 +1 @@


1	+ {}

ppo-Pendulum-v1.zip CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:00aadf63e4759008a054ce7cc1f32d01d6b53f8dfcf70af0a19af5b917a2eb2b
-size 134677

 version https://git-lfs.github.com/spec/v1
+oid sha256:c09e61dbf45ef98ad5f8a615b430144f5b1e7233f97ec304aba079920996eb17
+size 139074

ppo-Pendulum-v1/_stable_baselines3_version CHANGED Viewed

	@@ -1 +1 @@
1	- 1.5.~~1a5~~


1	+ 1.5.1a6

ppo-Pendulum-v1/data CHANGED Viewed

@@ -4,85 +4,85 @@
         ":serialized:": "gAWVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==",
         "__module__": "stable_baselines3.common.policies",
         "__doc__": "\n    Policy class for actor-critic algorithms (has both policy and value prediction).\n    Used by A2C, PPO and the likes.\n\n    :param observation_space: Observation space\n    :param action_space: Action space\n    :param lr_schedule: Learning rate schedule (could be constant)\n    :param net_arch: The specification of the policy and value networks.\n    :param activation_fn: Activation function\n    :param ortho_init: Whether to use or not orthogonal initialization\n    :param use_sde: Whether to use State Dependent Exploration or not\n    :param log_std_init: Initial value for the log standard deviation\n    :param full_std: Whether to use (n_features x n_actions) parameters\n        for the std instead of only (n_features,) when using gSDE\n    :param sde_net_arch: Network architecture for extracting features\n        when using gSDE. If None, the latent features from the policy will be used.\n        Pass an empty list to use the states as features.\n    :param use_expln: Use ``expln()`` function instead of ``exp()`` to ensure\n        a positive standard deviation (cf paper). It allows to keep variance\n        above zero and prevent it from growing too fast. In practice, ``exp()`` is usually enough.\n    :param squash_output: Whether to squash the output using a tanh function,\n        this allows to ensure boundaries when using gSDE.\n    :param features_extractor_class: Features extractor to use.\n    :param features_extractor_kwargs: Keyword arguments\n        to pass to the features extractor.\n    :param normalize_images: Whether to normalize images or not,\n         dividing by 255.0 (True by default)\n    :param optimizer_class: The optimizer to use,\n        ``th.optim.Adam`` by default\n    :param optimizer_kwargs: Additional keyword arguments,\n        excluding the learning rate, to pass to the optimizer\n    ",
-        "__init__": "<function ActorCriticPolicy.__init__ at 0x7f74713728c0>",
-        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f7471372950>",
-        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f74713729e0>",
-        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f7471372a70>",
-        "_build": "<function ActorCriticPolicy._build at 0x7f7471372b00>",
-        "forward": "<function ActorCriticPolicy.forward at 0x7f7471372b90>",
-        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f7471372c20>",
-        "_predict": "<function ActorCriticPolicy._predict at 0x7f7471372cb0>",
-        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f7471372d40>",
-        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f7471372dd0>",
-        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f7471372e60>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc_data object at 0x7f7471349390>"
     },
     "verbose": 1,
     "policy_kwargs": {},
     "observation_space": {
         ":type:": "<class 'gym.spaces.box.Box'>",
-        ":serialized:": "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",
         "dtype": "float32",
-        "_shape": [
-            3
-        ],
         "low": "[-1. -1. -8.]",
         "high": "[1. 1. 8.]",
         "bounded_below": "[ True  True  True]",
         "bounded_above": "[ True  True  True]",
-        "_np_random": null
     },
     "action_space": {
         ":type:": "<class 'gym.spaces.box.Box'>",
-        ":serialized:": "gAWVWQEAAAAAAACMDmd5bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lGgFk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMBl9zaGFwZZRLAYWUjANsb3eUjBJudW1weS5jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWBAAAAAAAAAAAAADAlGgKSwGFlIwBQ5R0lFKUjARoaWdolGgSKJYEAAAAAAAAAAAAAECUaApLAYWUaBV0lFKUjA1ib3VuZGVkX2JlbG93lGgSKJYBAAAAAAAAAAGUaAeMAmIxlImIh5RSlChLA4wBfJROTk5K/////0r/////SwB0lGJLAYWUaBV0lFKUjA1ib3VuZGVkX2Fib3ZllGgSKJYBAAAAAAAAAAGUaCFLAYWUaBV0lFKUjApfbnBfcmFuZG9tlE51Yi4=",
         "dtype": "float32",
-        "_shape": [
-            1
-        ],
         "low": "[-2.]",
         "high": "[2.]",
         "bounded_below": "[ True]",
         "bounded_above": "[ True]",
-        "_np_random": null
     },
-    "n_envs": 1,
-    "num_timesteps": 100352,
     "_total_timesteps": 100000,
     "_num_timesteps_at_start": 0,
-    "seed": null,
     "action_noise": null,
-    "start_time": 1651656807.660387,
-    "learning_rate": 0.001,
     "tensorboard_log": null,
     "lr_schedule": {
         ":type:": "<class 'function'>",
-        ":serialized:": "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"
-    },
-    "_last_obs": {
-        ":type:": "<class 'numpy.ndarray'>",
-        ":serialized:": "gAWVgQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYMAAAAAAAAAHnwfz9RULK8EVDfvZSMBW51bXB5lIwFZHR5cGWUk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGJLAUsDhpSMAUOUdJRSlC4="
     },
     "_last_episode_starts": {
         ":type:": "<class 'numpy.ndarray'>",
-        ":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="
     },
     "_last_original_obs": null,
     "_episode_num": 0,
     "use_sde": true,
     "sde_sample_freq": 4,
-    "_current_progress_remaining": -0.0035199999999999676,
     "ep_info_buffer": {
         ":type:": "<class 'collections.deque'>",
-        ":serialized:": "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"
     },
     "ep_success_buffer": {
         ":type:": "<class 'collections.deque'>",
         ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
     },
-    "_n_updates": 490,
-    "n_steps": 2048,
-    "gamma": 0.98,
     "gae_lambda": 0.95,
     "ent_coef": 0.0,
     "vf_coef": 0.5,
@@ -91,7 +91,7 @@
     "n_epochs": 10,
     "clip_range": {
         ":type:": "<class 'function'>",
-        ":serialized:": "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"
     },
     "clip_range_vf": null,
     "normalize_advantage": true,

         ":serialized:": "gAWVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==",
         "__module__": "stable_baselines3.common.policies",
         "__doc__": "\n    Policy class for actor-critic algorithms (has both policy and value prediction).\n    Used by A2C, PPO and the likes.\n\n    :param observation_space: Observation space\n    :param action_space: Action space\n    :param lr_schedule: Learning rate schedule (could be constant)\n    :param net_arch: The specification of the policy and value networks.\n    :param activation_fn: Activation function\n    :param ortho_init: Whether to use or not orthogonal initialization\n    :param use_sde: Whether to use State Dependent Exploration or not\n    :param log_std_init: Initial value for the log standard deviation\n    :param full_std: Whether to use (n_features x n_actions) parameters\n        for the std instead of only (n_features,) when using gSDE\n    :param sde_net_arch: Network architecture for extracting features\n        when using gSDE. If None, the latent features from the policy will be used.\n        Pass an empty list to use the states as features.\n    :param use_expln: Use ``expln()`` function instead of ``exp()`` to ensure\n        a positive standard deviation (cf paper). It allows to keep variance\n        above zero and prevent it from growing too fast. In practice, ``exp()`` is usually enough.\n    :param squash_output: Whether to squash the output using a tanh function,\n        this allows to ensure boundaries when using gSDE.\n    :param features_extractor_class: Features extractor to use.\n    :param features_extractor_kwargs: Keyword arguments\n        to pass to the features extractor.\n    :param normalize_images: Whether to normalize images or not,\n         dividing by 255.0 (True by default)\n    :param optimizer_class: The optimizer to use,\n        ``th.optim.Adam`` by default\n    :param optimizer_kwargs: Additional keyword arguments,\n        excluding the learning rate, to pass to the optimizer\n    ",
+        "__init__": "<function ActorCriticPolicy.__init__ at 0x7f25658c3a70>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f25658c3b00>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f25658c3b90>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f25658c3c20>",
+        "_build": "<function ActorCriticPolicy._build at 0x7f25658c3cb0>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7f25658c3d40>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f25658c3dd0>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7f25658c3e60>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f25658c3ef0>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f25658c3f80>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f25658c9050>",
         "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc_data object at 0x7f2565917660>"
     },
     "verbose": 1,
     "policy_kwargs": {},
     "observation_space": {
         ":type:": "<class 'gym.spaces.box.Box'>",
+        ":serialized:": "gAWVbQEAAAAAAACMDmd5bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lGgFk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMA2xvd5SMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYMAAAAAAAAAAAAgL8AAIC/AAAAwZRoCksDhZSMAUOUdJRSlIwEaGlnaJRoECiWDAAAAAAAAAAAAIA/AACAPwAAAEGUaApLA4WUaBN0lFKUjA1ib3VuZGVkX2JlbG93lGgQKJYDAAAAAAAAAAEBAZRoB4wCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksDhZRoE3SUUpSMDWJvdW5kZWRfYWJvdmWUaBAolgMAAAAAAAAAAQEBlGgfSwOFlGgTdJRSlIwKX25wX3JhbmRvbZROjAZfc2hhcGWUSwOFlHViLg==",
         "dtype": "float32",
         "low": "[-1. -1. -8.]",
         "high": "[1. 1. 8.]",
         "bounded_below": "[ True  True  True]",
         "bounded_above": "[ True  True  True]",
+        "_np_random": null,
+        "_shape": [
+            3
+        ]
     },
     "action_space": {
         ":type:": "<class 'gym.spaces.box.Box'>",
+        ":serialized:": "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",
         "dtype": "float32",
         "low": "[-2.]",
         "high": "[2.]",
         "bounded_below": "[ True]",
         "bounded_above": "[ True]",
+        "_np_random": "RandomState(MT19937)",
+        "_shape": [
+            1
+        ]
     },
+    "n_envs": 4,
+    "num_timesteps": 102400,
     "_total_timesteps": 100000,
     "_num_timesteps_at_start": 0,
+    "seed": 0,
     "action_noise": null,
+    "start_time": 1632734690.5461335,
+    "learning_rate": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
     "tensorboard_log": null,
     "lr_schedule": {
         ":type:": "<class 'function'>",
+        ":serialized:": "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"
     },
+    "_last_obs": null,
     "_last_episode_starts": {
         ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVdwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYEAAAAAAAAAAEBAQGUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwSFlIwBQ5R0lFKULg=="
     },
     "_last_original_obs": null,
     "_episode_num": 0,
     "use_sde": true,
     "sde_sample_freq": 4,
+    "_current_progress_remaining": -0.02400000000000002,
     "ep_info_buffer": {
         ":type:": "<class 'collections.deque'>",
+        ":serialized:": "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"
     },
     "ep_success_buffer": {
         ":type:": "<class 'collections.deque'>",
         ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
     },
+    "_n_updates": 250,
+    "n_steps": 1024,
+    "gamma": 0.9,
     "gae_lambda": 0.95,
     "ent_coef": 0.0,
     "vf_coef": 0.5,
     "n_epochs": 10,
     "clip_range": {
         ":type:": "<class 'function'>",
+        ":serialized:": "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"
     },
     "clip_range_vf": null,
     "normalize_advantage": true,

ppo-Pendulum-v1/policy.optimizer.pth CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab7bb241ea8bdf9ba2cb0b273908ebea05f4558db996f851afbc36423cd0e12b
 size 78871

 version https://git-lfs.github.com/spec/v1
+oid sha256:71a7025b982c08ed412ef200a303c5f9ec430bd0191e8fbff50ce7270508e279
 size 78871

ppo-Pendulum-v1/policy.pth CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28f38865aa31f8900ad8e354f1fbce0442fd64c47fdc0ae631c082fc5359872f
 size 40254

 version https://git-lfs.github.com/spec/v1
+oid sha256:e1af2047696c1fabfabd154e08c09f753d48dfb5e6209186cf81994d1c86239d
 size 40254

ppo-Pendulum-v1/system_info.txt CHANGED Viewed

@@ -1,7 +1,7 @@
-OS: Linux-5.4.0-109-generic-x86_64-with-debian-bullseye-sid #123-Ubuntu SMP Fri Apr 8 09:10:54 UTC 2022
-Python: 3.7.9
-Stable-Baselines3: 1.5.1a5
 PyTorch: 1.11.0+cpu
 GPU Enabled: False
-Numpy: 1.20.2
 Gym: 0.21.0

+OS: Linux-5.4.0-110-generic-x86_64-with-debian-bullseye-sid #124-Ubuntu SMP Thu Apr 14 19:46:19 UTC 2022
+Python: 3.7.12
+Stable-Baselines3: 1.5.1a6
 PyTorch: 1.11.0+cpu
 GPU Enabled: False
+Numpy: 1.21.6
 Gym: 0.21.0

replay.mp4 CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:76a757969f0b4f5af3cec9fae2326ba90dc3f60a8d064e3b808e4fc1e855eb1c
-size 203450

 version https://git-lfs.github.com/spec/v1
+oid sha256:1287e5a758782bf6750be702e811de23b3181737a983f31b2af6b062ecc5832e
+size 163345

results.json CHANGED Viewed

	@@ -1 +1 @@
1	- {"mean_reward": -~~272~~.~~21298450000006~~, "std_reward": ~~159~~.~~73207117998575~~, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-~~04T11~~:35:55.~~019292~~"}


1	+ {"mean_reward": -230.42289380000003, "std_reward": 142.53933962970044, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-24T22:05:42.793806"}

train_eval_metrics.zip ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:64d86e8a9902ea1331859979b2116525b315535c88e8101d21b1b235f8143864
+size 18474