model with 1M steps

README.md

@@ -10,7 +10,7 @@ model-index:
   results:
   - metrics:
     - type: mean_reward
-      value: 174.53 +/- 27.38
+      value: 277.89 +/- 22.93
       name: mean_reward
     task:
       type: reinforcement-learning

config.json

@@ -1 +1 @@
-{"policy_class": {":type:": "<class 'abc.ABCMeta'>", ":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 0x7fce93877280>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fce93877310>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fce938773a0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fce93877430>", "_build": "<function ActorCriticPolicy._build at 0x7fce938774c0>", "forward": "<function ActorCriticPolicy.forward at 0x7fce93877550>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fce938775e0>", "_predict": "<function ActorCriticPolicy._predict at 0x7fce93877670>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fce93877700>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fce93877790>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fce93877820>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7fce93879100>"}, "verbose": 1, "policy_kwargs": {}, "observation_space": {":type:": "<class 'gym.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "_shape": [8], "low": "[-inf -inf -inf -inf -inf -inf -inf -inf]", "high": "[inf inf inf inf inf inf inf inf]", "bounded_below": "[False False False False False False False False]", "bounded_above": "[False False False False False False False False]", "_np_random": null}, "action_space": {":type:": "<class 'gym.spaces.discrete.Discrete'>", ":serialized:": "gAWVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", "n": 4, "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 16, "num_timesteps": 507904, "_total_timesteps": 500000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1652124571.5557187, "learning_rate": 0.0003, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "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"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.015808000000000044, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 124, "n_steps": 1024, "gamma": 0.999, "gae_lambda": 0.98, "ent_coef": 0.01, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 64, "n_epochs": 4, "clip_range": {":type:": "<class 'function'>", ":serialized:": "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"}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "system_info": {"OS": "Linux-5.11.0-051100-generic-x86_64-with-glibc2.27 #202102142330 SMP Sun Feb 14 23:33:21 UTC 2021", "Python": "3.9.9", "Stable-Baselines3": "1.5.0", "PyTorch": "1.11.0+cu102", "GPU Enabled": "True", "Numpy": "1.22.3", "Gym": "0.21.0"}}
+{"policy_class": {":type:": "<class 'abc.ABCMeta'>", ":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 0x7fce93877280>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fce93877310>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fce938773a0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fce93877430>", "_build": "<function ActorCriticPolicy._build at 0x7fce938774c0>", "forward": "<function ActorCriticPolicy.forward at 0x7fce93877550>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fce938775e0>", "_predict": "<function ActorCriticPolicy._predict at 0x7fce93877670>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fce93877700>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fce93877790>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fce93877820>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7fce93879100>"}, "verbose": 1, "policy_kwargs": {}, "observation_space": {":type:": "<class 'gym.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "_shape": [8], "low": "[-inf -inf -inf -inf -inf -inf -inf -inf]", "high": "[inf inf inf inf inf inf inf inf]", "bounded_below": "[False False False False False False False False]", "bounded_above": "[False False False False False False False False]", "_np_random": null}, "action_space": {":type:": "<class 'gym.spaces.discrete.Discrete'>", ":serialized:": "gAWVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", "n": 4, "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 16, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1652127830.031709, "learning_rate": 0.0003, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "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"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.015808000000000044, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 372, "n_steps": 1024, "gamma": 0.999, "gae_lambda": 0.98, "ent_coef": 0.01, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 64, "n_epochs": 4, "clip_range": {":type:": "<class 'function'>", ":serialized:": "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"}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "system_info": {"OS": "Linux-5.11.0-051100-generic-x86_64-with-glibc2.27 #202102142330 SMP Sun Feb 14 23:33:21 UTC 2021", "Python": "3.9.9", "Stable-Baselines3": "1.5.0", "PyTorch": "1.11.0+cu102", "GPU Enabled": "True", "Numpy": "1.22.3", "Gym": "0.21.0"}}

ppo-LunarLander-v2-1M.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e7040f89172603f23aed8ba65b5de7e991bf7a1f0954bf3f1e07e38e486dbd5
+size 144351

ppo-LunarLander-v2-1M/_stable_baselines3_version

@@ -0,0 +1 @@
+1.5.0

ppo-LunarLander-v2-1M/data

@@ -0,0 +1,94 @@
+{
+    "policy_class": {
+        ":type:": "<class 'abc.ABCMeta'>",
+        ":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 0x7fce93877280>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fce93877310>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fce938773a0>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fce93877430>",
+        "_build": "<function ActorCriticPolicy._build at 0x7fce938774c0>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7fce93877550>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fce938775e0>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7fce93877670>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fce93877700>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fce93877790>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fce93877820>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x7fce93879100>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {},
+    "observation_space": {
+        ":type:": "<class 'gym.spaces.box.Box'>",
+        ":serialized:": "gAWVnwEAAAAAAACMDmd5bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lGgFk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMBl9zaGFwZZRLCIWUjANsb3eUjBJudW1weS5jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWIAAAAAAAAAAAAID/AACA/wAAgP8AAID/AACA/wAAgP8AAID/AACA/5RoCksIhZSMAUOUdJRSlIwEaGlnaJRoEiiWIAAAAAAAAAAAAIB/AACAfwAAgH8AAIB/AACAfwAAgH8AAIB/AACAf5RoCksIhZRoFXSUUpSMDWJvdW5kZWRfYmVsb3eUaBIolggAAAAAAAAAAAAAAAAAAACUaAeMAmIxlImIh5RSlChLA4wBfJROTk5K/////0r/////SwB0lGJLCIWUaBV0lFKUjA1ib3VuZGVkX2Fib3ZllGgSKJYIAAAAAAAAAAAAAAAAAAAAlGghSwiFlGgVdJRSlIwKX25wX3JhbmRvbZROdWIu",
+        "dtype": "float32",
+        "_shape": [
+            8
+        ],
+        "low": "[-inf -inf -inf -inf -inf -inf -inf -inf]",
+        "high": "[inf inf inf inf inf inf inf inf]",
+        "bounded_below": "[False False False False False False False False]",
+        "bounded_above": "[False False False False False False False False]",
+        "_np_random": null
+    },
+    "action_space": {
+        ":type:": "<class 'gym.spaces.discrete.Discrete'>",
+        ":serialized:": "gAWVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu",
+        "n": 4,
+        "_shape": [],
+        "dtype": "int64",
+        "_np_random": null
+    },
+    "n_envs": 16,
+    "num_timesteps": 1015808,
+    "_total_timesteps": 1000000,
+    "_num_timesteps_at_start": 0,
+    "seed": null,
+    "action_noise": null,
+    "start_time": 1652127830.031709,
+    "learning_rate": 0.0003,
+    "tensorboard_log": null,
+    "lr_schedule": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "_last_obs": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "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"
+    },
+    "_last_episode_starts": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="
+    },
+    "_last_original_obs": null,
+    "_episode_num": 0,
+    "use_sde": false,
+    "sde_sample_freq": -1,
+    "_current_progress_remaining": -0.015808000000000044,
+    "ep_info_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "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"
+    },
+    "ep_success_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
+    },
+    "_n_updates": 372,
+    "n_steps": 1024,
+    "gamma": 0.999,
+    "gae_lambda": 0.98,
+    "ent_coef": 0.01,
+    "vf_coef": 0.5,
+    "max_grad_norm": 0.5,
+    "batch_size": 64,
+    "n_epochs": 4,
+    "clip_range": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "clip_range_vf": null,
+    "normalize_advantage": true,
+    "target_kl": null
+}

ppo-LunarLander-v2-1M/policy.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42afba191912f202033e1d6f1647e53b8d38713186d6986fef9109cf6ea84b3a
+size 84893

ppo-LunarLander-v2-1M/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36d11b137c091cfd1daefa2bed7dcef3d25c7a1de39ad1de739201d093122b11
+size 43201

ppo-LunarLander-v2-1M/pytorch_variables.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d030ad8db708280fcae77d87e973102039acd23a11bdecc3db8eb6c0ac940ee1
+size 431

ppo-LunarLander-v2-1M/system_info.txt

@@ -0,0 +1,7 @@
+OS: Linux-5.11.0-051100-generic-x86_64-with-glibc2.27 #202102142330 SMP Sun Feb 14 23:33:21 UTC 2021
+Python: 3.9.9
+Stable-Baselines3: 1.5.0
+PyTorch: 1.11.0+cu102
+GPU Enabled: True
+Numpy: 1.22.3
+Gym: 0.21.0

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:458dd97c8443e8379bd617836c812477feefdf89458d91ae749c606d3d69dda5
-size 260106
+oid sha256:687338214645914750598c0b1c4747275e7bc1cf3aeba7c2c87daea24865a92f
+size 193830

results.json

@@ -1 +1 @@
-{"mean_reward": 174.53302082216229, "std_reward": 27.379202916577217, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-09T22:17:43.852869"}
+{"mean_reward": 277.8878432480518, "std_reward": 22.933267602070053, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-09T22:41:09.288170"}