Initial commit

README.md

@@ -16,7 +16,7 @@ model-index:
       type: PandaReachDense-v3
     metrics:
     - type: mean_reward
-      value: -8.24 +/- 2.80
+      value: -0.24 +/- 0.19
       name: mean_reward
       verified: false
 ---

a2c-PandaReachDense-v3.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a6b41f2866dfdb93da24dba2bea005c83bc5046003a2a05282fc5b1a06bcb80
-size 55300
+oid sha256:7303181912e150b79e990d4c28c3bf7cfa749390eddcec32c479ca4dcbfe4b1e
+size 106952

a2c-PandaReachDense-v3/data

@@ -4,9 +4,9 @@
         ":serialized:": "gAWVRQAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMG011bHRpSW5wdXRBY3RvckNyaXRpY1BvbGljeZSTlC4=",
         "__module__": "stable_baselines3.common.policies",
         "__doc__": "\n    MultiInputActorClass 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 (Tuple)\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 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: Uses the CombinedExtractor\n    :param features_extractor_kwargs: Keyword arguments\n        to pass to the features extractor.\n    :param share_features_extractor: If True, the features extractor is shared between the policy and value networks.\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 MultiInputActorCriticPolicy.__init__ at 0x7d2824926a70>",
+        "__init__": "<function MultiInputActorCriticPolicy.__init__ at 0x7bcc9e8d2b90>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x7d282492d500>"
+        "_abc_impl": "<_abc._abc_data object at 0x7bcc9e8ce980>"
     },
     "verbose": 1,
     "policy_kwargs": {
@@ -19,25 +19,46 @@
             "weight_decay": 0
         }
     },
-    "num_timesteps": 0,
-    "_total_timesteps": 0,
+    "num_timesteps": 1000000,
+    "_total_timesteps": 1000000,
     "_num_timesteps_at_start": 0,
     "seed": null,
     "action_noise": null,
-    "start_time": 0.0,
+    "start_time": 1697569673121478178,
     "learning_rate": 0.0007,
     "tensorboard_log": null,
-    "_last_obs": null,
-    "_last_episode_starts": null,
-    "_last_original_obs": null,
+    "_last_obs": {
+        ":type:": "<class 'collections.OrderedDict'>",
+        ":serialized:": "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",
+        "achieved_goal": "[[-9.3807958e-02 -4.1968563e-01 -1.9861451e-01]\n [ 1.0870047e+00  2.1625884e+00  7.9280925e-01]\n [-9.2611915e-01  1.5629762e+00 -1.3532977e-03]\n [-9.6905828e-02  3.8224092e-01 -1.8572168e-01]]",
+        "desired_goal": "[[-1.4347371  -0.889495   -1.2551153 ]\n [ 1.5030643   1.5350993   1.6444306 ]\n [ 1.0331436   1.5978372   1.6258519 ]\n [-1.4991413   0.05165337 -1.2369933 ]]",
+        "observation": "[[-9.3807958e-02 -4.1968563e-01 -1.9861451e-01 -1.7586955e+00\n  -1.6993774e+00 -1.3765476e+00]\n [ 1.0870047e+00  2.1625884e+00  7.9280925e-01  1.0513716e+00\n   1.3638124e-01 -9.5775288e-01]\n [-9.2611915e-01  1.5629762e+00 -1.3532977e-03  2.3715768e+00\n  -4.9752149e-01  8.8873380e-01]\n [-9.6905828e-02  3.8224092e-01 -1.8572168e-01 -1.7875109e+00\n   8.6398834e-01 -1.3793590e+00]]"
+    },
+    "_last_episode_starts": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVdwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYEAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwSFlIwBQ5R0lFKULg=="
+    },
+    "_last_original_obs": {
+        ":type:": "<class 'collections.OrderedDict'>",
+        ":serialized:": "gAWVuwEAAAAAAACMC2NvbGxlY3Rpb25zlIwLT3JkZXJlZERpY3SUk5QpUpQojA1hY2hpZXZlZF9nb2FslIwSbnVtcHkuY29yZS5udW1lcmljlIwLX2Zyb21idWZmZXKUk5QoljAAAAAAAAAA6nIdPRlsGqxDI0o+6nIdPRlsGqxDI0o+6nIdPRlsGqxDI0o+6nIdPRlsGqxDI0o+lIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksESwOGlIwBQ5R0lFKUjAxkZXNpcmVkX2dvYWyUaAcoljAAAAAAAAAA1JrdPcCMyT2xV4U+GCAPvhqdkD0zDDU++nXPvX2/Fr7ODgE+86cDPhYc/T32akU+lGgOSwRLA4aUaBJ0lFKUjAtvYnNlcnZhdGlvbpRoByiWYAAAAAAAAADqch09GWwarEMjSj4AAAAAAAAAgAAAAADqch09GWwarEMjSj4AAAAAAAAAgAAAAADqch09GWwarEMjSj4AAAAAAAAAgAAAAADqch09GWwarEMjSj4AAAAAAAAAgAAAAACUaA5LBEsGhpRoEnSUUpR1Lg==",
+        "achieved_goal": "[[ 3.8439669e-02 -2.1944723e-12  1.9740014e-01]\n [ 3.8439669e-02 -2.1944723e-12  1.9740014e-01]\n [ 3.8439669e-02 -2.1944723e-12  1.9740014e-01]\n [ 3.8439669e-02 -2.1944723e-12  1.9740014e-01]]",
+        "desired_goal": "[[ 0.10820547  0.09841299  0.26043466]\n [-0.13977087  0.07061215  0.17680435]\n [-0.10129924 -0.14721484  0.12603304]\n [ 0.12857036  0.12358873  0.19279084]]",
+        "observation": "[[ 3.8439669e-02 -2.1944723e-12  1.9740014e-01  0.0000000e+00\n  -0.0000000e+00  0.0000000e+00]\n [ 3.8439669e-02 -2.1944723e-12  1.9740014e-01  0.0000000e+00\n  -0.0000000e+00  0.0000000e+00]\n [ 3.8439669e-02 -2.1944723e-12  1.9740014e-01  0.0000000e+00\n  -0.0000000e+00  0.0000000e+00]\n [ 3.8439669e-02 -2.1944723e-12  1.9740014e-01  0.0000000e+00\n  -0.0000000e+00  0.0000000e+00]]"
+    },
     "_episode_num": 0,
     "use_sde": false,
     "sde_sample_freq": -1,
-    "_current_progress_remaining": 1.0,
+    "_current_progress_remaining": 0.0,
     "_stats_window_size": 100,
-    "ep_info_buffer": null,
-    "ep_success_buffer": null,
-    "_n_updates": 0,
+    "ep_info_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "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"
+    },
+    "ep_success_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
+    },
+    "_n_updates": 50000,
     "n_steps": 5,
     "gamma": 0.99,
     "gae_lambda": 1.0,

a2c-PandaReachDense-v3/policy.optimizer.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c7b2e55b9d2524652dd7a7dba0a98d761f3ba58839455894af3d91cd644015c
-size 687
+oid sha256:d2a0e9a3511373fa9d8d8010087400c5ad279c0c737cb5bb3c3cce05521dd120
+size 44734

a2c-PandaReachDense-v3/policy.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26ab1940106460309a158cd3951c4fa2b74aa159cbacacd7c2d5cb0a734859f4
+oid sha256:25b94a2c575f2e9f426b672da8b20edba76d9ade9acefe96eadb93461315d488
 size 46014

config.json

@@ -1 +1 @@
-{"policy_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gAWVRQAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMG011bHRpSW5wdXRBY3RvckNyaXRpY1BvbGljeZSTlC4=", "__module__": "stable_baselines3.common.policies", "__doc__": "\n    MultiInputActorClass 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 (Tuple)\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 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: Uses the CombinedExtractor\n    :param features_extractor_kwargs: Keyword arguments\n        to pass to the features extractor.\n    :param share_features_extractor: If True, the features extractor is shared between the policy and value networks.\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 MultiInputActorCriticPolicy.__init__ at 0x7d2824926a70>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7d282492d500>"}, "verbose": 1, "policy_kwargs": {":type:": "<class 'dict'>", ":serialized:": "gAWVgQAAAAAAAAB9lCiMD29wdGltaXplcl9jbGFzc5SME3RvcmNoLm9wdGltLnJtc3Byb3CUjAdSTVNwcm9wlJOUjBBvcHRpbWl6ZXJfa3dhcmdzlH2UKIwFYWxwaGGURz/vrhR64UeujANlcHOURz7k+LWI42jxjAx3ZWlnaHRfZGVjYXmUSwB1dS4=", "optimizer_class": "<class 'torch.optim.rmsprop.RMSprop'>", "optimizer_kwargs": {"alpha": 0.99, "eps": 1e-05, "weight_decay": 0}}, "num_timesteps": 0, "_total_timesteps": 0, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 0.0, "learning_rate": 0.0007, "tensorboard_log": null, "_last_obs": null, "_last_episode_starts": null, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": 1.0, "_stats_window_size": 100, "ep_info_buffer": null, "ep_success_buffer": null, "_n_updates": 0, "n_steps": 5, "gamma": 0.99, "gae_lambda": 1.0, "ent_coef": 0.0, "vf_coef": 0.5, "max_grad_norm": 0.5, "normalize_advantage": false, "observation_space": {":type:": "<class 'gymnasium.spaces.dict.Dict'>", ":serialized:": "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", "spaces": "OrderedDict([('achieved_goal', Box(-10.0, 10.0, (3,), float32)), ('desired_goal', Box(-10.0, 10.0, (3,), float32)), ('observation', Box(-10.0, 10.0, (6,), float32))])", "_shape": null, "dtype": null, "_np_random": null}, "action_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "bounded_below": "[ True  True  True]", "bounded_above": "[ True  True  True]", "_shape": [3], "low": "[-1. -1. -1.]", "high": "[1. 1. 1.]", "low_repr": "-1.0", "high_repr": "1.0", "_np_random": null}, "n_envs": 4, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "system_info": {"OS": "Linux-5.15.120+-x86_64-with-glibc2.35 # 1 SMP Wed Aug 30 11:19:59 UTC 2023", "Python": "3.10.12", "Stable-Baselines3": "2.1.0", "PyTorch": "2.0.1+cu118", "GPU Enabled": "True", "Numpy": "1.23.5", "Cloudpickle": "2.2.1", "Gymnasium": "0.29.1", "OpenAI Gym": "0.25.2"}}
+{"policy_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gAWVRQAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMG011bHRpSW5wdXRBY3RvckNyaXRpY1BvbGljeZSTlC4=", "__module__": "stable_baselines3.common.policies", "__doc__": "\n    MultiInputActorClass 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 (Tuple)\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 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: Uses the CombinedExtractor\n    :param features_extractor_kwargs: Keyword arguments\n        to pass to the features extractor.\n    :param share_features_extractor: If True, the features extractor is shared between the policy and value networks.\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 MultiInputActorCriticPolicy.__init__ at 0x7bcc9e8d2b90>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7bcc9e8ce980>"}, "verbose": 1, "policy_kwargs": {":type:": "<class 'dict'>", ":serialized:": "gAWVgQAAAAAAAAB9lCiMD29wdGltaXplcl9jbGFzc5SME3RvcmNoLm9wdGltLnJtc3Byb3CUjAdSTVNwcm9wlJOUjBBvcHRpbWl6ZXJfa3dhcmdzlH2UKIwFYWxwaGGURz/vrhR64UeujANlcHOURz7k+LWI42jxjAx3ZWlnaHRfZGVjYXmUSwB1dS4=", "optimizer_class": "<class 'torch.optim.rmsprop.RMSprop'>", "optimizer_kwargs": {"alpha": 0.99, "eps": 1e-05, "weight_decay": 0}}, "num_timesteps": 1000000, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1697569673121478178, "learning_rate": 0.0007, "tensorboard_log": null, "_last_obs": {":type:": "<class 'collections.OrderedDict'>", ":serialized:": "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", "achieved_goal": "[[-9.3807958e-02 -4.1968563e-01 -1.9861451e-01]\n [ 1.0870047e+00  2.1625884e+00  7.9280925e-01]\n [-9.2611915e-01  1.5629762e+00 -1.3532977e-03]\n [-9.6905828e-02  3.8224092e-01 -1.8572168e-01]]", "desired_goal": "[[-1.4347371  -0.889495   -1.2551153 ]\n [ 1.5030643   1.5350993   1.6444306 ]\n [ 1.0331436   1.5978372   1.6258519 ]\n [-1.4991413   0.05165337 -1.2369933 ]]", "observation": "[[-9.3807958e-02 -4.1968563e-01 -1.9861451e-01 -1.7586955e+00\n  -1.6993774e+00 -1.3765476e+00]\n [ 1.0870047e+00  2.1625884e+00  7.9280925e-01  1.0513716e+00\n   1.3638124e-01 -9.5775288e-01]\n [-9.2611915e-01  1.5629762e+00 -1.3532977e-03  2.3715768e+00\n  -4.9752149e-01  8.8873380e-01]\n [-9.6905828e-02  3.8224092e-01 -1.8572168e-01 -1.7875109e+00\n   8.6398834e-01 -1.3793590e+00]]"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYEAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwSFlIwBQ5R0lFKULg=="}, "_last_original_obs": {":type:": "<class 'collections.OrderedDict'>", ":serialized:": "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", "achieved_goal": "[[ 3.8439669e-02 -2.1944723e-12  1.9740014e-01]\n [ 3.8439669e-02 -2.1944723e-12  1.9740014e-01]\n [ 3.8439669e-02 -2.1944723e-12  1.9740014e-01]\n [ 3.8439669e-02 -2.1944723e-12  1.9740014e-01]]", "desired_goal": "[[ 0.10820547  0.09841299  0.26043466]\n [-0.13977087  0.07061215  0.17680435]\n [-0.10129924 -0.14721484  0.12603304]\n [ 0.12857036  0.12358873  0.19279084]]", "observation": "[[ 3.8439669e-02 -2.1944723e-12  1.9740014e-01  0.0000000e+00\n  -0.0000000e+00  0.0000000e+00]\n [ 3.8439669e-02 -2.1944723e-12  1.9740014e-01  0.0000000e+00\n  -0.0000000e+00  0.0000000e+00]\n [ 3.8439669e-02 -2.1944723e-12  1.9740014e-01  0.0000000e+00\n  -0.0000000e+00  0.0000000e+00]\n [ 3.8439669e-02 -2.1944723e-12  1.9740014e-01  0.0000000e+00\n  -0.0000000e+00  0.0000000e+00]]"}, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": 0.0, "_stats_window_size": 100, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 50000, "n_steps": 5, "gamma": 0.99, "gae_lambda": 1.0, "ent_coef": 0.0, "vf_coef": 0.5, "max_grad_norm": 0.5, "normalize_advantage": false, "observation_space": {":type:": "<class 'gymnasium.spaces.dict.Dict'>", ":serialized:": "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", "spaces": "OrderedDict([('achieved_goal', Box(-10.0, 10.0, (3,), float32)), ('desired_goal', Box(-10.0, 10.0, (3,), float32)), ('observation', Box(-10.0, 10.0, (6,), float32))])", "_shape": null, "dtype": null, "_np_random": null}, "action_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "bounded_below": "[ True  True  True]", "bounded_above": "[ True  True  True]", "_shape": [3], "low": "[-1. -1. -1.]", "high": "[1. 1. 1.]", "low_repr": "-1.0", "high_repr": "1.0", "_np_random": null}, "n_envs": 4, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "system_info": {"OS": "Linux-5.15.120+-x86_64-with-glibc2.35 # 1 SMP Wed Aug 30 11:19:59 UTC 2023", "Python": "3.10.12", "Stable-Baselines3": "2.1.0", "PyTorch": "2.0.1+cu118", "GPU Enabled": "True", "Numpy": "1.23.5", "Cloudpickle": "2.2.1", "Gymnasium": "0.29.1", "OpenAI Gym": "0.25.2"}}

results.json

@@ -1 +1 @@
-{"mean_reward": -8.244367230683565, "std_reward": 2.803799874988558, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-10-08T22:21:19.234027"}
+{"mean_reward": -0.2357559097930789, "std_reward": 0.1860218707284692, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-10-17T19:52:53.230195"}

vec_normalize.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a635a993cb9273b21abd3675c11238ba7eafcc5de136d76b139134eb7c8c4783
+oid sha256:b64b8e211adde73bf5ac59a5aff301baeaa0ae3f305d2be2c9b29c5bc1af066a
 size 2623