diff --git "a/slurmm1.0-7382.out" "b/slurmm1.0-7382.out" new file mode 100644--- /dev/null +++ "b/slurmm1.0-7382.out" @@ -0,0 +1,4747 @@ +Lmod has detected the following error: The following module(s) are unknown: +"buildenv-gcccuda/12.1.1-gcc12.3.0" + +Please check the spelling or version number. Also try "module spider ..." +It is also possible your cache file is out-of-date; it may help to try: + $ module --ignore_cache load "buildenv-gcccuda/12.1.1-gcc12.3.0" + +Also make sure that all modulefiles written in TCL start with the string +#%Module + + + +/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/defaults_list.py:251: UserWarning: In 'training': Defaults list is missing `_self_`. See https://hydra.cc/docs/1.2/upgrades/1.0_to_1.1/default_composition_order for more information + warnings.warn(msg, UserWarning) +/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/defaults_list.py:251: UserWarning: In 'training': Defaults list is missing `_self_`. See https://hydra.cc/docs/1.2/upgrades/1.0_to_1.1/default_composition_order for more information + warnings.warn(msg, UserWarning) +/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/defaults_list.py:251: UserWarning: In 'training': Defaults list is missing `_self_`. See https://hydra.cc/docs/1.2/upgrades/1.0_to_1.1/default_composition_order for more information + warnings.warn(msg, UserWarning) +/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/defaults_list.py:251: UserWarning: In 'training': Defaults list is missing `_self_`. See https://hydra.cc/docs/1.2/upgrades/1.0_to_1.1/default_composition_order for more information + warnings.warn(msg, UserWarning) +/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/defaults_list.py:251: UserWarning: In 'training': Defaults list is missing `_self_`. See https://hydra.cc/docs/1.2/upgrades/1.0_to_1.1/default_composition_order for more information + warnings.warn(msg, UserWarning) +/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/defaults_list.py:251: UserWarning: In 'training': Defaults list is missing `_self_`. See https://hydra.cc/docs/1.2/upgrades/1.0_to_1.1/default_composition_order for more information + warnings.warn(msg, UserWarning) +/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/defaults_list.py:251: UserWarning: In 'training': Defaults list is missing `_self_`. See https://hydra.cc/docs/1.2/upgrades/1.0_to_1.1/default_composition_order for more information + warnings.warn(msg, UserWarning) +/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/defaults_list.py:251: UserWarning: In 'training': Defaults list is missing `_self_`. See https://hydra.cc/docs/1.2/upgrades/1.0_to_1.1/default_composition_order for more information + warnings.warn(msg, UserWarning) +/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/fabric/__init__.py:40: pkg_resources is deprecated as an API. See https://setuptools.pypa.io/en/latest/pkg_resources.html. The pkg_resources package is slated for removal as early as 2025-11-30. Refrain from using this package or pin to Setuptools<81. +/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/fabric/__init__.py:40: pkg_resources is deprecated as an API. See https://setuptools.pypa.io/en/latest/pkg_resources.html. The pkg_resources package is slated for removal as early as 2025-11-30. Refrain from using this package or pin to Setuptools<81. +/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/fabric/__init__.py:40: pkg_resources is deprecated as an API. See https://setuptools.pypa.io/en/latest/pkg_resources.html. The pkg_resources package is slated for removal as early as 2025-11-30. Refrain from using this package or pin to Setuptools<81. +/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/fabric/__init__.py:40: pkg_resources is deprecated as an API. See https://setuptools.pypa.io/en/latest/pkg_resources.html. The pkg_resources package is slated for removal as early as 2025-11-30. Refrain from using this package or pin to Setuptools<81. +/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/fabric/__init__.py:40: pkg_resources is deprecated as an API. See https://setuptools.pypa.io/en/latest/pkg_resources.html. The pkg_resources package is slated for removal as early as 2025-11-30. Refrain from using this package or pin to Setuptools<81. +/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/fabric/__init__.py:40: pkg_resources is deprecated as an API. See https://setuptools.pypa.io/en/latest/pkg_resources.html. The pkg_resources package is slated for removal as early as 2025-11-30. Refrain from using this package or pin to Setuptools<81. +/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/fabric/__init__.py:40: pkg_resources is deprecated as an API. See https://setuptools.pypa.io/en/latest/pkg_resources.html. The pkg_resources package is slated for removal as early as 2025-11-30. Refrain from using this package or pin to Setuptools<81. +/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/fabric/__init__.py:40: pkg_resources is deprecated as an API. See https://setuptools.pypa.io/en/latest/pkg_resources.html. The pkg_resources package is slated for removal as early as 2025-11-30. Refrain from using this package or pin to Setuptools<81. +/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torchvision/models/_utils.py:208: UserWarning: The parameter 'pretrained' is deprecated since 0.13 and may be removed in the future, please use 'weights' instead. + warnings.warn( +/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or `None` for 'weights' are deprecated since 0.13 and may be removed in the future. The current behavior is equivalent to passing `weights=AlexNet_Weights.IMAGENET1K_V1`. You can also use `weights=AlexNet_Weights.DEFAULT` to get the most up-to-date weights. + warnings.warn(msg) +/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torchvision/models/_utils.py:208: UserWarning: The parameter 'pretrained' is deprecated since 0.13 and may be removed in the future, please use 'weights' instead. + warnings.warn( +/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or `None` for 'weights' are deprecated since 0.13 and may be removed in the future. The current behavior is equivalent to passing `weights=AlexNet_Weights.IMAGENET1K_V1`. You can also use `weights=AlexNet_Weights.DEFAULT` to get the most up-to-date weights. + warnings.warn(msg) +/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lpips/lpips.py:107: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature. + self.load_state_dict(torch.load(model_path, map_location='cpu'), strict=False) +/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lpips/lpips.py:107: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature. + self.load_state_dict(torch.load(model_path, map_location='cpu'), strict=False) +/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torchvision/models/_utils.py:208: UserWarning: The parameter 'pretrained' is deprecated since 0.13 and may be removed in the future, please use 'weights' instead. + warnings.warn( +/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or `None` for 'weights' are deprecated since 0.13 and may be removed in the future. The current behavior is equivalent to passing `weights=AlexNet_Weights.IMAGENET1K_V1`. You can also use `weights=AlexNet_Weights.DEFAULT` to get the most up-to-date weights. + warnings.warn(msg) +/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torchvision/models/_utils.py:208: UserWarning: The parameter 'pretrained' is deprecated since 0.13 and may be removed in the future, please use 'weights' instead. + warnings.warn( +/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or `None` for 'weights' are deprecated since 0.13 and may be removed in the future. The current behavior is equivalent to passing `weights=AlexNet_Weights.IMAGENET1K_V1`. You can also use `weights=AlexNet_Weights.DEFAULT` to get the most up-to-date weights. + warnings.warn(msg) +/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torchvision/models/_utils.py:208: UserWarning: The parameter 'pretrained' is deprecated since 0.13 and may be removed in the future, please use 'weights' instead. + warnings.warn( +/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or `None` for 'weights' are deprecated since 0.13 and may be removed in the future. The current behavior is equivalent to passing `weights=AlexNet_Weights.IMAGENET1K_V1`. You can also use `weights=AlexNet_Weights.DEFAULT` to get the most up-to-date weights. + warnings.warn(msg) +/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torchvision/models/_utils.py:208: UserWarning: The parameter 'pretrained' is deprecated since 0.13 and may be removed in the future, please use 'weights' instead. + warnings.warn( +/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or `None` for 'weights' are deprecated since 0.13 and may be removed in the future. The current behavior is equivalent to passing `weights=AlexNet_Weights.IMAGENET1K_V1`. You can also use `weights=AlexNet_Weights.DEFAULT` to get the most up-to-date weights. + warnings.warn(msg) +/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lpips/lpips.py:107: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature. + self.load_state_dict(torch.load(model_path, map_location='cpu'), strict=False) +/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torchvision/models/_utils.py:208: UserWarning: The parameter 'pretrained' is deprecated since 0.13 and may be removed in the future, please use 'weights' instead. + warnings.warn( +/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or `None` for 'weights' are deprecated since 0.13 and may be removed in the future. The current behavior is equivalent to passing `weights=AlexNet_Weights.IMAGENET1K_V1`. You can also use `weights=AlexNet_Weights.DEFAULT` to get the most up-to-date weights. + warnings.warn(msg) +/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lpips/lpips.py:107: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature. + self.load_state_dict(torch.load(model_path, map_location='cpu'), strict=False) +/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lpips/lpips.py:107: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature. + self.load_state_dict(torch.load(model_path, map_location='cpu'), strict=False) +/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lpips/lpips.py:107: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature. + self.load_state_dict(torch.load(model_path, map_location='cpu'), strict=False) +/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torchvision/models/_utils.py:208: UserWarning: The parameter 'pretrained' is deprecated since 0.13 and may be removed in the future, please use 'weights' instead. + warnings.warn( +/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or `None` for 'weights' are deprecated since 0.13 and may be removed in the future. The current behavior is equivalent to passing `weights=AlexNet_Weights.IMAGENET1K_V1`. You can also use `weights=AlexNet_Weights.DEFAULT` to get the most up-to-date weights. + warnings.warn(msg) +/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lpips/lpips.py:107: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature. + self.load_state_dict(torch.load(model_path, map_location='cpu'), strict=False) +/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lpips/lpips.py:107: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature. + self.load_state_dict(torch.load(model_path, map_location='cpu'), strict=False) +/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/plugins/precision/amp.py:54: `torch.cuda.amp.GradScaler(args...)` is deprecated. Please use `torch.amp.GradScaler('cuda', args...)` instead. +/proj/cvl/users/x_fahkh2/WorldMem_Repro/experiments/exp_base.py:74: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature. + ckpt = torch.load(checkpoint_path, map_location=torch.device('cpu')) +/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/plugins/precision/amp.py:54: `torch.cuda.amp.GradScaler(args...)` is deprecated. Please use `torch.amp.GradScaler('cuda', args...)` instead. +/proj/cvl/users/x_fahkh2/WorldMem_Repro/experiments/exp_base.py:74: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature. + ckpt = torch.load(checkpoint_path, map_location=torch.device('cpu')) +/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/plugins/precision/amp.py:54: `torch.cuda.amp.GradScaler(args...)` is deprecated. Please use `torch.amp.GradScaler('cuda', args...)` instead. +/proj/cvl/users/x_fahkh2/WorldMem_Repro/experiments/exp_base.py:74: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature. + ckpt = torch.load(checkpoint_path, map_location=torch.device('cpu')) +/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/plugins/precision/amp.py:54: `torch.cuda.amp.GradScaler(args...)` is deprecated. Please use `torch.amp.GradScaler('cuda', args...)` instead. +/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/plugins/precision/amp.py:54: `torch.cuda.amp.GradScaler(args...)` is deprecated. Please use `torch.amp.GradScaler('cuda', args...)` instead. +/proj/cvl/users/x_fahkh2/WorldMem_Repro/experiments/exp_base.py:74: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature. + ckpt = torch.load(checkpoint_path, map_location=torch.device('cpu')) +/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/plugins/precision/amp.py:54: `torch.cuda.amp.GradScaler(args...)` is deprecated. Please use `torch.amp.GradScaler('cuda', args...)` instead. +Outputs will be saved to: /proj/cvl/users/x_fahkh2/WorldMem_Repro/checkpoints/bimamba_stage_b +Will load checkpoint from /proj/cvl/users/x_fahkh2/WorldMem_Repro/checkpoints/bimamba_stage_a_128/checkpoints/epoch0_step2000.ckpt +Executing task: training out of ['training'] +[2026-03-11 19:10:19,804][pytorch_lightning.utilities.rank_zero][INFO] - Using 16bit Automatic Mixed Precision (AMP) +/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/plugins/precision/amp.py:54: `torch.cuda.amp.GradScaler(args...)` is deprecated. Please use `torch.amp.GradScaler('cuda', args...)` instead. +/proj/cvl/users/x_fahkh2/WorldMem_Repro/experiments/exp_base.py:74: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature. + ckpt = torch.load(checkpoint_path, map_location=torch.device('cpu')) +/proj/cvl/users/x_fahkh2/WorldMem_Repro/experiments/exp_base.py:74: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature. + ckpt = torch.load(checkpoint_path, map_location=torch.device('cpu')) +[2026-03-11 19:10:19,926][pytorch_lightning.utilities.rank_zero][INFO] - GPU available: True (cuda), used: True +[2026-03-11 19:10:19,926][pytorch_lightning.utilities.rank_zero][INFO] - TPU available: False, using: 0 TPU cores +[2026-03-11 19:10:19,926][pytorch_lightning.utilities.rank_zero][INFO] - IPU available: False, using: 0 IPUs +[2026-03-11 19:10:19,926][pytorch_lightning.utilities.rank_zero][INFO] - HPU available: False, using: 0 HPUs +[2026-03-11 19:10:19,927][pytorch_lightning.utilities.rank_zero][INFO] - `Trainer(limit_val_batches=1)` was configured so 1 batch will be used. +/proj/cvl/users/x_fahkh2/WorldMem_Repro/experiments/exp_base.py:74: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature. + ckpt = torch.load(checkpoint_path, map_location=torch.device('cpu')) +/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/plugins/precision/amp.py:54: `torch.cuda.amp.GradScaler(args...)` is deprecated. Please use `torch.amp.GradScaler('cuda', args...)` instead. +/proj/cvl/users/x_fahkh2/WorldMem_Repro/experiments/exp_base.py:74: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature. + ckpt = torch.load(checkpoint_path, map_location=torch.device('cpu')) +[2026-03-11 19:10:21,692][pytorch_lightning.utilities.rank_zero][INFO] - Model weights loaded. +INFO: Initializing distributed: GLOBAL_RANK: 4, MEMBER: 5/8 +Outputs will be saved to: /proj/cvl/users/x_fahkh2/WorldMem_Repro/checkpoints/bimamba_stage_b +Will load checkpoint from /proj/cvl/users/x_fahkh2/WorldMem_Repro/checkpoints/bimamba_stage_a_128/checkpoints/epoch0_step2000.ckpt +Executing task: training out of ['training'] +[2026-03-11 19:10:27,411][lightning.fabric.utilities.distributed][INFO] - Initializing distributed: GLOBAL_RANK: 4, MEMBER: 5/8 +INFO: Initializing distributed: GLOBAL_RANK: 3, MEMBER: 4/8 +Outputs will be saved to: /proj/cvl/users/x_fahkh2/WorldMem_Repro/checkpoints/bimamba_stage_b +Will load checkpoint from /proj/cvl/users/x_fahkh2/WorldMem_Repro/checkpoints/bimamba_stage_a_128/checkpoints/epoch0_step2000.ckpt +Executing task: training out of ['training'] +[2026-03-11 19:10:27,563][lightning.fabric.utilities.distributed][INFO] - Initializing distributed: GLOBAL_RANK: 3, MEMBER: 4/8 +Outputs will be saved to: /proj/cvl/users/x_fahkh2/WorldMem_Repro/checkpoints/bimamba_stage_b +Will load checkpoint from /proj/cvl/users/x_fahkh2/WorldMem_Repro/checkpoints/bimamba_stage_a_128/checkpoints/epoch0_step2000.ckpt +Executing task: training out of ['training'] +[2026-03-11 19:10:27,647][lightning.fabric.utilities.distributed][INFO] - Initializing distributed: GLOBAL_RANK: 6, MEMBER: 7/8 +INFO: Initializing distributed: GLOBAL_RANK: 6, MEMBER: 7/8 +INFO: Initializing distributed: GLOBAL_RANK: 5, MEMBER: 6/8 +Outputs will be saved to: /proj/cvl/users/x_fahkh2/WorldMem_Repro/checkpoints/bimamba_stage_b +Will load checkpoint from /proj/cvl/users/x_fahkh2/WorldMem_Repro/checkpoints/bimamba_stage_a_128/checkpoints/epoch0_step2000.ckpt +Executing task: training out of ['training'] +[2026-03-11 19:10:27,760][lightning.fabric.utilities.distributed][INFO] - Initializing distributed: GLOBAL_RANK: 5, MEMBER: 6/8 +[2026-03-11 19:10:27,891][lightning.fabric.utilities.distributed][INFO] - Initializing distributed: GLOBAL_RANK: 0, MEMBER: 1/8 +INFO: Initializing distributed: GLOBAL_RANK: 0, MEMBER: 1/8 +INFO: Initializing distributed: GLOBAL_RANK: 1, MEMBER: 2/8 +Outputs will be saved to: /proj/cvl/users/x_fahkh2/WorldMem_Repro/checkpoints/bimamba_stage_b +Will load checkpoint from /proj/cvl/users/x_fahkh2/WorldMem_Repro/checkpoints/bimamba_stage_a_128/checkpoints/epoch0_step2000.ckpt +Executing task: training out of ['training'] +[2026-03-11 19:10:28,117][lightning.fabric.utilities.distributed][INFO] - Initializing distributed: GLOBAL_RANK: 1, MEMBER: 2/8 +Outputs will be saved to: /proj/cvl/users/x_fahkh2/WorldMem_Repro/checkpoints/bimamba_stage_b +Will load checkpoint from /proj/cvl/users/x_fahkh2/WorldMem_Repro/checkpoints/bimamba_stage_a_128/checkpoints/epoch0_step2000.ckpt +Executing task: training out of ['training'] +[2026-03-11 19:10:28,205][lightning.fabric.utilities.distributed][INFO] - Initializing distributed: GLOBAL_RANK: 7, MEMBER: 8/8 +INFO: Initializing distributed: GLOBAL_RANK: 7, MEMBER: 8/8 +INFO: Initializing distributed: GLOBAL_RANK: 2, MEMBER: 3/8 +Outputs will be saved to: /proj/cvl/users/x_fahkh2/WorldMem_Repro/checkpoints/bimamba_stage_b +Will load checkpoint from /proj/cvl/users/x_fahkh2/WorldMem_Repro/checkpoints/bimamba_stage_a_128/checkpoints/epoch0_step2000.ckpt +Executing task: training out of ['training'] +[2026-03-11 19:10:28,486][lightning.fabric.utilities.distributed][INFO] - Initializing distributed: GLOBAL_RANK: 2, MEMBER: 3/8 +[2026-03-11 19:10:32,855][pytorch_lightning.utilities.rank_zero][INFO] - ---------------------------------------------------------------------------------------------------- +distributed_backend=nccl +All distributed processes registered. Starting with 8 processes +---------------------------------------------------------------------------------------------------- + +wandb: WARNING `resume` will be ignored since W&B syncing is set to `offline`. Starting a new run with run id stage_b_offline. +wandb: Tracking run with wandb version 0.17.9 +wandb: W&B syncing is set to `offline` in this directory. +wandb: Run `wandb online` or set WANDB_MODE=online to enable cloud syncing. +INFO: LOCAL_RANK: 0 - CUDA_VISIBLE_DEVICES: [0,1,2,3,4,5,6,7] +[2026-03-11 19:10:47,256][lightning.pytorch.accelerators.cuda][INFO] - LOCAL_RANK: 0 - CUDA_VISIBLE_DEVICES: [0,1,2,3,4,5,6,7] +INFO: LOCAL_RANK: 1 - CUDA_VISIBLE_DEVICES: [0,1,2,3,4,5,6,7] +INFO: LOCAL_RANK: 3 - CUDA_VISIBLE_DEVICES: [0,1,2,3,4,5,6,7] +INFO: LOCAL_RANK: 4 - CUDA_VISIBLE_DEVICES: [0,1,2,3,4,5,6,7] +INFO: LOCAL_RANK: 5 - CUDA_VISIBLE_DEVICES: [0,1,2,3,4,5,6,7] +INFO: LOCAL_RANK: 6 - CUDA_VISIBLE_DEVICES: [0,1,2,3,4,5,6,7] +INFO: LOCAL_RANK: 7 - CUDA_VISIBLE_DEVICES: [0,1,2,3,4,5,6,7] +[2026-03-11 19:10:47,256][lightning.pytorch.accelerators.cuda][INFO] - LOCAL_RANK: 1 - CUDA_VISIBLE_DEVICES: [0,1,2,3,4,5,6,7] +INFO: LOCAL_RANK: 2 - CUDA_VISIBLE_DEVICES: [0,1,2,3,4,5,6,7] +[2026-03-11 19:10:47,256][lightning.pytorch.accelerators.cuda][INFO] - LOCAL_RANK: 3 - CUDA_VISIBLE_DEVICES: [0,1,2,3,4,5,6,7] +[2026-03-11 19:10:47,256][lightning.pytorch.accelerators.cuda][INFO] - LOCAL_RANK: 4 - CUDA_VISIBLE_DEVICES: [0,1,2,3,4,5,6,7] +[2026-03-11 19:10:47,256][lightning.pytorch.accelerators.cuda][INFO] - LOCAL_RANK: 5 - CUDA_VISIBLE_DEVICES: [0,1,2,3,4,5,6,7] +[2026-03-11 19:10:47,256][lightning.pytorch.accelerators.cuda][INFO] - LOCAL_RANK: 6 - CUDA_VISIBLE_DEVICES: [0,1,2,3,4,5,6,7] +[2026-03-11 19:10:47,256][lightning.pytorch.accelerators.cuda][INFO] - LOCAL_RANK: 7 - CUDA_VISIBLE_DEVICES: [0,1,2,3,4,5,6,7] +[2026-03-11 19:10:47,256][lightning.pytorch.accelerators.cuda][INFO] - LOCAL_RANK: 2 - CUDA_VISIBLE_DEVICES: [0,1,2,3,4,5,6,7] +INFO: + | Name | Type | Params +--------------------------------------------------------------------------------- +0 | diffusion_model | DiffusionMamba | 609 M +1 | validation_lpips_model | LearnedPerceptualImagePatchSimilarity | 2.5 M +2 | vae | AutoencoderKL | 229 M +3 | mamba_memory | BiMambaMemory | 4.5 M +4 | pose_prediction_model | PosePredictionNet | 200 K +--------------------------------------------------------------------------------- +609 M Trainable params +236 M Non-trainable params +846 M Total params +3,384.157 Total estimated model params size (MB) +[2026-03-11 19:10:49,730][lightning.pytorch.callbacks.model_summary][INFO] - + | Name | Type | Params +--------------------------------------------------------------------------------- +0 | diffusion_model | DiffusionMamba | 609 M +1 | validation_lpips_model | LearnedPerceptualImagePatchSimilarity | 2.5 M +2 | vae | AutoencoderKL | 229 M +3 | mamba_memory | BiMambaMemory | 4.5 M +4 | pose_prediction_model | PosePredictionNet | 200 K +--------------------------------------------------------------------------------- +609 M Trainable params +236 M Non-trainable params +846 M Total params +3,384.157 Total estimated model params size (MB) +INFO: SLURM auto-requeueing enabled. Setting signal handlers. +INFO: SLURM auto-requeueing enabled. Setting signal handlers. +INFO: SLURM auto-requeueing enabled. Setting signal handlers. +INFO: SLURM auto-requeueing enabled. Setting signal handlers. +[2026-03-11 19:10:50,787][lightning.pytorch.trainer.connectors.signal_connector][INFO] - SLURM auto-requeueing enabled. Setting signal handlers. +INFO: SLURM auto-requeueing enabled. Setting signal handlers. +[2026-03-11 19:10:50,787][lightning.pytorch.trainer.connectors.signal_connector][INFO] - SLURM auto-requeueing enabled. Setting signal handlers. +[2026-03-11 19:10:50,787][lightning.pytorch.trainer.connectors.signal_connector][INFO] - SLURM auto-requeueing enabled. Setting signal handlers. +[2026-03-11 19:10:50,787][lightning.pytorch.trainer.connectors.signal_connector][INFO] - SLURM auto-requeueing enabled. Setting signal handlers. +[2026-03-11 19:10:50,787][lightning.pytorch.trainer.connectors.signal_connector][INFO] - SLURM auto-requeueing enabled. Setting signal handlers. +INFO: SLURM auto-requeueing enabled. Setting signal handlers. +INFO: SLURM auto-requeueing enabled. Setting signal handlers. +[2026-03-11 19:10:50,788][lightning.pytorch.trainer.connectors.signal_connector][INFO] - SLURM auto-requeueing enabled. Setting signal handlers. +INFO: SLURM auto-requeueing enabled. Setting signal handlers. +[2026-03-11 19:10:50,788][lightning.pytorch.trainer.connectors.signal_connector][INFO] - SLURM auto-requeueing enabled. Setting signal handlers. +[2026-03-11 19:10:50,788][lightning.pytorch.trainer.connectors.signal_connector][INFO] - SLURM auto-requeueing enabled. Setting signal handlers. +/proj/cvl/users/x_fahkh2/WorldMem_Repro/algorithms/worldmem/models/mamba_memory.py:173: FutureWarning: `torch.cuda.amp.autocast(args...)` is deprecated. Please use `torch.amp.autocast('cuda', args...)` instead. + with torch.cuda.amp.autocast(enabled=False): +/proj/cvl/users/x_fahkh2/WorldMem_Repro/algorithms/worldmem/models/mamba_memory.py:173: FutureWarning: `torch.cuda.amp.autocast(args...)` is deprecated. Please use `torch.amp.autocast('cuda', args...)` instead. + with torch.cuda.amp.autocast(enabled=False): +/proj/cvl/users/x_fahkh2/WorldMem_Repro/algorithms/worldmem/models/mamba_memory.py:173: FutureWarning: `torch.cuda.amp.autocast(args...)` is deprecated. Please use `torch.amp.autocast('cuda', args...)` instead. + with torch.cuda.amp.autocast(enabled=False): +/proj/cvl/users/x_fahkh2/WorldMem_Repro/algorithms/worldmem/models/mamba_memory.py:173: FutureWarning: `torch.cuda.amp.autocast(args...)` is deprecated. Please use `torch.amp.autocast('cuda', args...)` instead. + with torch.cuda.amp.autocast(enabled=False): +/proj/cvl/users/x_fahkh2/WorldMem_Repro/algorithms/worldmem/models/mamba_memory.py:173: FutureWarning: `torch.cuda.amp.autocast(args...)` is deprecated. Please use `torch.amp.autocast('cuda', args...)` instead. + with torch.cuda.amp.autocast(enabled=False): +/proj/cvl/users/x_fahkh2/WorldMem_Repro/algorithms/worldmem/models/mamba_memory.py:173: FutureWarning: `torch.cuda.amp.autocast(args...)` is deprecated. Please use `torch.amp.autocast('cuda', args...)` instead. + with torch.cuda.amp.autocast(enabled=False): +/proj/cvl/users/x_fahkh2/WorldMem_Repro/algorithms/worldmem/models/mamba_memory.py:173: FutureWarning: `torch.cuda.amp.autocast(args...)` is deprecated. Please use `torch.amp.autocast('cuda', args...)` instead. + with torch.cuda.amp.autocast(enabled=False): +/proj/cvl/users/x_fahkh2/WorldMem_Repro/algorithms/worldmem/models/mamba_memory.py:173: FutureWarning: `torch.cuda.amp.autocast(args...)` is deprecated. Please use `torch.amp.autocast('cuda', args...)` instead. + with torch.cuda.amp.autocast(enabled=False): +Traceback (most recent call last): + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 300, in _run_finalizers + finalizer() + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 224, in __call__ + res = self._callback(*self._args, **self._kwargs) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 133, in _remove_temp_dir + rmtree(tempdir) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 725, in rmtree + _rmtree_safe_fd(fd, path, onerror) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 681, in _rmtree_safe_fd + onerror(os.unlink, fullname, sys.exc_info()) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 679, in _rmtree_safe_fd + os.unlink(entry.name, dir_fd=topfd) +OSError: [Errno 16] Device or resource busy: '.nfs53b29da5af195896000002b6' +Traceback (most recent call last): + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 300, in _run_finalizers + finalizer() + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 224, in __call__ + res = self._callback(*self._args, **self._kwargs) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 133, in _remove_temp_dir + rmtree(tempdir) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 725, in rmtree + _rmtree_safe_fd(fd, path, onerror) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 681, in _rmtree_safe_fd + onerror(os.unlink, fullname, sys.exc_info()) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 679, in _rmtree_safe_fd + os.unlink(entry.name, dir_fd=topfd) +OSError: [Errno 16] Device or resource busy: '.nfs882f64acc10a0ef1000002b7' +Traceback (most recent call last): + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 300, in _run_finalizers + finalizer() + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 224, in __call__ + res = self._callback(*self._args, **self._kwargs) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 133, in _remove_temp_dir + rmtree(tempdir) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 725, in rmtree + _rmtree_safe_fd(fd, path, onerror) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 681, in _rmtree_safe_fd + onerror(os.unlink, fullname, sys.exc_info()) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 679, in _rmtree_safe_fd + os.unlink(entry.name, dir_fd=topfd) +OSError: [Errno 16] Device or resource busy: '.nfsa8e6dab3b752a107000002b8' +Traceback (most recent call last): + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 300, in _run_finalizers + finalizer() + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 224, in __call__ + res = self._callback(*self._args, **self._kwargs) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 133, in _remove_temp_dir + rmtree(tempdir) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 725, in rmtree + _rmtree_safe_fd(fd, path, onerror) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 681, in _rmtree_safe_fd + onerror(os.unlink, fullname, sys.exc_info()) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 679, in _rmtree_safe_fd + os.unlink(entry.name, dir_fd=topfd) +OSError: [Errno 16] Device or resource busy: '.nfsba38b4f40f4714d1000002b9' +Traceback (most recent call last): + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 300, in _run_finalizers + finalizer() + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 224, in __call__ + res = self._callback(*self._args, **self._kwargs) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 133, in _remove_temp_dir + rmtree(tempdir) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 725, in rmtree + _rmtree_safe_fd(fd, path, onerror) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 681, in _rmtree_safe_fd + onerror(os.unlink, fullname, sys.exc_info()) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 679, in _rmtree_safe_fd + os.unlink(entry.name, dir_fd=topfd) +OSError: [Errno 16] Device or resource busy: '.nfsb91cc4a09cf6e99d000002ba' +Traceback (most recent call last): + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 300, in _run_finalizers + finalizer() + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 224, in __call__ + res = self._callback(*self._args, **self._kwargs) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 133, in _remove_temp_dir + rmtree(tempdir) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 725, in rmtree + _rmtree_safe_fd(fd, path, onerror) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 681, in _rmtree_safe_fd + onerror(os.unlink, fullname, sys.exc_info()) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 679, in _rmtree_safe_fd + os.unlink(entry.name, dir_fd=topfd) +OSError: [Errno 16] Device or resource busy: '.nfs6b92336da45a5c8a000002bb' +Traceback (most recent call last): + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 300, in _run_finalizers + finalizer() + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 224, in __call__ + res = self._callback(*self._args, **self._kwargs) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 133, in _remove_temp_dir + rmtree(tempdir) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 725, in rmtree + _rmtree_safe_fd(fd, path, onerror) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 681, in _rmtree_safe_fd + onerror(os.unlink, fullname, sys.exc_info()) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 679, in _rmtree_safe_fd + os.unlink(entry.name, dir_fd=topfd) +OSError: [Errno 16] Device or resource busy: '.nfsa9c70a3d6ad255ef000002bd' +Traceback (most recent call last): + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 300, in _run_finalizers + finalizer() + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 224, in __call__ + res = self._callback(*self._args, **self._kwargs) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 133, in _remove_temp_dir + rmtree(tempdir) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 725, in rmtree + _rmtree_safe_fd(fd, path, onerror) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 681, in _rmtree_safe_fd + onerror(os.unlink, fullname, sys.exc_info()) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 679, in _rmtree_safe_fd + os.unlink(entry.name, dir_fd=topfd) +OSError: [Errno 16] Device or resource busy: '.nfs7a8f466ece31debf000002bc' +Traceback (most recent call last): + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 300, in _run_finalizers + finalizer() + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 224, in __call__ + res = self._callback(*self._args, **self._kwargs) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 133, in _remove_temp_dir + rmtree(tempdir) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 725, in rmtree + _rmtree_safe_fd(fd, path, onerror) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 681, in _rmtree_safe_fd + onerror(os.unlink, fullname, sys.exc_info()) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 679, in _rmtree_safe_fd + os.unlink(entry.name, dir_fd=topfd) +OSError: [Errno 16] Device or resource busy: '.nfs41ffd7a467d377ed000002be' +Traceback (most recent call last): + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 300, in _run_finalizers + finalizer() + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 224, in __call__ + res = self._callback(*self._args, **self._kwargs) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 133, in _remove_temp_dir + rmtree(tempdir) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 725, in rmtree + _rmtree_safe_fd(fd, path, onerror) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 681, in _rmtree_safe_fd + onerror(os.unlink, fullname, sys.exc_info()) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 679, in _rmtree_safe_fd + os.unlink(entry.name, dir_fd=topfd) +OSError: [Errno 16] Device or resource busy: '.nfs4d8841d5f4a12275000002bf' +Traceback (most recent call last): + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 300, in _run_finalizers + finalizer() + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 224, in __call__ + res = self._callback(*self._args, **self._kwargs) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 133, in _remove_temp_dir + rmtree(tempdir) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 725, in rmtree + _rmtree_safe_fd(fd, path, onerror) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 681, in _rmtree_safe_fd + onerror(os.unlink, fullname, sys.exc_info()) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 679, in _rmtree_safe_fd + os.unlink(entry.name, dir_fd=topfd) +OSError: [Errno 16] Device or resource busy: '.nfs65bc92a9ef8359a9000002c0' +Traceback (most recent call last): + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 300, in _run_finalizers + finalizer() + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 224, in __call__ + res = self._callback(*self._args, **self._kwargs) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 133, in _remove_temp_dir + rmtree(tempdir) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 725, in rmtree + _rmtree_safe_fd(fd, path, onerror) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 681, in _rmtree_safe_fd + onerror(os.unlink, fullname, sys.exc_info()) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 679, in _rmtree_safe_fd + os.unlink(entry.name, dir_fd=topfd) +OSError: [Errno 16] Device or resource busy: '.nfs8b9c4e24d7623df2000002c1' +Traceback (most recent call last): + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 300, in _run_finalizers + finalizer() + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 224, in __call__ + res = self._callback(*self._args, **self._kwargs) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 133, in _remove_temp_dir + rmtree(tempdir) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 725, in rmtree + _rmtree_safe_fd(fd, path, onerror) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 681, in _rmtree_safe_fd + onerror(os.unlink, fullname, sys.exc_info()) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 679, in _rmtree_safe_fd + os.unlink(entry.name, dir_fd=topfd) +OSError: [Errno 16] Device or resource busy: '.nfs6d6a1d30d78b9b40000002c2' +Traceback (most recent call last): + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 300, in _run_finalizers + finalizer() + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 224, in __call__ + res = self._callback(*self._args, **self._kwargs) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 133, in _remove_temp_dir + rmtree(tempdir) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 725, in rmtree + _rmtree_safe_fd(fd, path, onerror) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 681, in _rmtree_safe_fd + onerror(os.unlink, fullname, sys.exc_info()) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 679, in _rmtree_safe_fd + os.unlink(entry.name, dir_fd=topfd) +OSError: [Errno 16] Device or resource busy: '.nfs1074dc4f03a07269000002c3' +Traceback (most recent call last): + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 300, in _run_finalizers + finalizer() + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 224, in __call__ + res = self._callback(*self._args, **self._kwargs) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 133, in _remove_temp_dir + rmtree(tempdir) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 725, in rmtree + _rmtree_safe_fd(fd, path, onerror) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 681, in _rmtree_safe_fd + onerror(os.unlink, fullname, sys.exc_info()) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 679, in _rmtree_safe_fd + os.unlink(entry.name, dir_fd=topfd) +OSError: [Errno 16] Device or resource busy: '.nfs4adc9f3da03a6c76000002c4' +Traceback (most recent call last): + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 300, in _run_finalizers + finalizer() + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 224, in __call__ + res = self._callback(*self._args, **self._kwargs) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 133, in _remove_temp_dir + rmtree(tempdir) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 725, in rmtree + _rmtree_safe_fd(fd, path, onerror) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 681, in _rmtree_safe_fd + onerror(os.unlink, fullname, sys.exc_info()) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 679, in _rmtree_safe_fd + os.unlink(entry.name, dir_fd=topfd) +OSError: [Errno 16] Device or resource busy: '.nfsafa07ac932f72342000002c5' +Traceback (most recent call last): + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 300, in _run_finalizers + finalizer() + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 224, in __call__ + res = self._callback(*self._args, **self._kwargs) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 133, in _remove_temp_dir + rmtree(tempdir) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 725, in rmtree + _rmtree_safe_fd(fd, path, onerror) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 681, in _rmtree_safe_fd + onerror(os.unlink, fullname, sys.exc_info()) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 679, in _rmtree_safe_fd + os.unlink(entry.name, dir_fd=topfd) +OSError: [Errno 16] Device or resource busy: '.nfsd5c554b98bfe3bf5000002c6' +Traceback (most recent call last): + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 300, in _run_finalizers + finalizer() + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 224, in __call__ + res = self._callback(*self._args, **self._kwargs) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 133, in _remove_temp_dir + rmtree(tempdir) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 725, in rmtree + _rmtree_safe_fd(fd, path, onerror) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 681, in _rmtree_safe_fd + onerror(os.unlink, fullname, sys.exc_info()) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 679, in _rmtree_safe_fd + os.unlink(entry.name, dir_fd=topfd) +OSError: [Errno 16] Device or resource busy: '.nfs0f0a74752cdff2bb000002c7' +Traceback (most recent call last): + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 300, in _run_finalizers + finalizer() + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 224, in __call__ + res = self._callback(*self._args, **self._kwargs) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 133, in _remove_temp_dir + rmtree(tempdir) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 725, in rmtree + _rmtree_safe_fd(fd, path, onerror) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 681, in _rmtree_safe_fd + onerror(os.unlink, fullname, sys.exc_info()) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 679, in _rmtree_safe_fd + os.unlink(entry.name, dir_fd=topfd) +OSError: [Errno 16] Device or resource busy: '.nfsedc297dae670e45a000002c8' +Traceback (most recent call last): + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 300, in _run_finalizers + finalizer() + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 224, in __call__ + res = self._callback(*self._args, **self._kwargs) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 133, in _remove_temp_dir + rmtree(tempdir) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 725, in rmtree + _rmtree_safe_fd(fd, path, onerror) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 681, in _rmtree_safe_fd + onerror(os.unlink, fullname, sys.exc_info()) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 679, in _rmtree_safe_fd + os.unlink(entry.name, dir_fd=topfd) +OSError: [Errno 16] Device or resource busy: '.nfs320ed0974425537a000002c9' +Traceback (most recent call last): + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 300, in _run_finalizers + finalizer() + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 224, in __call__ + res = self._callback(*self._args, **self._kwargs) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 133, in _remove_temp_dir + rmtree(tempdir) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 725, in rmtree + _rmtree_safe_fd(fd, path, onerror) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 681, in _rmtree_safe_fd + onerror(os.unlink, fullname, sys.exc_info()) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 679, in _rmtree_safe_fd + os.unlink(entry.name, dir_fd=topfd) +OSError: [Errno 16] Device or resource busy: '.nfsc6538662702932fc000002ca' +Traceback (most recent call last): + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 300, in _run_finalizers + finalizer() + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 224, in __call__ + res = self._callback(*self._args, **self._kwargs) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 133, in _remove_temp_dir + rmtree(tempdir) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 725, in rmtree + _rmtree_safe_fd(fd, path, onerror) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 681, in _rmtree_safe_fd + onerror(os.unlink, fullname, sys.exc_info()) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 679, in _rmtree_safe_fd + os.unlink(entry.name, dir_fd=topfd) +OSError: [Errno 16] Device or resource busy: '.nfs0cbe62abfd9de375000002cb' +Traceback (most recent call last): + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 300, in _run_finalizers + finalizer() + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 224, in __call__ + res = self._callback(*self._args, **self._kwargs) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 133, in _remove_temp_dir + rmtree(tempdir) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 725, in rmtree + _rmtree_safe_fd(fd, path, onerror) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 681, in _rmtree_safe_fd + onerror(os.unlink, fullname, sys.exc_info()) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 679, in _rmtree_safe_fd + os.unlink(entry.name, dir_fd=topfd) +OSError: [Errno 16] Device or resource busy: '.nfsfc39db7b541e8b92000002cc' +Traceback (most recent call last): + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 300, in _run_finalizers + finalizer() + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 224, in __call__ + res = self._callback(*self._args, **self._kwargs) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 133, in _remove_temp_dir + rmtree(tempdir) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 725, in rmtree + _rmtree_safe_fd(fd, path, onerror) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 681, in _rmtree_safe_fd + onerror(os.unlink, fullname, sys.exc_info()) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 679, in _rmtree_safe_fd + os.unlink(entry.name, dir_fd=topfd) +OSError: [Errno 16] Device or resource busy: '.nfs3cffa4b77a5a93d5000002cd' +Traceback (most recent call last): + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 300, in _run_finalizers + finalizer() + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 224, in __call__ + res = self._callback(*self._args, **self._kwargs) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 133, in _remove_temp_dir + rmtree(tempdir) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 725, in rmtree + _rmtree_safe_fd(fd, path, onerror) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 681, in _rmtree_safe_fd + onerror(os.unlink, fullname, sys.exc_info()) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 679, in _rmtree_safe_fd + os.unlink(entry.name, dir_fd=topfd) +OSError: [Errno 16] Device or resource busy: '.nfse45ab7cb9f42a894000002ce' +Traceback (most recent call last): + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 300, in _run_finalizers + finalizer() + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 224, in __call__ + res = self._callback(*self._args, **self._kwargs) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 133, in _remove_temp_dir + rmtree(tempdir) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 725, in rmtree + _rmtree_safe_fd(fd, path, onerror) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 681, in _rmtree_safe_fd + onerror(os.unlink, fullname, sys.exc_info()) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 679, in _rmtree_safe_fd + os.unlink(entry.name, dir_fd=topfd) +OSError: [Errno 16] Device or resource busy: '.nfsd7470719afe76e80000002cf' +Traceback (most recent call last): + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 300, in _run_finalizers + finalizer() + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 224, in __call__ + res = self._callback(*self._args, **self._kwargs) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 133, in _remove_temp_dir + rmtree(tempdir) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 725, in rmtree + _rmtree_safe_fd(fd, path, onerror) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 681, in _rmtree_safe_fd + onerror(os.unlink, fullname, sys.exc_info()) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 679, in _rmtree_safe_fd + os.unlink(entry.name, dir_fd=topfd) +OSError: [Errno 16] Device or resource busy: '.nfsc71c3b699433fe49000002d0' +Traceback (most recent call last): + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 300, in _run_finalizers + finalizer() + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 224, in __call__ + res = self._callback(*self._args, **self._kwargs) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 133, in _remove_temp_dir + rmtree(tempdir) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 725, in rmtree + _rmtree_safe_fd(fd, path, onerror) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 681, in _rmtree_safe_fd + onerror(os.unlink, fullname, sys.exc_info()) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 679, in _rmtree_safe_fd + os.unlink(entry.name, dir_fd=topfd) +OSError: [Errno 16] Device or resource busy: '.nfs1b7bed37db55e66c000002d1' +Error executing job with overrides: ['+name=train_stage_b_mamba', 'algorithm=df_video_mamba3stage', '+customized_load=true', '+seperate_load=false', 'experiment.num_nodes=1', 'load=/proj/cvl/users/x_fahkh2/WorldMem_Repro/checkpoints/bimamba_stage_a_128/checkpoints/epoch0_step2000.ckpt', 'dataset.save_dir=/proj/cvl/users/x_fahkh2/WorldMem_Repro/datasets/minecraft', 'dataset.n_frames=200', '+dataset.n_frames_valid=200', '+dataset.angle_range=110', '+dataset.pos_range=2', '+dataset.wo_updown=false', '+dataset.customized_validation=true', '+dataset.add_timestamp_embedding=true', '+dataset.use_explicit_memory_frames=false', 'algorithm.training_stage=stage_b_diffusion_frozen_memory', 'algorithm.use_mamba_memory_pipeline=true', 'algorithm.use_oracle_pose_eval=false', 'algorithm.enable_memory_noise_curriculum=false', '+algorithm.require_pose_prediction=false', '+algorithm.use_memory_attention=false', '+algorithm.relative_embedding=false', '+algorithm.memory_retrieval_topk=32', 'algorithm.diff_window_size=8', 'algorithm.memory_condition_length=0', 'algorithm.context_frames=100', '+algorithm.n_tokens=8', 'experiment.training.batch_size=8', 'experiment.training.checkpointing.every_n_train_steps=2500', 'experiment.training.max_steps=30000', 'experiment.validation.val_every_n_step=2500', '+output_dir=/proj/cvl/users/x_fahkh2/WorldMem_Repro/checkpoints/bimamba_stage_b/'] +[rank4]: Traceback (most recent call last): +[rank4]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/runpy.py", line 196, in _run_module_as_main +[rank4]: return _run_code(code, main_globals, None, +[rank4]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/runpy.py", line 86, in _run_code +[rank4]: exec(code, run_globals) +[rank4]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/main.py", line 202, in +[rank4]: run() # pylint: disable=no-value-for-parameter +[rank4]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/main.py", line 94, in decorated_main +[rank4]: _run_hydra( +[rank4]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/utils.py", line 394, in _run_hydra +[rank4]: _run_app( +[rank4]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/utils.py", line 457, in _run_app +[rank4]: run_and_report( +[rank4]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/utils.py", line 223, in run_and_report +[rank4]: raise ex +[rank4]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/utils.py", line 220, in run_and_report +[rank4]: return func() +[rank4]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/utils.py", line 458, in +[rank4]: lambda: hydra.run( +[rank4]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/hydra.py", line 132, in run +[rank4]: _ = ret.return_value +[rank4]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/core/utils.py", line 260, in return_value +[rank4]: raise self._return_value +[rank4]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/core/utils.py", line 186, in run_job +[rank4]: ret.return_value = task_function(task_cfg) +[rank4]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/main.py", line 198, in run +[rank4]: run_local(cfg) +[rank4]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/main.py", line 122, in run_local +[rank4]: experiment.exec_task(task) +[rank4]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/experiments/exp_base.py", line 172, in exec_task +[rank4]: getattr(self, task)() +[rank4]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/experiments/exp_base.py", line 357, in training +[rank4]: trainer.fit( +[rank4]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/trainer.py", line 544, in fit +[rank4]: call._call_and_handle_interrupt( +[rank4]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/call.py", line 43, in _call_and_handle_interrupt +[rank4]: return trainer.strategy.launcher.launch(trainer_fn, *args, trainer=trainer, **kwargs) +[rank4]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/launchers/subprocess_script.py", line 102, in launch +[rank4]: return function(*args, **kwargs) +[rank4]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/trainer.py", line 580, in _fit_impl +[rank4]: self._run(model, ckpt_path=ckpt_path) +[rank4]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/trainer.py", line 989, in _run +[rank4]: results = self._run_stage() +[rank4]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/trainer.py", line 1035, in _run_stage +[rank4]: self.fit_loop.run() +[rank4]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/fit_loop.py", line 202, in run +[rank4]: self.advance() +[rank4]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/fit_loop.py", line 359, in advance +[rank4]: self.epoch_loop.run(self._data_fetcher) +[rank4]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/training_epoch_loop.py", line 136, in run +[rank4]: self.advance(data_fetcher) +[rank4]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/training_epoch_loop.py", line 240, in advance +[rank4]: batch_output = self.automatic_optimization.run(trainer.optimizers[0], batch_idx, kwargs) +[rank4]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/optimization/automatic.py", line 187, in run +[rank4]: self._optimizer_step(batch_idx, closure) +[rank4]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/optimization/automatic.py", line 265, in _optimizer_step +[rank4]: call._call_lightning_module_hook( +[rank4]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/call.py", line 157, in _call_lightning_module_hook +[rank4]: output = fn(*args, **kwargs) +[rank4]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/algorithms/worldmem/df_base.py", line 65, in optimizer_step +[rank4]: optimizer.step(closure=optimizer_closure) +[rank4]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/core/optimizer.py", line 151, in step +[rank4]: step_output = self._strategy.optimizer_step(self._optimizer, closure, **kwargs) +[rank4]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/ddp.py", line 265, in optimizer_step +[rank4]: optimizer_output = super().optimizer_step(optimizer, closure, model, **kwargs) +[rank4]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/strategy.py", line 230, in optimizer_step +[rank4]: return self.precision_plugin.optimizer_step(optimizer, model=model, closure=closure, **kwargs) +[rank4]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/plugins/precision/amp.py", line 77, in optimizer_step +[rank4]: closure_result = closure() +[rank4]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/optimization/automatic.py", line 140, in __call__ +[rank4]: self._result = self.closure(*args, **kwargs) +[rank4]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 116, in decorate_context +[rank4]: return func(*args, **kwargs) +[rank4]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/optimization/automatic.py", line 126, in closure +[rank4]: step_output = self._step_fn() +[rank4]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/optimization/automatic.py", line 315, in _training_step +[rank4]: training_step_output = call._call_strategy_hook(trainer, "training_step", *kwargs.values()) +[rank4]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/call.py", line 309, in _call_strategy_hook +[rank4]: output = fn(*args, **kwargs) +[rank4]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/strategy.py", line 381, in training_step +[rank4]: return self._forward_redirection(self.model, self.lightning_module, "training_step", *args, **kwargs) +[rank4]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/strategy.py", line 633, in __call__ +[rank4]: wrapper_output = wrapper_module(*args, **kwargs) +[rank4]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1553, in _wrapped_call_impl +[rank4]: return self._call_impl(*args, **kwargs) +[rank4]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1562, in _call_impl +[rank4]: return forward_call(*args, **kwargs) +[rank4]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/parallel/distributed.py", line 1636, in forward +[rank4]: else self._run_ddp_forward(*inputs, **kwargs) +[rank4]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/parallel/distributed.py", line 1454, in _run_ddp_forward +[rank4]: return self.module(*inputs, **kwargs) # type: ignore[index] +[rank4]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1553, in _wrapped_call_impl +[rank4]: return self._call_impl(*args, **kwargs) +[rank4]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1562, in _call_impl +[rank4]: return forward_call(*args, **kwargs) +[rank4]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/strategy.py", line 626, in wrapped_forward +[rank4]: out = method(*_args, **_kwargs) +[rank4]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/algorithms/worldmem/df_video_mamba3stage.py", line 1073, in training_step +[rank4]: self.log("training/curriculum_phase", float(phase_idx)) +[rank4]: TypeError: float() argument must be a string or a real number, not 'NoneType' +Error executing job with overrides: ['+name=train_stage_b_mamba', 'algorithm=df_video_mamba3stage', '+customized_load=true', '+seperate_load=false', 'experiment.num_nodes=1', 'load=/proj/cvl/users/x_fahkh2/WorldMem_Repro/checkpoints/bimamba_stage_a_128/checkpoints/epoch0_step2000.ckpt', 'dataset.save_dir=/proj/cvl/users/x_fahkh2/WorldMem_Repro/datasets/minecraft', 'dataset.n_frames=200', '+dataset.n_frames_valid=200', '+dataset.angle_range=110', '+dataset.pos_range=2', '+dataset.wo_updown=false', '+dataset.customized_validation=true', '+dataset.add_timestamp_embedding=true', '+dataset.use_explicit_memory_frames=false', 'algorithm.training_stage=stage_b_diffusion_frozen_memory', 'algorithm.use_mamba_memory_pipeline=true', 'algorithm.use_oracle_pose_eval=false', 'algorithm.enable_memory_noise_curriculum=false', '+algorithm.require_pose_prediction=false', '+algorithm.use_memory_attention=false', '+algorithm.relative_embedding=false', '+algorithm.memory_retrieval_topk=32', 'algorithm.diff_window_size=8', 'algorithm.memory_condition_length=0', 'algorithm.context_frames=100', '+algorithm.n_tokens=8', 'experiment.training.batch_size=8', 'experiment.training.checkpointing.every_n_train_steps=2500', 'experiment.training.max_steps=30000', 'experiment.validation.val_every_n_step=2500', '+output_dir=/proj/cvl/users/x_fahkh2/WorldMem_Repro/checkpoints/bimamba_stage_b/'] +[rank7]: Traceback (most recent call last): +[rank7]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/runpy.py", line 196, in _run_module_as_main +[rank7]: return _run_code(code, main_globals, None, +[rank7]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/runpy.py", line 86, in _run_code +[rank7]: exec(code, run_globals) +[rank7]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/main.py", line 202, in +[rank7]: run() # pylint: disable=no-value-for-parameter +[rank7]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/main.py", line 94, in decorated_main +[rank7]: _run_hydra( +[rank7]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/utils.py", line 394, in _run_hydra +[rank7]: _run_app( +[rank7]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/utils.py", line 457, in _run_app +[rank7]: run_and_report( +[rank7]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/utils.py", line 223, in run_and_report +[rank7]: raise ex +[rank7]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/utils.py", line 220, in run_and_report +[rank7]: return func() +[rank7]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/utils.py", line 458, in +[rank7]: lambda: hydra.run( +[rank7]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/hydra.py", line 132, in run +[rank7]: _ = ret.return_value +[rank7]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/core/utils.py", line 260, in return_value +[rank7]: raise self._return_value +[rank7]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/core/utils.py", line 186, in run_job +[rank7]: ret.return_value = task_function(task_cfg) +[rank7]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/main.py", line 198, in run +[rank7]: run_local(cfg) +[rank7]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/main.py", line 122, in run_local +[rank7]: experiment.exec_task(task) +[rank7]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/experiments/exp_base.py", line 172, in exec_task +[rank7]: getattr(self, task)() +[rank7]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/experiments/exp_base.py", line 357, in training +[rank7]: trainer.fit( +[rank7]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/trainer.py", line 544, in fit +[rank7]: call._call_and_handle_interrupt( +[rank7]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/call.py", line 43, in _call_and_handle_interrupt +[rank7]: return trainer.strategy.launcher.launch(trainer_fn, *args, trainer=trainer, **kwargs) +[rank7]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/launchers/subprocess_script.py", line 102, in launch +[rank7]: return function(*args, **kwargs) +[rank7]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/trainer.py", line 580, in _fit_impl +[rank7]: self._run(model, ckpt_path=ckpt_path) +[rank7]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/trainer.py", line 989, in _run +[rank7]: results = self._run_stage() +[rank7]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/trainer.py", line 1035, in _run_stage +[rank7]: self.fit_loop.run() +[rank7]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/fit_loop.py", line 202, in run +[rank7]: self.advance() +[rank7]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/fit_loop.py", line 359, in advance +[rank7]: self.epoch_loop.run(self._data_fetcher) +[rank7]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/training_epoch_loop.py", line 136, in run +[rank7]: self.advance(data_fetcher) +[rank7]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/training_epoch_loop.py", line 240, in advance +[rank7]: batch_output = self.automatic_optimization.run(trainer.optimizers[0], batch_idx, kwargs) +[rank7]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/optimization/automatic.py", line 187, in run +[rank7]: self._optimizer_step(batch_idx, closure) +[rank7]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/optimization/automatic.py", line 265, in _optimizer_step +[rank7]: call._call_lightning_module_hook( +[rank7]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/call.py", line 157, in _call_lightning_module_hook +[rank7]: output = fn(*args, **kwargs) +[rank7]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/algorithms/worldmem/df_base.py", line 65, in optimizer_step +[rank7]: optimizer.step(closure=optimizer_closure) +[rank7]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/core/optimizer.py", line 151, in step +[rank7]: step_output = self._strategy.optimizer_step(self._optimizer, closure, **kwargs) +[rank7]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/ddp.py", line 265, in optimizer_step +[rank7]: optimizer_output = super().optimizer_step(optimizer, closure, model, **kwargs) +[rank7]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/strategy.py", line 230, in optimizer_step +[rank7]: return self.precision_plugin.optimizer_step(optimizer, model=model, closure=closure, **kwargs) +[rank7]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/plugins/precision/amp.py", line 77, in optimizer_step +[rank7]: closure_result = closure() +[rank7]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/optimization/automatic.py", line 140, in __call__ +[rank7]: self._result = self.closure(*args, **kwargs) +[rank7]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 116, in decorate_context +[rank7]: return func(*args, **kwargs) +[rank7]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/optimization/automatic.py", line 126, in closure +[rank7]: step_output = self._step_fn() +[rank7]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/optimization/automatic.py", line 315, in _training_step +[rank7]: training_step_output = call._call_strategy_hook(trainer, "training_step", *kwargs.values()) +[rank7]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/call.py", line 309, in _call_strategy_hook +[rank7]: output = fn(*args, **kwargs) +[rank7]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/strategy.py", line 381, in training_step +[rank7]: return self._forward_redirection(self.model, self.lightning_module, "training_step", *args, **kwargs) +[rank7]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/strategy.py", line 633, in __call__ +[rank7]: wrapper_output = wrapper_module(*args, **kwargs) +[rank7]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1553, in _wrapped_call_impl +[rank7]: return self._call_impl(*args, **kwargs) +[rank7]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1562, in _call_impl +[rank7]: return forward_call(*args, **kwargs) +[rank7]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/parallel/distributed.py", line 1636, in forward +[rank7]: else self._run_ddp_forward(*inputs, **kwargs) +[rank7]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/parallel/distributed.py", line 1454, in _run_ddp_forward +[rank7]: return self.module(*inputs, **kwargs) # type: ignore[index] +[rank7]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1553, in _wrapped_call_impl +[rank7]: return self._call_impl(*args, **kwargs) +[rank7]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1562, in _call_impl +[rank7]: return forward_call(*args, **kwargs) +[rank7]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/strategy.py", line 626, in wrapped_forward +[rank7]: out = method(*_args, **_kwargs) +[rank7]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/algorithms/worldmem/df_video_mamba3stage.py", line 1073, in training_step +[rank7]: self.log("training/curriculum_phase", float(phase_idx)) +[rank7]: TypeError: float() argument must be a string or a real number, not 'NoneType' +Traceback (most recent call last): + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 300, in _run_finalizers + finalizer() + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 224, in __call__ + res = self._callback(*self._args, **self._kwargs) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 133, in _remove_temp_dir + rmtree(tempdir) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 725, in rmtree + _rmtree_safe_fd(fd, path, onerror) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 681, in _rmtree_safe_fd + onerror(os.unlink, fullname, sys.exc_info()) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 679, in _rmtree_safe_fd + os.unlink(entry.name, dir_fd=topfd) +OSError: [Errno 16] Device or resource busy: '.nfsd62f175f2b87b4b7000002d2' +Traceback (most recent call last): + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 300, in _run_finalizers + finalizer() + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 224, in __call__ + res = self._callback(*self._args, **self._kwargs) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 133, in _remove_temp_dir + rmtree(tempdir) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 725, in rmtree + _rmtree_safe_fd(fd, path, onerror) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 681, in _rmtree_safe_fd + onerror(os.unlink, fullname, sys.exc_info()) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 679, in _rmtree_safe_fd + os.unlink(entry.name, dir_fd=topfd) +OSError: [Errno 16] Device or resource busy: '.nfs14c3854683fc8e21000002d3' +Traceback (most recent call last): + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 300, in _run_finalizers + finalizer() + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 224, in __call__ + res = self._callback(*self._args, **self._kwargs) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 133, in _remove_temp_dir + rmtree(tempdir) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 725, in rmtree + _rmtree_safe_fd(fd, path, onerror) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 681, in _rmtree_safe_fd + onerror(os.unlink, fullname, sys.exc_info()) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 679, in _rmtree_safe_fd + os.unlink(entry.name, dir_fd=topfd) +OSError: [Errno 16] Device or resource busy: '.nfs43121d8c4ab15ad1000002d4' +Error executing job with overrides: ['+name=train_stage_b_mamba', 'algorithm=df_video_mamba3stage', '+customized_load=true', '+seperate_load=false', 'experiment.num_nodes=1', 'load=/proj/cvl/users/x_fahkh2/WorldMem_Repro/checkpoints/bimamba_stage_a_128/checkpoints/epoch0_step2000.ckpt', 'dataset.save_dir=/proj/cvl/users/x_fahkh2/WorldMem_Repro/datasets/minecraft', 'dataset.n_frames=200', '+dataset.n_frames_valid=200', '+dataset.angle_range=110', '+dataset.pos_range=2', '+dataset.wo_updown=false', '+dataset.customized_validation=true', '+dataset.add_timestamp_embedding=true', '+dataset.use_explicit_memory_frames=false', 'algorithm.training_stage=stage_b_diffusion_frozen_memory', 'algorithm.use_mamba_memory_pipeline=true', 'algorithm.use_oracle_pose_eval=false', 'algorithm.enable_memory_noise_curriculum=false', '+algorithm.require_pose_prediction=false', '+algorithm.use_memory_attention=false', '+algorithm.relative_embedding=false', '+algorithm.memory_retrieval_topk=32', 'algorithm.diff_window_size=8', 'algorithm.memory_condition_length=0', 'algorithm.context_frames=100', '+algorithm.n_tokens=8', 'experiment.training.batch_size=8', 'experiment.training.checkpointing.every_n_train_steps=2500', 'experiment.training.max_steps=30000', 'experiment.validation.val_every_n_step=2500', '+output_dir=/proj/cvl/users/x_fahkh2/WorldMem_Repro/checkpoints/bimamba_stage_b/'] +[rank2]: Traceback (most recent call last): +[rank2]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/runpy.py", line 196, in _run_module_as_main +[rank2]: return _run_code(code, main_globals, None, +[rank2]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/runpy.py", line 86, in _run_code +[rank2]: exec(code, run_globals) +[rank2]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/main.py", line 202, in +[rank2]: run() # pylint: disable=no-value-for-parameter +[rank2]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/main.py", line 94, in decorated_main +[rank2]: _run_hydra( +[rank2]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/utils.py", line 394, in _run_hydra +[rank2]: _run_app( +[rank2]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/utils.py", line 457, in _run_app +[rank2]: run_and_report( +[rank2]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/utils.py", line 223, in run_and_report +[rank2]: raise ex +[rank2]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/utils.py", line 220, in run_and_report +[rank2]: return func() +[rank2]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/utils.py", line 458, in +[rank2]: lambda: hydra.run( +[rank2]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/hydra.py", line 132, in run +[rank2]: _ = ret.return_value +[rank2]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/core/utils.py", line 260, in return_value +[rank2]: raise self._return_value +[rank2]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/core/utils.py", line 186, in run_job +[rank2]: ret.return_value = task_function(task_cfg) +[rank2]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/main.py", line 198, in run +[rank2]: run_local(cfg) +[rank2]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/main.py", line 122, in run_local +[rank2]: experiment.exec_task(task) +[rank2]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/experiments/exp_base.py", line 172, in exec_task +[rank2]: getattr(self, task)() +[rank2]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/experiments/exp_base.py", line 357, in training +[rank2]: trainer.fit( +[rank2]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/trainer.py", line 544, in fit +[rank2]: call._call_and_handle_interrupt( +[rank2]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/call.py", line 43, in _call_and_handle_interrupt +[rank2]: return trainer.strategy.launcher.launch(trainer_fn, *args, trainer=trainer, **kwargs) +[rank2]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/launchers/subprocess_script.py", line 102, in launch +[rank2]: return function(*args, **kwargs) +[rank2]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/trainer.py", line 580, in _fit_impl +[rank2]: self._run(model, ckpt_path=ckpt_path) +[rank2]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/trainer.py", line 989, in _run +[rank2]: results = self._run_stage() +[rank2]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/trainer.py", line 1035, in _run_stage +[rank2]: self.fit_loop.run() +[rank2]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/fit_loop.py", line 202, in run +[rank2]: self.advance() +[rank2]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/fit_loop.py", line 359, in advance +[rank2]: self.epoch_loop.run(self._data_fetcher) +[rank2]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/training_epoch_loop.py", line 136, in run +[rank2]: self.advance(data_fetcher) +[rank2]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/training_epoch_loop.py", line 240, in advance +[rank2]: batch_output = self.automatic_optimization.run(trainer.optimizers[0], batch_idx, kwargs) +[rank2]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/optimization/automatic.py", line 187, in run +[rank2]: self._optimizer_step(batch_idx, closure) +[rank2]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/optimization/automatic.py", line 265, in _optimizer_step +[rank2]: call._call_lightning_module_hook( +[rank2]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/call.py", line 157, in _call_lightning_module_hook +[rank2]: output = fn(*args, **kwargs) +[rank2]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/algorithms/worldmem/df_base.py", line 65, in optimizer_step +[rank2]: optimizer.step(closure=optimizer_closure) +[rank2]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/core/optimizer.py", line 151, in step +[rank2]: step_output = self._strategy.optimizer_step(self._optimizer, closure, **kwargs) +[rank2]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/ddp.py", line 265, in optimizer_step +[rank2]: optimizer_output = super().optimizer_step(optimizer, closure, model, **kwargs) +[rank2]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/strategy.py", line 230, in optimizer_step +[rank2]: return self.precision_plugin.optimizer_step(optimizer, model=model, closure=closure, **kwargs) +[rank2]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/plugins/precision/amp.py", line 77, in optimizer_step +[rank2]: closure_result = closure() +[rank2]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/optimization/automatic.py", line 140, in __call__ +[rank2]: self._result = self.closure(*args, **kwargs) +[rank2]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 116, in decorate_context +[rank2]: return func(*args, **kwargs) +[rank2]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/optimization/automatic.py", line 126, in closure +[rank2]: step_output = self._step_fn() +[rank2]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/optimization/automatic.py", line 315, in _training_step +[rank2]: training_step_output = call._call_strategy_hook(trainer, "training_step", *kwargs.values()) +[rank2]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/call.py", line 309, in _call_strategy_hook +[rank2]: output = fn(*args, **kwargs) +[rank2]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/strategy.py", line 381, in training_step +[rank2]: return self._forward_redirection(self.model, self.lightning_module, "training_step", *args, **kwargs) +[rank2]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/strategy.py", line 633, in __call__ +[rank2]: wrapper_output = wrapper_module(*args, **kwargs) +[rank2]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1553, in _wrapped_call_impl +[rank2]: return self._call_impl(*args, **kwargs) +[rank2]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1562, in _call_impl +[rank2]: return forward_call(*args, **kwargs) +[rank2]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/parallel/distributed.py", line 1636, in forward +[rank2]: else self._run_ddp_forward(*inputs, **kwargs) +[rank2]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/parallel/distributed.py", line 1454, in _run_ddp_forward +[rank2]: return self.module(*inputs, **kwargs) # type: ignore[index] +[rank2]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1553, in _wrapped_call_impl +[rank2]: return self._call_impl(*args, **kwargs) +[rank2]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1562, in _call_impl +[rank2]: return forward_call(*args, **kwargs) +[rank2]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/strategy.py", line 626, in wrapped_forward +[rank2]: out = method(*_args, **_kwargs) +[rank2]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/algorithms/worldmem/df_video_mamba3stage.py", line 1073, in training_step +[rank2]: self.log("training/curriculum_phase", float(phase_idx)) +[rank2]: TypeError: float() argument must be a string or a real number, not 'NoneType' +Error executing job with overrides: ['+name=train_stage_b_mamba', 'algorithm=df_video_mamba3stage', '+customized_load=true', '+seperate_load=false', 'experiment.num_nodes=1', 'load=/proj/cvl/users/x_fahkh2/WorldMem_Repro/checkpoints/bimamba_stage_a_128/checkpoints/epoch0_step2000.ckpt', 'dataset.save_dir=/proj/cvl/users/x_fahkh2/WorldMem_Repro/datasets/minecraft', 'dataset.n_frames=200', '+dataset.n_frames_valid=200', '+dataset.angle_range=110', '+dataset.pos_range=2', '+dataset.wo_updown=false', '+dataset.customized_validation=true', '+dataset.add_timestamp_embedding=true', '+dataset.use_explicit_memory_frames=false', 'algorithm.training_stage=stage_b_diffusion_frozen_memory', 'algorithm.use_mamba_memory_pipeline=true', 'algorithm.use_oracle_pose_eval=false', 'algorithm.enable_memory_noise_curriculum=false', '+algorithm.require_pose_prediction=false', '+algorithm.use_memory_attention=false', '+algorithm.relative_embedding=false', '+algorithm.memory_retrieval_topk=32', 'algorithm.diff_window_size=8', 'algorithm.memory_condition_length=0', 'algorithm.context_frames=100', '+algorithm.n_tokens=8', 'experiment.training.batch_size=8', 'experiment.training.checkpointing.every_n_train_steps=2500', 'experiment.training.max_steps=30000', 'experiment.validation.val_every_n_step=2500', '+output_dir=/proj/cvl/users/x_fahkh2/WorldMem_Repro/checkpoints/bimamba_stage_b/'] +Error executing job with overrides: ['+name=train_stage_b_mamba', 'algorithm=df_video_mamba3stage', '+customized_load=true', '+seperate_load=false', 'experiment.num_nodes=1', 'load=/proj/cvl/users/x_fahkh2/WorldMem_Repro/checkpoints/bimamba_stage_a_128/checkpoints/epoch0_step2000.ckpt', 'dataset.save_dir=/proj/cvl/users/x_fahkh2/WorldMem_Repro/datasets/minecraft', 'dataset.n_frames=200', '+dataset.n_frames_valid=200', '+dataset.angle_range=110', '+dataset.pos_range=2', '+dataset.wo_updown=false', '+dataset.customized_validation=true', '+dataset.add_timestamp_embedding=true', '+dataset.use_explicit_memory_frames=false', 'algorithm.training_stage=stage_b_diffusion_frozen_memory', 'algorithm.use_mamba_memory_pipeline=true', 'algorithm.use_oracle_pose_eval=false', 'algorithm.enable_memory_noise_curriculum=false', '+algorithm.require_pose_prediction=false', '+algorithm.use_memory_attention=false', '+algorithm.relative_embedding=false', '+algorithm.memory_retrieval_topk=32', 'algorithm.diff_window_size=8', 'algorithm.memory_condition_length=0', 'algorithm.context_frames=100', '+algorithm.n_tokens=8', 'experiment.training.batch_size=8', 'experiment.training.checkpointing.every_n_train_steps=2500', 'experiment.training.max_steps=30000', 'experiment.validation.val_every_n_step=2500', '+output_dir=/proj/cvl/users/x_fahkh2/WorldMem_Repro/checkpoints/bimamba_stage_b/'] +Error executing job with overrides: ['+name=train_stage_b_mamba', 'algorithm=df_video_mamba3stage', '+customized_load=true', '+seperate_load=false', 'experiment.num_nodes=1', 'load=/proj/cvl/users/x_fahkh2/WorldMem_Repro/checkpoints/bimamba_stage_a_128/checkpoints/epoch0_step2000.ckpt', 'dataset.save_dir=/proj/cvl/users/x_fahkh2/WorldMem_Repro/datasets/minecraft', 'dataset.n_frames=200', '+dataset.n_frames_valid=200', '+dataset.angle_range=110', '+dataset.pos_range=2', '+dataset.wo_updown=false', '+dataset.customized_validation=true', '+dataset.add_timestamp_embedding=true', '+dataset.use_explicit_memory_frames=false', 'algorithm.training_stage=stage_b_diffusion_frozen_memory', 'algorithm.use_mamba_memory_pipeline=true', 'algorithm.use_oracle_pose_eval=false', 'algorithm.enable_memory_noise_curriculum=false', '+algorithm.require_pose_prediction=false', '+algorithm.use_memory_attention=false', '+algorithm.relative_embedding=false', '+algorithm.memory_retrieval_topk=32', 'algorithm.diff_window_size=8', 'algorithm.memory_condition_length=0', 'algorithm.context_frames=100', '+algorithm.n_tokens=8', 'experiment.training.batch_size=8', 'experiment.training.checkpointing.every_n_train_steps=2500', 'experiment.training.max_steps=30000', 'experiment.validation.val_every_n_step=2500', '+output_dir=/proj/cvl/users/x_fahkh2/WorldMem_Repro/checkpoints/bimamba_stage_b/'] +[rank6]: Traceback (most recent call last): +[rank6]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/runpy.py", line 196, in _run_module_as_main +[rank6]: return _run_code(code, main_globals, None, +[rank6]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/runpy.py", line 86, in _run_code +[rank6]: exec(code, run_globals) +[rank6]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/main.py", line 202, in +[rank6]: run() # pylint: disable=no-value-for-parameter +[rank6]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/main.py", line 94, in decorated_main +[rank6]: _run_hydra( +[rank6]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/utils.py", line 394, in _run_hydra +[rank6]: _run_app( +[rank6]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/utils.py", line 457, in _run_app +[rank6]: run_and_report( +[rank6]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/utils.py", line 223, in run_and_report +[rank6]: raise ex +[rank6]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/utils.py", line 220, in run_and_report +[rank6]: return func() +[rank6]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/utils.py", line 458, in +[rank6]: lambda: hydra.run( +[rank6]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/hydra.py", line 132, in run +[rank6]: _ = ret.return_value +[rank6]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/core/utils.py", line 260, in return_value +[rank6]: raise self._return_value +[rank6]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/core/utils.py", line 186, in run_job +[rank6]: ret.return_value = task_function(task_cfg) +[rank6]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/main.py", line 198, in run +[rank6]: run_local(cfg) +[rank6]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/main.py", line 122, in run_local +[rank6]: experiment.exec_task(task) +[rank6]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/experiments/exp_base.py", line 172, in exec_task +[rank6]: getattr(self, task)() +[rank6]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/experiments/exp_base.py", line 357, in training +[rank6]: trainer.fit( +[rank6]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/trainer.py", line 544, in fit +[rank6]: call._call_and_handle_interrupt( +[rank6]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/call.py", line 43, in _call_and_handle_interrupt +[rank6]: return trainer.strategy.launcher.launch(trainer_fn, *args, trainer=trainer, **kwargs) +[rank6]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/launchers/subprocess_script.py", line 102, in launch +[rank6]: return function(*args, **kwargs) +[rank6]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/trainer.py", line 580, in _fit_impl +[rank6]: self._run(model, ckpt_path=ckpt_path) +[rank6]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/trainer.py", line 989, in _run +[rank6]: results = self._run_stage() +[rank6]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/trainer.py", line 1035, in _run_stage +[rank6]: self.fit_loop.run() +[rank6]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/fit_loop.py", line 202, in run +[rank6]: self.advance() +[rank6]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/fit_loop.py", line 359, in advance +[rank6]: self.epoch_loop.run(self._data_fetcher) +[rank6]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/training_epoch_loop.py", line 136, in run +[rank6]: self.advance(data_fetcher) +[rank6]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/training_epoch_loop.py", line 240, in advance +[rank6]: batch_output = self.automatic_optimization.run(trainer.optimizers[0], batch_idx, kwargs) +[rank6]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/optimization/automatic.py", line 187, in run +[rank6]: self._optimizer_step(batch_idx, closure) +[rank6]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/optimization/automatic.py", line 265, in _optimizer_step +[rank6]: call._call_lightning_module_hook( +[rank6]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/call.py", line 157, in _call_lightning_module_hook +[rank6]: output = fn(*args, **kwargs) +[rank6]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/algorithms/worldmem/df_base.py", line 65, in optimizer_step +[rank6]: optimizer.step(closure=optimizer_closure) +[rank6]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/core/optimizer.py", line 151, in step +[rank6]: step_output = self._strategy.optimizer_step(self._optimizer, closure, **kwargs) +[rank6]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/ddp.py", line 265, in optimizer_step +[rank6]: optimizer_output = super().optimizer_step(optimizer, closure, model, **kwargs) +[rank6]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/strategy.py", line 230, in optimizer_step +[rank6]: return self.precision_plugin.optimizer_step(optimizer, model=model, closure=closure, **kwargs) +[rank6]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/plugins/precision/amp.py", line 77, in optimizer_step +[rank6]: closure_result = closure() +[rank6]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/optimization/automatic.py", line 140, in __call__ +[rank6]: self._result = self.closure(*args, **kwargs) +[rank6]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 116, in decorate_context +[rank6]: return func(*args, **kwargs) +[rank6]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/optimization/automatic.py", line 126, in closure +[rank6]: step_output = self._step_fn() +[rank6]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/optimization/automatic.py", line 315, in _training_step +[rank6]: training_step_output = call._call_strategy_hook(trainer, "training_step", *kwargs.values()) +[rank6]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/call.py", line 309, in _call_strategy_hook +[rank6]: output = fn(*args, **kwargs) +[rank6]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/strategy.py", line 381, in training_step +[rank6]: return self._forward_redirection(self.model, self.lightning_module, "training_step", *args, **kwargs) +[rank6]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/strategy.py", line 633, in __call__ +[rank6]: wrapper_output = wrapper_module(*args, **kwargs) +[rank6]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1553, in _wrapped_call_impl +[rank6]: return self._call_impl(*args, **kwargs) +[rank6]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1562, in _call_impl +[rank6]: return forward_call(*args, **kwargs) +[rank6]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/parallel/distributed.py", line 1636, in forward +[rank6]: else self._run_ddp_forward(*inputs, **kwargs) +[rank6]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/parallel/distributed.py", line 1454, in _run_ddp_forward +[rank6]: return self.module(*inputs, **kwargs) # type: ignore[index] +[rank6]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1553, in _wrapped_call_impl +[rank6]: return self._call_impl(*args, **kwargs) +[rank6]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1562, in _call_impl +[rank6]: return forward_call(*args, **kwargs) +[rank6]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/strategy.py", line 626, in wrapped_forward +[rank6]: out = method(*_args, **_kwargs) +[rank6]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/algorithms/worldmem/df_video_mamba3stage.py", line 1073, in training_step +[rank6]: self.log("training/curriculum_phase", float(phase_idx)) +[rank6]: TypeError: float() argument must be a string or a real number, not 'NoneType' +[rank5]: Traceback (most recent call last): +[rank5]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/runpy.py", line 196, in _run_module_as_main +[rank5]: return _run_code(code, main_globals, None, +[rank5]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/runpy.py", line 86, in _run_code +[rank5]: exec(code, run_globals) +[rank5]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/main.py", line 202, in +[rank5]: run() # pylint: disable=no-value-for-parameter +[rank5]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/main.py", line 94, in decorated_main +[rank5]: _run_hydra( +[rank5]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/utils.py", line 394, in _run_hydra +[rank5]: _run_app( +[rank5]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/utils.py", line 457, in _run_app +[rank5]: run_and_report( +[rank5]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/utils.py", line 223, in run_and_report +[rank5]: raise ex +[rank5]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/utils.py", line 220, in run_and_report +[rank5]: return func() +[rank5]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/utils.py", line 458, in +[rank5]: lambda: hydra.run( +[rank5]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/hydra.py", line 132, in run +[rank5]: _ = ret.return_value +[rank5]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/core/utils.py", line 260, in return_value +[rank5]: raise self._return_value +[rank5]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/core/utils.py", line 186, in run_job +[rank5]: ret.return_value = task_function(task_cfg) +[rank5]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/main.py", line 198, in run +[rank5]: run_local(cfg) +[rank5]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/main.py", line 122, in run_local +[rank5]: experiment.exec_task(task) +[rank5]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/experiments/exp_base.py", line 172, in exec_task +[rank5]: getattr(self, task)() +[rank5]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/experiments/exp_base.py", line 357, in training +[rank5]: trainer.fit( +[rank5]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/trainer.py", line 544, in fit +[rank5]: call._call_and_handle_interrupt( +[rank5]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/call.py", line 43, in _call_and_handle_interrupt +[rank5]: return trainer.strategy.launcher.launch(trainer_fn, *args, trainer=trainer, **kwargs) +[rank5]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/launchers/subprocess_script.py", line 102, in launch +[rank5]: return function(*args, **kwargs) +[rank5]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/trainer.py", line 580, in _fit_impl +[rank5]: self._run(model, ckpt_path=ckpt_path) +[rank5]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/trainer.py", line 989, in _run +[rank5]: results = self._run_stage() +[rank5]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/trainer.py", line 1035, in _run_stage +[rank5]: self.fit_loop.run() +[rank5]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/fit_loop.py", line 202, in run +[rank5]: self.advance() +[rank5]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/fit_loop.py", line 359, in advance +[rank5]: self.epoch_loop.run(self._data_fetcher) +[rank5]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/training_epoch_loop.py", line 136, in run +[rank5]: self.advance(data_fetcher) +[rank5]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/training_epoch_loop.py", line 240, in advance +[rank5]: batch_output = self.automatic_optimization.run(trainer.optimizers[0], batch_idx, kwargs) +[rank5]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/optimization/automatic.py", line 187, in run +[rank5]: self._optimizer_step(batch_idx, closure) +[rank5]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/optimization/automatic.py", line 265, in _optimizer_step +[rank5]: call._call_lightning_module_hook( +[rank5]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/call.py", line 157, in _call_lightning_module_hook +[rank5]: output = fn(*args, **kwargs) +[rank5]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/algorithms/worldmem/df_base.py", line 65, in optimizer_step +[rank5]: optimizer.step(closure=optimizer_closure) +[rank5]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/core/optimizer.py", line 151, in step +[rank5]: step_output = self._strategy.optimizer_step(self._optimizer, closure, **kwargs) +[rank5]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/ddp.py", line 265, in optimizer_step +[rank5]: optimizer_output = super().optimizer_step(optimizer, closure, model, **kwargs) +[rank5]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/strategy.py", line 230, in optimizer_step +[rank5]: return self.precision_plugin.optimizer_step(optimizer, model=model, closure=closure, **kwargs) +[rank5]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/plugins/precision/amp.py", line 77, in optimizer_step +[rank5]: closure_result = closure() +[rank5]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/optimization/automatic.py", line 140, in __call__ +[rank5]: self._result = self.closure(*args, **kwargs) +[rank5]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 116, in decorate_context +[rank5]: return func(*args, **kwargs) +[rank5]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/optimization/automatic.py", line 126, in closure +[rank5]: step_output = self._step_fn() +[rank5]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/optimization/automatic.py", line 315, in _training_step +[rank5]: training_step_output = call._call_strategy_hook(trainer, "training_step", *kwargs.values()) +[rank5]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/call.py", line 309, in _call_strategy_hook +[rank5]: output = fn(*args, **kwargs) +[rank5]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/strategy.py", line 381, in training_step +[rank5]: return self._forward_redirection(self.model, self.lightning_module, "training_step", *args, **kwargs) +[rank5]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/strategy.py", line 633, in __call__ +[rank5]: wrapper_output = wrapper_module(*args, **kwargs) +[rank5]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1553, in _wrapped_call_impl +[rank5]: return self._call_impl(*args, **kwargs) +[rank5]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1562, in _call_impl +[rank5]: return forward_call(*args, **kwargs) +[rank5]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/parallel/distributed.py", line 1636, in forward +[rank5]: else self._run_ddp_forward(*inputs, **kwargs) +[rank5]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/parallel/distributed.py", line 1454, in _run_ddp_forward +[rank5]: return self.module(*inputs, **kwargs) # type: ignore[index] +[rank5]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1553, in _wrapped_call_impl +[rank5]: return self._call_impl(*args, **kwargs) +[rank5]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1562, in _call_impl +[rank5]: return forward_call(*args, **kwargs) +[rank5]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/strategy.py", line 626, in wrapped_forward +[rank5]: out = method(*_args, **_kwargs) +[rank5]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/algorithms/worldmem/df_video_mamba3stage.py", line 1073, in training_step +[rank5]: self.log("training/curriculum_phase", float(phase_idx)) +[rank5]: TypeError: float() argument must be a string or a real number, not 'NoneType' +Error executing job with overrides: ['+name=train_stage_b_mamba', 'algorithm=df_video_mamba3stage', '+customized_load=true', '+seperate_load=false', 'experiment.num_nodes=1', 'load=/proj/cvl/users/x_fahkh2/WorldMem_Repro/checkpoints/bimamba_stage_a_128/checkpoints/epoch0_step2000.ckpt', 'dataset.save_dir=/proj/cvl/users/x_fahkh2/WorldMem_Repro/datasets/minecraft', 'dataset.n_frames=200', '+dataset.n_frames_valid=200', '+dataset.angle_range=110', '+dataset.pos_range=2', '+dataset.wo_updown=false', '+dataset.customized_validation=true', '+dataset.add_timestamp_embedding=true', '+dataset.use_explicit_memory_frames=false', 'algorithm.training_stage=stage_b_diffusion_frozen_memory', 'algorithm.use_mamba_memory_pipeline=true', 'algorithm.use_oracle_pose_eval=false', 'algorithm.enable_memory_noise_curriculum=false', '+algorithm.require_pose_prediction=false', '+algorithm.use_memory_attention=false', '+algorithm.relative_embedding=false', '+algorithm.memory_retrieval_topk=32', 'algorithm.diff_window_size=8', 'algorithm.memory_condition_length=0', 'algorithm.context_frames=100', '+algorithm.n_tokens=8', 'experiment.training.batch_size=8', 'experiment.training.checkpointing.every_n_train_steps=2500', 'experiment.training.max_steps=30000', 'experiment.validation.val_every_n_step=2500', '+output_dir=/proj/cvl/users/x_fahkh2/WorldMem_Repro/checkpoints/bimamba_stage_b/'] +[rank1]: Traceback (most recent call last): +[rank1]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/runpy.py", line 196, in _run_module_as_main +[rank1]: return _run_code(code, main_globals, None, +[rank1]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/runpy.py", line 86, in _run_code +[rank1]: exec(code, run_globals) +[rank1]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/main.py", line 202, in +[rank1]: run() # pylint: disable=no-value-for-parameter +[rank1]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/main.py", line 94, in decorated_main +[rank1]: _run_hydra( +[rank1]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/utils.py", line 394, in _run_hydra +[rank1]: _run_app( +[rank1]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/utils.py", line 457, in _run_app +[rank1]: run_and_report( +[rank1]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/utils.py", line 223, in run_and_report +[rank1]: raise ex +[rank1]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/utils.py", line 220, in run_and_report +[rank1]: return func() +[rank1]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/utils.py", line 458, in +[rank1]: lambda: hydra.run( +[rank1]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/hydra.py", line 132, in run +[rank1]: _ = ret.return_value +[rank1]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/core/utils.py", line 260, in return_value +[rank1]: raise self._return_value +[rank1]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/core/utils.py", line 186, in run_job +[rank1]: ret.return_value = task_function(task_cfg) +[rank1]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/main.py", line 198, in run +[rank1]: run_local(cfg) +[rank1]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/main.py", line 122, in run_local +[rank1]: experiment.exec_task(task) +[rank1]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/experiments/exp_base.py", line 172, in exec_task +[rank1]: getattr(self, task)() +[rank1]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/experiments/exp_base.py", line 357, in training +[rank1]: trainer.fit( +[rank1]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/trainer.py", line 544, in fit +[rank1]: call._call_and_handle_interrupt( +[rank1]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/call.py", line 43, in _call_and_handle_interrupt +[rank1]: return trainer.strategy.launcher.launch(trainer_fn, *args, trainer=trainer, **kwargs) +[rank1]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/launchers/subprocess_script.py", line 102, in launch +[rank1]: return function(*args, **kwargs) +[rank1]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/trainer.py", line 580, in _fit_impl +[rank1]: self._run(model, ckpt_path=ckpt_path) +[rank1]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/trainer.py", line 989, in _run +[rank1]: results = self._run_stage() +[rank1]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/trainer.py", line 1035, in _run_stage +[rank1]: self.fit_loop.run() +[rank1]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/fit_loop.py", line 202, in run +[rank1]: self.advance() +[rank1]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/fit_loop.py", line 359, in advance +[rank1]: self.epoch_loop.run(self._data_fetcher) +[rank1]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/training_epoch_loop.py", line 136, in run +[rank1]: self.advance(data_fetcher) +[rank1]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/training_epoch_loop.py", line 240, in advance +[rank1]: batch_output = self.automatic_optimization.run(trainer.optimizers[0], batch_idx, kwargs) +[rank1]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/optimization/automatic.py", line 187, in run +[rank1]: self._optimizer_step(batch_idx, closure) +[rank1]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/optimization/automatic.py", line 265, in _optimizer_step +[rank1]: call._call_lightning_module_hook( +[rank1]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/call.py", line 157, in _call_lightning_module_hook +[rank1]: output = fn(*args, **kwargs) +[rank1]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/algorithms/worldmem/df_base.py", line 65, in optimizer_step +[rank1]: optimizer.step(closure=optimizer_closure) +[rank1]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/core/optimizer.py", line 151, in step +[rank1]: step_output = self._strategy.optimizer_step(self._optimizer, closure, **kwargs) +[rank1]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/ddp.py", line 265, in optimizer_step +[rank1]: optimizer_output = super().optimizer_step(optimizer, closure, model, **kwargs) +[rank1]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/strategy.py", line 230, in optimizer_step +[rank1]: return self.precision_plugin.optimizer_step(optimizer, model=model, closure=closure, **kwargs) +[rank1]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/plugins/precision/amp.py", line 77, in optimizer_step +[rank1]: closure_result = closure() +[rank1]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/optimization/automatic.py", line 140, in __call__ +[rank1]: self._result = self.closure(*args, **kwargs) +[rank1]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 116, in decorate_context +[rank1]: return func(*args, **kwargs) +[rank1]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/optimization/automatic.py", line 126, in closure +[rank1]: step_output = self._step_fn() +[rank1]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/optimization/automatic.py", line 315, in _training_step +[rank1]: training_step_output = call._call_strategy_hook(trainer, "training_step", *kwargs.values()) +[rank1]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/call.py", line 309, in _call_strategy_hook +[rank1]: output = fn(*args, **kwargs) +[rank1]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/strategy.py", line 381, in training_step +[rank1]: return self._forward_redirection(self.model, self.lightning_module, "training_step", *args, **kwargs) +[rank1]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/strategy.py", line 633, in __call__ +[rank1]: wrapper_output = wrapper_module(*args, **kwargs) +[rank1]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1553, in _wrapped_call_impl +[rank1]: return self._call_impl(*args, **kwargs) +[rank1]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1562, in _call_impl +[rank1]: return forward_call(*args, **kwargs) +[rank1]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/parallel/distributed.py", line 1636, in forward +[rank1]: else self._run_ddp_forward(*inputs, **kwargs) +[rank1]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/parallel/distributed.py", line 1454, in _run_ddp_forward +[rank1]: return self.module(*inputs, **kwargs) # type: ignore[index] +[rank1]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1553, in _wrapped_call_impl +[rank1]: return self._call_impl(*args, **kwargs) +[rank1]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1562, in _call_impl +[rank1]: return forward_call(*args, **kwargs) +[rank1]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/strategy.py", line 626, in wrapped_forward +[rank1]: out = method(*_args, **_kwargs) +[rank1]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/algorithms/worldmem/df_video_mamba3stage.py", line 1073, in training_step +[rank1]: self.log("training/curriculum_phase", float(phase_idx)) +[rank1]: TypeError: float() argument must be a string or a real number, not 'NoneType' +[rank3]: Traceback (most recent call last): +[rank3]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/runpy.py", line 196, in _run_module_as_main +[rank3]: return _run_code(code, main_globals, None, +[rank3]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/runpy.py", line 86, in _run_code +[rank3]: exec(code, run_globals) +[rank3]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/main.py", line 202, in +[rank3]: run() # pylint: disable=no-value-for-parameter +[rank3]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/main.py", line 94, in decorated_main +[rank3]: _run_hydra( +[rank3]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/utils.py", line 394, in _run_hydra +[rank3]: _run_app( +[rank3]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/utils.py", line 457, in _run_app +[rank3]: run_and_report( +[rank3]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/utils.py", line 223, in run_and_report +[rank3]: raise ex +[rank3]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/utils.py", line 220, in run_and_report +[rank3]: return func() +[rank3]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/utils.py", line 458, in +[rank3]: lambda: hydra.run( +[rank3]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/hydra.py", line 132, in run +[rank3]: _ = ret.return_value +[rank3]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/core/utils.py", line 260, in return_value +[rank3]: raise self._return_value +[rank3]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/core/utils.py", line 186, in run_job +[rank3]: ret.return_value = task_function(task_cfg) +[rank3]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/main.py", line 198, in run +[rank3]: run_local(cfg) +[rank3]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/main.py", line 122, in run_local +[rank3]: experiment.exec_task(task) +[rank3]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/experiments/exp_base.py", line 172, in exec_task +[rank3]: getattr(self, task)() +[rank3]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/experiments/exp_base.py", line 357, in training +[rank3]: trainer.fit( +[rank3]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/trainer.py", line 544, in fit +[rank3]: call._call_and_handle_interrupt( +[rank3]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/call.py", line 43, in _call_and_handle_interrupt +[rank3]: return trainer.strategy.launcher.launch(trainer_fn, *args, trainer=trainer, **kwargs) +[rank3]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/launchers/subprocess_script.py", line 102, in launch +[rank3]: return function(*args, **kwargs) +[rank3]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/trainer.py", line 580, in _fit_impl +[rank3]: self._run(model, ckpt_path=ckpt_path) +[rank3]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/trainer.py", line 989, in _run +[rank3]: results = self._run_stage() +[rank3]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/trainer.py", line 1035, in _run_stage +[rank3]: self.fit_loop.run() +[rank3]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/fit_loop.py", line 202, in run +[rank3]: self.advance() +[rank3]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/fit_loop.py", line 359, in advance +[rank3]: self.epoch_loop.run(self._data_fetcher) +[rank3]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/training_epoch_loop.py", line 136, in run +[rank3]: self.advance(data_fetcher) +[rank3]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/training_epoch_loop.py", line 240, in advance +[rank3]: batch_output = self.automatic_optimization.run(trainer.optimizers[0], batch_idx, kwargs) +[rank3]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/optimization/automatic.py", line 187, in run +[rank3]: self._optimizer_step(batch_idx, closure) +[rank3]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/optimization/automatic.py", line 265, in _optimizer_step +[rank3]: call._call_lightning_module_hook( +[rank3]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/call.py", line 157, in _call_lightning_module_hook +[rank3]: output = fn(*args, **kwargs) +[rank3]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/algorithms/worldmem/df_base.py", line 65, in optimizer_step +[rank3]: optimizer.step(closure=optimizer_closure) +[rank3]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/core/optimizer.py", line 151, in step +[rank3]: step_output = self._strategy.optimizer_step(self._optimizer, closure, **kwargs) +[rank3]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/ddp.py", line 265, in optimizer_step +[rank3]: optimizer_output = super().optimizer_step(optimizer, closure, model, **kwargs) +[rank3]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/strategy.py", line 230, in optimizer_step +[rank3]: return self.precision_plugin.optimizer_step(optimizer, model=model, closure=closure, **kwargs) +[rank3]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/plugins/precision/amp.py", line 77, in optimizer_step +[rank3]: closure_result = closure() +[rank3]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/optimization/automatic.py", line 140, in __call__ +[rank3]: self._result = self.closure(*args, **kwargs) +[rank3]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 116, in decorate_context +[rank3]: return func(*args, **kwargs) +[rank3]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/optimization/automatic.py", line 126, in closure +[rank3]: step_output = self._step_fn() +[rank3]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/optimization/automatic.py", line 315, in _training_step +[rank3]: training_step_output = call._call_strategy_hook(trainer, "training_step", *kwargs.values()) +[rank3]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/call.py", line 309, in _call_strategy_hook +[rank3]: output = fn(*args, **kwargs) +[rank3]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/strategy.py", line 381, in training_step +[rank3]: return self._forward_redirection(self.model, self.lightning_module, "training_step", *args, **kwargs) +[rank3]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/strategy.py", line 633, in __call__ +[rank3]: wrapper_output = wrapper_module(*args, **kwargs) +[rank3]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1553, in _wrapped_call_impl +[rank3]: return self._call_impl(*args, **kwargs) +[rank3]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1562, in _call_impl +[rank3]: return forward_call(*args, **kwargs) +[rank3]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/parallel/distributed.py", line 1636, in forward +[rank3]: else self._run_ddp_forward(*inputs, **kwargs) +[rank3]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/parallel/distributed.py", line 1454, in _run_ddp_forward +[rank3]: return self.module(*inputs, **kwargs) # type: ignore[index] +[rank3]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1553, in _wrapped_call_impl +[rank3]: return self._call_impl(*args, **kwargs) +[rank3]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1562, in _call_impl +[rank3]: return forward_call(*args, **kwargs) +[rank3]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/strategy.py", line 626, in wrapped_forward +[rank3]: out = method(*_args, **_kwargs) +[rank3]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/algorithms/worldmem/df_video_mamba3stage.py", line 1073, in training_step +[rank3]: self.log("training/curriculum_phase", float(phase_idx)) +[rank3]: TypeError: float() argument must be a string or a real number, not 'NoneType' +Error executing job with overrides: ['+name=train_stage_b_mamba', 'algorithm=df_video_mamba3stage', '+customized_load=true', '+seperate_load=false', 'experiment.num_nodes=1', 'load=/proj/cvl/users/x_fahkh2/WorldMem_Repro/checkpoints/bimamba_stage_a_128/checkpoints/epoch0_step2000.ckpt', 'dataset.save_dir=/proj/cvl/users/x_fahkh2/WorldMem_Repro/datasets/minecraft', 'dataset.n_frames=200', '+dataset.n_frames_valid=200', '+dataset.angle_range=110', '+dataset.pos_range=2', '+dataset.wo_updown=false', '+dataset.customized_validation=true', '+dataset.add_timestamp_embedding=true', '+dataset.use_explicit_memory_frames=false', 'algorithm.training_stage=stage_b_diffusion_frozen_memory', 'algorithm.use_mamba_memory_pipeline=true', 'algorithm.use_oracle_pose_eval=false', 'algorithm.enable_memory_noise_curriculum=false', '+algorithm.require_pose_prediction=false', '+algorithm.use_memory_attention=false', '+algorithm.relative_embedding=false', '+algorithm.memory_retrieval_topk=32', 'algorithm.diff_window_size=8', 'algorithm.memory_condition_length=0', 'algorithm.context_frames=100', '+algorithm.n_tokens=8', 'experiment.training.batch_size=8', 'experiment.training.checkpointing.every_n_train_steps=2500', 'experiment.training.max_steps=30000', 'experiment.validation.val_every_n_step=2500', '+output_dir=/proj/cvl/users/x_fahkh2/WorldMem_Repro/checkpoints/bimamba_stage_b/'] +Traceback (most recent call last): + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/runpy.py", line 196, in _run_module_as_main + return _run_code(code, main_globals, None, + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/runpy.py", line 86, in _run_code + exec(code, run_globals) + File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/main.py", line 202, in + run() # pylint: disable=no-value-for-parameter + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/main.py", line 94, in decorated_main + _run_hydra( + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/utils.py", line 394, in _run_hydra + _run_app( + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/utils.py", line 457, in _run_app + run_and_report( + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/utils.py", line 223, in run_and_report + raise ex + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/utils.py", line 220, in run_and_report + return func() + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/utils.py", line 458, in + lambda: hydra.run( + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/hydra.py", line 132, in run + _ = ret.return_value + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/core/utils.py", line 260, in return_value + raise self._return_value + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/core/utils.py", line 186, in run_job + ret.return_value = task_function(task_cfg) + File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/main.py", line 198, in run + run_local(cfg) + File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/main.py", line 122, in run_local + experiment.exec_task(task) + File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/experiments/exp_base.py", line 172, in exec_task + getattr(self, task)() + File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/experiments/exp_base.py", line 357, in training + trainer.fit( + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/trainer.py", line 544, in fit + call._call_and_handle_interrupt( + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/call.py", line 43, in _call_and_handle_interrupt + return trainer.strategy.launcher.launch(trainer_fn, *args, trainer=trainer, **kwargs) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/launchers/subprocess_script.py", line 102, in launch + return function(*args, **kwargs) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/trainer.py", line 580, in _fit_impl + self._run(model, ckpt_path=ckpt_path) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/trainer.py", line 989, in _run + results = self._run_stage() + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/trainer.py", line 1035, in _run_stage + self.fit_loop.run() + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/fit_loop.py", line 202, in run + self.advance() + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/fit_loop.py", line 359, in advance + self.epoch_loop.run(self._data_fetcher) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/training_epoch_loop.py", line 136, in run + self.advance(data_fetcher) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/training_epoch_loop.py", line 240, in advance + batch_output = self.automatic_optimization.run(trainer.optimizers[0], batch_idx, kwargs) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/optimization/automatic.py", line 187, in run + self._optimizer_step(batch_idx, closure) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/optimization/automatic.py", line 265, in _optimizer_step + call._call_lightning_module_hook( + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/call.py", line 157, in _call_lightning_module_hook + output = fn(*args, **kwargs) + File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/algorithms/worldmem/df_base.py", line 65, in optimizer_step + optimizer.step(closure=optimizer_closure) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/core/optimizer.py", line 151, in step + step_output = self._strategy.optimizer_step(self._optimizer, closure, **kwargs) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/ddp.py", line 265, in optimizer_step + optimizer_output = super().optimizer_step(optimizer, closure, model, **kwargs) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/strategy.py", line 230, in optimizer_step + return self.precision_plugin.optimizer_step(optimizer, model=model, closure=closure, **kwargs) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/plugins/precision/amp.py", line 77, in optimizer_step + closure_result = closure() + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/optimization/automatic.py", line 140, in __call__ + self._result = self.closure(*args, **kwargs) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 116, in decorate_context + return func(*args, **kwargs) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/optimization/automatic.py", line 126, in closure + step_output = self._step_fn() + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/optimization/automatic.py", line 315, in _training_step + training_step_output = call._call_strategy_hook(trainer, "training_step", *kwargs.values()) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/call.py", line 309, in _call_strategy_hook + output = fn(*args, **kwargs) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/strategy.py", line 381, in training_step + return self._forward_redirection(self.model, self.lightning_module, "training_step", *args, **kwargs) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/strategy.py", line 633, in __call__ + wrapper_output = wrapper_module(*args, **kwargs) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1553, in _wrapped_call_impl + return self._call_impl(*args, **kwargs) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1562, in _call_impl + return forward_call(*args, **kwargs) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/parallel/distributed.py", line 1636, in forward + else self._run_ddp_forward(*inputs, **kwargs) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/parallel/distributed.py", line 1454, in _run_ddp_forward + return self.module(*inputs, **kwargs) # type: ignore[index] + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1553, in _wrapped_call_impl + return self._call_impl(*args, **kwargs) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1562, in _call_impl + return forward_call(*args, **kwargs) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/strategy.py", line 626, in wrapped_forward + out = method(*_args, **_kwargs) + File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/algorithms/worldmem/df_video_mamba3stage.py", line 1073, in training_step + self.log("training/curriculum_phase", float(phase_idx)) +TypeError: float() argument must be a string or a real number, not 'NoneType' +[rank0]: Traceback (most recent call last): +[rank0]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/runpy.py", line 196, in _run_module_as_main +[rank0]: return _run_code(code, main_globals, None, +[rank0]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/runpy.py", line 86, in _run_code +[rank0]: exec(code, run_globals) +[rank0]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/main.py", line 202, in +[rank0]: run() # pylint: disable=no-value-for-parameter +[rank0]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/main.py", line 94, in decorated_main +[rank0]: _run_hydra( +[rank0]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/utils.py", line 394, in _run_hydra +[rank0]: _run_app( +[rank0]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/utils.py", line 457, in _run_app +[rank0]: run_and_report( +[rank0]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/utils.py", line 223, in run_and_report +[rank0]: raise ex +[rank0]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/utils.py", line 220, in run_and_report +[rank0]: return func() +[rank0]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/utils.py", line 458, in +[rank0]: lambda: hydra.run( +[rank0]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/hydra.py", line 132, in run +[rank0]: _ = ret.return_value +[rank0]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/core/utils.py", line 260, in return_value +[rank0]: raise self._return_value +[rank0]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/core/utils.py", line 186, in run_job +[rank0]: ret.return_value = task_function(task_cfg) +[rank0]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/main.py", line 198, in run +[rank0]: run_local(cfg) +[rank0]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/main.py", line 122, in run_local +[rank0]: experiment.exec_task(task) +[rank0]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/experiments/exp_base.py", line 172, in exec_task +[rank0]: getattr(self, task)() +[rank0]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/experiments/exp_base.py", line 357, in training +[rank0]: trainer.fit( +[rank0]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/trainer.py", line 544, in fit +[rank0]: call._call_and_handle_interrupt( +[rank0]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/call.py", line 43, in _call_and_handle_interrupt +[rank0]: return trainer.strategy.launcher.launch(trainer_fn, *args, trainer=trainer, **kwargs) +[rank0]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/launchers/subprocess_script.py", line 102, in launch +[rank0]: return function(*args, **kwargs) +[rank0]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/trainer.py", line 580, in _fit_impl +[rank0]: self._run(model, ckpt_path=ckpt_path) +[rank0]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/trainer.py", line 989, in _run +[rank0]: results = self._run_stage() +[rank0]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/trainer.py", line 1035, in _run_stage +[rank0]: self.fit_loop.run() +[rank0]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/fit_loop.py", line 202, in run +[rank0]: self.advance() +[rank0]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/fit_loop.py", line 359, in advance +[rank0]: self.epoch_loop.run(self._data_fetcher) +[rank0]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/training_epoch_loop.py", line 136, in run +[rank0]: self.advance(data_fetcher) +[rank0]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/training_epoch_loop.py", line 240, in advance +[rank0]: batch_output = self.automatic_optimization.run(trainer.optimizers[0], batch_idx, kwargs) +[rank0]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/optimization/automatic.py", line 187, in run +[rank0]: self._optimizer_step(batch_idx, closure) +[rank0]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/optimization/automatic.py", line 265, in _optimizer_step +[rank0]: call._call_lightning_module_hook( +[rank0]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/call.py", line 157, in _call_lightning_module_hook +[rank0]: output = fn(*args, **kwargs) +[rank0]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/algorithms/worldmem/df_base.py", line 65, in optimizer_step +[rank0]: optimizer.step(closure=optimizer_closure) +[rank0]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/core/optimizer.py", line 151, in step +[rank0]: step_output = self._strategy.optimizer_step(self._optimizer, closure, **kwargs) +[rank0]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/ddp.py", line 265, in optimizer_step +[rank0]: optimizer_output = super().optimizer_step(optimizer, closure, model, **kwargs) +[rank0]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/strategy.py", line 230, in optimizer_step +[rank0]: return self.precision_plugin.optimizer_step(optimizer, model=model, closure=closure, **kwargs) +[rank0]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/plugins/precision/amp.py", line 77, in optimizer_step +[rank0]: closure_result = closure() +[rank0]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/optimization/automatic.py", line 140, in __call__ +[rank0]: self._result = self.closure(*args, **kwargs) +[rank0]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 116, in decorate_context +[rank0]: return func(*args, **kwargs) +[rank0]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/optimization/automatic.py", line 126, in closure +[rank0]: step_output = self._step_fn() +[rank0]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/optimization/automatic.py", line 315, in _training_step +[rank0]: training_step_output = call._call_strategy_hook(trainer, "training_step", *kwargs.values()) +[rank0]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/call.py", line 309, in _call_strategy_hook +[rank0]: output = fn(*args, **kwargs) +[rank0]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/strategy.py", line 381, in training_step +[rank0]: return self._forward_redirection(self.model, self.lightning_module, "training_step", *args, **kwargs) +[rank0]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/strategy.py", line 633, in __call__ +[rank0]: wrapper_output = wrapper_module(*args, **kwargs) +[rank0]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1553, in _wrapped_call_impl +[rank0]: return self._call_impl(*args, **kwargs) +[rank0]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1562, in _call_impl +[rank0]: return forward_call(*args, **kwargs) +[rank0]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/parallel/distributed.py", line 1636, in forward +[rank0]: else self._run_ddp_forward(*inputs, **kwargs) +[rank0]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/parallel/distributed.py", line 1454, in _run_ddp_forward +[rank0]: return self.module(*inputs, **kwargs) # type: ignore[index] +[rank0]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1553, in _wrapped_call_impl +[rank0]: return self._call_impl(*args, **kwargs) +[rank0]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1562, in _call_impl +[rank0]: return forward_call(*args, **kwargs) +[rank0]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/strategy.py", line 626, in wrapped_forward +[rank0]: out = method(*_args, **_kwargs) +[rank0]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/algorithms/worldmem/df_video_mamba3stage.py", line 1073, in training_step +[rank0]: self.log("training/curriculum_phase", float(phase_idx)) +[rank0]: TypeError: float() argument must be a string or a real number, not 'NoneType' +srun: error: node109: task 4: Exited with exit code 1 +srun: Terminating StepId=7382.0 +[2026-03-11T19:11:21.584] error: *** STEP 7382.0 ON node109 CANCELLED AT 2026-03-11T19:11:21 DUE TO TASK FAILURE *** +srun: error: node109: task 7: Exited with exit code 1 +srun: error: node109: task 2: Terminated +srun: error: node109: task 3: Terminated +srun: error: node109: task 5: Terminated +srun: error: node109: task 1: Terminated +srun: error: node109: task 6: Terminated +wandb: - 0.000 MB of 0.000 MB uploaded wandb: You can sync this run to the cloud by running: +wandb: wandb sync /proj/cvl/users/x_fahkh2/WorldMem_Repro/checkpoints/bimamba_stage_b/wandb/offline-run-20260311_191040-stage_b_offline +wandb: Find logs at: ./checkpoints/bimamba_stage_b/wandb/offline-run-20260311_191040-stage_b_offline/logs +wandb: WARNING The new W&B backend becomes opt-out in version 0.18.0; try it out with `wandb.require("core")`! See https://wandb.me/wandb-core for more information. + Training: | | 0/? [00:00 + run() # pylint: disable=no-value-for-parameter + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/main.py", line 94, in decorated_main + _run_hydra( + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/utils.py", line 394, in _run_hydra + _run_app( + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/utils.py", line 457, in _run_app + run_and_report( + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/utils.py", line 223, in run_and_report + raise ex + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/utils.py", line 220, in run_and_report + return func() + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/utils.py", line 458, in + lambda: hydra.run( + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/hydra.py", line 132, in run + _ = ret.return_value + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/core/utils.py", line 260, in return_value + raise self._return_value + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/core/utils.py", line 186, in run_job + ret.return_value = task_function(task_cfg) + File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/main.py", line 198, in run + run_local(cfg) + File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/main.py", line 122, in run_local + experiment.exec_task(task) + File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/experiments/exp_base.py", line 172, in exec_task + getattr(self, task)() + File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/experiments/exp_base.py", line 371, in training + trainer.fit( + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/trainer.py", line 544, in fit + call._call_and_handle_interrupt( + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/call.py", line 43, in _call_and_handle_interrupt + return trainer.strategy.launcher.launch(trainer_fn, *args, trainer=trainer, **kwargs) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/launchers/subprocess_script.py", line 102, in launch + return function(*args, **kwargs) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/trainer.py", line 580, in _fit_impl + self._run(model, ckpt_path=ckpt_path) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/trainer.py", line 989, in _run + results = self._run_stage() + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/trainer.py", line 1035, in _run_stage + self.fit_loop.run() + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/fit_loop.py", line 202, in run + self.advance() + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/fit_loop.py", line 359, in advance + self.epoch_loop.run(self._data_fetcher) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/training_epoch_loop.py", line 136, in run + self.advance(data_fetcher) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/training_epoch_loop.py", line 240, in advance + batch_output = self.automatic_optimization.run(trainer.optimizers[0], batch_idx, kwargs) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/optimization/automatic.py", line 187, in run + self._optimizer_step(batch_idx, closure) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/optimization/automatic.py", line 265, in _optimizer_step + call._call_lightning_module_hook( + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/call.py", line 157, in _call_lightning_module_hook + output = fn(*args, **kwargs) + File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/algorithms/worldmem/df_base.py", line 65, in optimizer_step + optimizer.step(closure=optimizer_closure) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/core/optimizer.py", line 151, in step + step_output = self._strategy.optimizer_step(self._optimizer, closure, **kwargs) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/ddp.py", line 265, in optimizer_step + optimizer_output = super().optimizer_step(optimizer, closure, model, **kwargs) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/strategy.py", line 230, in optimizer_step + return self.precision_plugin.optimizer_step(optimizer, model=model, closure=closure, **kwargs) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/plugins/precision/amp.py", line 77, in optimizer_step + closure_result = closure() + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/optimization/automatic.py", line 140, in __call__ + self._result = self.closure(*args, **kwargs) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 116, in decorate_context + return func(*args, **kwargs) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/optimization/automatic.py", line 126, in closure + step_output = self._step_fn() + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/optimization/automatic.py", line 315, in _training_step + training_step_output = call._call_strategy_hook(trainer, "training_step", *kwargs.values()) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/call.py", line 309, in _call_strategy_hook + output = fn(*args, **kwargs) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/strategy.py", line 381, in training_step + return self._forward_redirection(self.model, self.lightning_module, "training_step", *args, **kwargs) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/strategy.py", line 633, in __call__ + wrapper_output = wrapper_module(*args, **kwargs) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1553, in _wrapped_call_impl + return self._call_impl(*args, **kwargs) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1562, in _call_impl + return forward_call(*args, **kwargs) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/parallel/distributed.py", line 1636, in forward + else self._run_ddp_forward(*inputs, **kwargs) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/parallel/distributed.py", line 1454, in _run_ddp_forward + return self.module(*inputs, **kwargs) # type: ignore[index] + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1553, in _wrapped_call_impl + return self._call_impl(*args, **kwargs) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1562, in _call_impl + return forward_call(*args, **kwargs) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/strategy.py", line 626, in wrapped_forward + out = method(*_args, **_kwargs) + File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/algorithms/worldmem/df_video_mamba3stage.py", line 1073, in training_step + self.log("training/curriculum_phase", float(phase_idx)) +TypeError: float() argument must be a string or a real number, not 'NoneType' +[rank0]: Traceback (most recent call last): +[rank0]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/runpy.py", line 196, in _run_module_as_main +[rank0]: return _run_code(code, main_globals, None, +[rank0]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/runpy.py", line 86, in _run_code +[rank0]: exec(code, run_globals) +[rank0]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/main.py", line 202, in +[rank0]: run() # pylint: disable=no-value-for-parameter +[rank0]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/main.py", line 94, in decorated_main +[rank0]: _run_hydra( +[rank0]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/utils.py", line 394, in _run_hydra +[rank0]: _run_app( +[rank0]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/utils.py", line 457, in _run_app +[rank0]: run_and_report( +[rank0]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/utils.py", line 223, in run_and_report +[rank0]: raise ex +[rank0]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/utils.py", line 220, in run_and_report +[rank0]: return func() +[rank0]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/utils.py", line 458, in +[rank0]: lambda: hydra.run( +[rank0]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/hydra.py", line 132, in run +[rank0]: _ = ret.return_value +[rank0]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/core/utils.py", line 260, in return_value +[rank0]: raise self._return_value +[rank0]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/core/utils.py", line 186, in run_job +[rank0]: ret.return_value = task_function(task_cfg) +[rank0]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/main.py", line 198, in run +[rank0]: run_local(cfg) +[rank0]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/main.py", line 122, in run_local +[rank0]: experiment.exec_task(task) +[rank0]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/experiments/exp_base.py", line 172, in exec_task +[rank0]: getattr(self, task)() +[rank0]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/experiments/exp_base.py", line 371, in training +[rank0]: trainer.fit( +[rank0]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/trainer.py", line 544, in fit +[rank0]: call._call_and_handle_interrupt( +[rank0]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/call.py", line 43, in _call_and_handle_interrupt +[rank0]: return trainer.strategy.launcher.launch(trainer_fn, *args, trainer=trainer, **kwargs) +[rank0]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/launchers/subprocess_script.py", line 102, in launch +[rank0]: return function(*args, **kwargs) +[rank0]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/trainer.py", line 580, in _fit_impl +[rank0]: self._run(model, ckpt_path=ckpt_path) +[rank0]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/trainer.py", line 989, in _run +[rank0]: results = self._run_stage() +[rank0]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/trainer.py", line 1035, in _run_stage +[rank0]: self.fit_loop.run() +[rank0]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/fit_loop.py", line 202, in run +[rank0]: self.advance() +[rank0]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/fit_loop.py", line 359, in advance +[rank0]: self.epoch_loop.run(self._data_fetcher) +[rank0]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/training_epoch_loop.py", line 136, in run +[rank0]: self.advance(data_fetcher) +[rank0]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/training_epoch_loop.py", line 240, in advance +[rank0]: batch_output = self.automatic_optimization.run(trainer.optimizers[0], batch_idx, kwargs) +[rank0]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/optimization/automatic.py", line 187, in run +[rank0]: self._optimizer_step(batch_idx, closure) +[rank0]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/optimization/automatic.py", line 265, in _optimizer_step +[rank0]: call._call_lightning_module_hook( +[rank0]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/call.py", line 157, in _call_lightning_module_hook +[rank0]: output = fn(*args, **kwargs) +[rank0]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/algorithms/worldmem/df_base.py", line 65, in optimizer_step +[rank0]: optimizer.step(closure=optimizer_closure) +[rank0]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/core/optimizer.py", line 151, in step +[rank0]: step_output = self._strategy.optimizer_step(self._optimizer, closure, **kwargs) +[rank0]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/ddp.py", line 265, in optimizer_step +[rank0]: optimizer_output = super().optimizer_step(optimizer, closure, model, **kwargs) +[rank0]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/strategy.py", line 230, in optimizer_step +[rank0]: return self.precision_plugin.optimizer_step(optimizer, model=model, closure=closure, **kwargs) +[rank0]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/plugins/precision/amp.py", line 77, in optimizer_step +[rank0]: closure_result = closure() +[rank0]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/optimization/automatic.py", line 140, in __call__ +[rank0]: self._result = self.closure(*args, **kwargs) +[rank0]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 116, in decorate_context +[rank0]: return func(*args, **kwargs) +[rank0]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/optimization/automatic.py", line 126, in closure +[rank0]: step_output = self._step_fn() +[rank0]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/optimization/automatic.py", line 315, in _training_step +[rank0]: training_step_output = call._call_strategy_hook(trainer, "training_step", *kwargs.values()) +[rank0]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/call.py", line 309, in _call_strategy_hook +[rank0]: output = fn(*args, **kwargs) +[rank0]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/strategy.py", line 381, in training_step +[rank0]: return self._forward_redirection(self.model, self.lightning_module, "training_step", *args, **kwargs) +[rank0]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/strategy.py", line 633, in __call__ +[rank0]: wrapper_output = wrapper_module(*args, **kwargs) +[rank0]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1553, in _wrapped_call_impl +[rank0]: return self._call_impl(*args, **kwargs) +[rank0]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1562, in _call_impl +[rank0]: return forward_call(*args, **kwargs) +[rank0]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/parallel/distributed.py", line 1636, in forward +[rank0]: else self._run_ddp_forward(*inputs, **kwargs) +[rank0]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/parallel/distributed.py", line 1454, in _run_ddp_forward +[rank0]: return self.module(*inputs, **kwargs) # type: ignore[index] +[rank0]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1553, in _wrapped_call_impl +[rank0]: return self._call_impl(*args, **kwargs) +[rank0]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1562, in _call_impl +[rank0]: return forward_call(*args, **kwargs) +[rank0]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/strategy.py", line 626, in wrapped_forward +[rank0]: out = method(*_args, **_kwargs) +[rank0]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/algorithms/worldmem/df_video_mamba3stage.py", line 1073, in training_step +[rank0]: self.log("training/curriculum_phase", float(phase_idx)) +[rank0]: TypeError: float() argument must be a string or a real number, not 'NoneType' +Traceback (most recent call last): + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 300, in _run_finalizers + finalizer() + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 224, in __call__ + res = self._callback(*self._args, **self._kwargs) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 133, in _remove_temp_dir + rmtree(tempdir) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 725, in rmtree + _rmtree_safe_fd(fd, path, onerror) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 681, in _rmtree_safe_fd + onerror(os.unlink, fullname, sys.exc_info()) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 679, in _rmtree_safe_fd + os.unlink(entry.name, dir_fd=topfd) +OSError: [Errno 16] Device or resource busy: '.nfs81c923980eb4d684000002f1' +Error executing job with overrides: ['+name=train_stage_b_mamba', 'algorithm=df_video_mamba3stage', 'experiment.num_nodes=1', 'dataset.save_dir=/proj/cvl/users/x_fahkh2/WorldMem_Repro/datasets/minecraft', 'dataset.n_frames=200', '+dataset.n_frames_valid=200', '+dataset.angle_range=110', '+dataset.pos_range=8', '+dataset.wo_updown=false', '+dataset.customized_validation=true', '+dataset.add_timestamp_embedding=true', '+dataset.use_explicit_memory_frames=false', 'algorithm.training_stage=stage_b_diffusion_frozen_memory', 'algorithm.use_mamba_memory_pipeline=true', 'algorithm.use_oracle_pose_eval=false', 'algorithm.enable_memory_noise_curriculum=false', '+algorithm.require_pose_prediction=false', '+algorithm.use_memory_attention=false', '+algorithm.relative_embedding=false', '+algorithm.memory_retrieval_topk=32', 'algorithm.diff_window_size=8', 'algorithm.memory_condition_length=0', 'algorithm.context_frames=100', '+algorithm.n_tokens=8', 'experiment.training.batch_size=8', 'experiment.training.checkpointing.every_n_train_steps=2500', 'experiment.training.max_steps=60000', 'experiment.validation.val_every_n_step=2500', 'resume=stage_b_offline', '+output_dir=/proj/cvl/users/x_fahkh2/WorldMem_Repro/checkpoints/bimamba_stage_b/'] +[rank6]: Traceback (most recent call last): +[rank6]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/runpy.py", line 196, in _run_module_as_main +[rank6]: return _run_code(code, main_globals, None, +[rank6]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/runpy.py", line 86, in _run_code +[rank6]: exec(code, run_globals) +[rank6]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/main.py", line 202, in +[rank6]: run() # pylint: disable=no-value-for-parameter +[rank6]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/main.py", line 94, in decorated_main +[rank6]: _run_hydra( +[rank6]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/utils.py", line 394, in _run_hydra +[rank6]: _run_app( +[rank6]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/utils.py", line 457, in _run_app +[rank6]: run_and_report( +[rank6]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/utils.py", line 223, in run_and_report +[rank6]: raise ex +[rank6]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/utils.py", line 220, in run_and_report +[rank6]: return func() +[rank6]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/utils.py", line 458, in +[rank6]: lambda: hydra.run( +[rank6]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/hydra.py", line 132, in run +[rank6]: _ = ret.return_value +[rank6]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/core/utils.py", line 260, in return_value +[rank6]: raise self._return_value +[rank6]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/core/utils.py", line 186, in run_job +[rank6]: ret.return_value = task_function(task_cfg) +[rank6]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/main.py", line 198, in run +[rank6]: run_local(cfg) +[rank6]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/main.py", line 122, in run_local +[rank6]: experiment.exec_task(task) +[rank6]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/experiments/exp_base.py", line 172, in exec_task +[rank6]: getattr(self, task)() +[rank6]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/experiments/exp_base.py", line 371, in training +[rank6]: trainer.fit( +[rank6]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/trainer.py", line 544, in fit +[rank6]: call._call_and_handle_interrupt( +[rank6]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/call.py", line 43, in _call_and_handle_interrupt +[rank6]: return trainer.strategy.launcher.launch(trainer_fn, *args, trainer=trainer, **kwargs) +[rank6]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/launchers/subprocess_script.py", line 102, in launch +[rank6]: return function(*args, **kwargs) +[rank6]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/trainer.py", line 580, in _fit_impl +[rank6]: self._run(model, ckpt_path=ckpt_path) +[rank6]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/trainer.py", line 989, in _run +[rank6]: results = self._run_stage() +[rank6]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/trainer.py", line 1035, in _run_stage +[rank6]: self.fit_loop.run() +[rank6]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/fit_loop.py", line 202, in run +[rank6]: self.advance() +[rank6]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/fit_loop.py", line 359, in advance +[rank6]: self.epoch_loop.run(self._data_fetcher) +[rank6]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/training_epoch_loop.py", line 136, in run +[rank6]: self.advance(data_fetcher) +[rank6]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/training_epoch_loop.py", line 240, in advance +[rank6]: batch_output = self.automatic_optimization.run(trainer.optimizers[0], batch_idx, kwargs) +[rank6]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/optimization/automatic.py", line 187, in run +[rank6]: self._optimizer_step(batch_idx, closure) +[rank6]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/optimization/automatic.py", line 265, in _optimizer_step +[rank6]: call._call_lightning_module_hook( +[rank6]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/call.py", line 157, in _call_lightning_module_hook +[rank6]: output = fn(*args, **kwargs) +[rank6]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/algorithms/worldmem/df_base.py", line 65, in optimizer_step +[rank6]: optimizer.step(closure=optimizer_closure) +[rank6]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/core/optimizer.py", line 151, in step +[rank6]: step_output = self._strategy.optimizer_step(self._optimizer, closure, **kwargs) +[rank6]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/ddp.py", line 265, in optimizer_step +[rank6]: optimizer_output = super().optimizer_step(optimizer, closure, model, **kwargs) +[rank6]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/strategy.py", line 230, in optimizer_step +[rank6]: return self.precision_plugin.optimizer_step(optimizer, model=model, closure=closure, **kwargs) +[rank6]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/plugins/precision/amp.py", line 77, in optimizer_step +[rank6]: closure_result = closure() +[rank6]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/optimization/automatic.py", line 140, in __call__ +[rank6]: self._result = self.closure(*args, **kwargs) +[rank6]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 116, in decorate_context +[rank6]: return func(*args, **kwargs) +[rank6]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/optimization/automatic.py", line 126, in closure +[rank6]: step_output = self._step_fn() +[rank6]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/optimization/automatic.py", line 315, in _training_step +[rank6]: training_step_output = call._call_strategy_hook(trainer, "training_step", *kwargs.values()) +[rank6]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/call.py", line 309, in _call_strategy_hook +[rank6]: output = fn(*args, **kwargs) +[rank6]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/strategy.py", line 381, in training_step +[rank6]: return self._forward_redirection(self.model, self.lightning_module, "training_step", *args, **kwargs) +[rank6]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/strategy.py", line 633, in __call__ +[rank6]: wrapper_output = wrapper_module(*args, **kwargs) +[rank6]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1553, in _wrapped_call_impl +[rank6]: return self._call_impl(*args, **kwargs) +[rank6]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1562, in _call_impl +[rank6]: return forward_call(*args, **kwargs) +[rank6]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/parallel/distributed.py", line 1636, in forward +[rank6]: else self._run_ddp_forward(*inputs, **kwargs) +[rank6]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/parallel/distributed.py", line 1454, in _run_ddp_forward +[rank6]: return self.module(*inputs, **kwargs) # type: ignore[index] +[rank6]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1553, in _wrapped_call_impl +[rank6]: return self._call_impl(*args, **kwargs) +[rank6]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1562, in _call_impl +[rank6]: return forward_call(*args, **kwargs) +[rank6]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/strategy.py", line 626, in wrapped_forward +[rank6]: out = method(*_args, **_kwargs) +[rank6]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/algorithms/worldmem/df_video_mamba3stage.py", line 1073, in training_step +[rank6]: self.log("training/curriculum_phase", float(phase_idx)) +[rank6]: TypeError: float() argument must be a string or a real number, not 'NoneType' +Error executing job with overrides: ['+name=train_stage_b_mamba', 'algorithm=df_video_mamba3stage', 'experiment.num_nodes=1', 'dataset.save_dir=/proj/cvl/users/x_fahkh2/WorldMem_Repro/datasets/minecraft', 'dataset.n_frames=200', '+dataset.n_frames_valid=200', '+dataset.angle_range=110', '+dataset.pos_range=8', '+dataset.wo_updown=false', '+dataset.customized_validation=true', '+dataset.add_timestamp_embedding=true', '+dataset.use_explicit_memory_frames=false', 'algorithm.training_stage=stage_b_diffusion_frozen_memory', 'algorithm.use_mamba_memory_pipeline=true', 'algorithm.use_oracle_pose_eval=false', 'algorithm.enable_memory_noise_curriculum=false', '+algorithm.require_pose_prediction=false', '+algorithm.use_memory_attention=false', '+algorithm.relative_embedding=false', '+algorithm.memory_retrieval_topk=32', 'algorithm.diff_window_size=8', 'algorithm.memory_condition_length=0', 'algorithm.context_frames=100', '+algorithm.n_tokens=8', 'experiment.training.batch_size=8', 'experiment.training.checkpointing.every_n_train_steps=2500', 'experiment.training.max_steps=60000', 'experiment.validation.val_every_n_step=2500', 'resume=stage_b_offline', '+output_dir=/proj/cvl/users/x_fahkh2/WorldMem_Repro/checkpoints/bimamba_stage_b/'] +Traceback (most recent call last): + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 300, in _run_finalizers + finalizer() + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 224, in __call__ + res = self._callback(*self._args, **self._kwargs) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 133, in _remove_temp_dir + rmtree(tempdir) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 725, in rmtree + _rmtree_safe_fd(fd, path, onerror) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 681, in _rmtree_safe_fd + onerror(os.unlink, fullname, sys.exc_info()) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 679, in _rmtree_safe_fd + os.unlink(entry.name, dir_fd=topfd) +OSError: [Errno 16] Device or resource busy: '.nfs9ad9301b65f10564000002f2' +[rank3]: Traceback (most recent call last): +[rank3]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/runpy.py", line 196, in _run_module_as_main +[rank3]: return _run_code(code, main_globals, None, +[rank3]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/runpy.py", line 86, in _run_code +[rank3]: exec(code, run_globals) +[rank3]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/main.py", line 202, in +[rank3]: run() # pylint: disable=no-value-for-parameter +[rank3]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/main.py", line 94, in decorated_main +[rank3]: _run_hydra( +[rank3]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/utils.py", line 394, in _run_hydra +[rank3]: _run_app( +[rank3]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/utils.py", line 457, in _run_app +[rank3]: run_and_report( +[rank3]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/utils.py", line 223, in run_and_report +[rank3]: raise ex +[rank3]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/utils.py", line 220, in run_and_report +[rank3]: return func() +[rank3]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/utils.py", line 458, in +[rank3]: lambda: hydra.run( +[rank3]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/hydra.py", line 132, in run +[rank3]: _ = ret.return_value +[rank3]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/core/utils.py", line 260, in return_value +[rank3]: raise self._return_value +[rank3]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/core/utils.py", line 186, in run_job +[rank3]: ret.return_value = task_function(task_cfg) +[rank3]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/main.py", line 198, in run +[rank3]: run_local(cfg) +[rank3]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/main.py", line 122, in run_local +[rank3]: experiment.exec_task(task) +[rank3]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/experiments/exp_base.py", line 172, in exec_task +[rank3]: getattr(self, task)() +[rank3]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/experiments/exp_base.py", line 371, in training +[rank3]: trainer.fit( +[rank3]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/trainer.py", line 544, in fit +[rank3]: call._call_and_handle_interrupt( +[rank3]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/call.py", line 43, in _call_and_handle_interrupt +[rank3]: return trainer.strategy.launcher.launch(trainer_fn, *args, trainer=trainer, **kwargs) +[rank3]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/launchers/subprocess_script.py", line 102, in launch +[rank3]: return function(*args, **kwargs) +[rank3]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/trainer.py", line 580, in _fit_impl +[rank3]: self._run(model, ckpt_path=ckpt_path) +[rank3]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/trainer.py", line 989, in _run +[rank3]: results = self._run_stage() +[rank3]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/trainer.py", line 1035, in _run_stage +[rank3]: self.fit_loop.run() +[rank3]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/fit_loop.py", line 202, in run +[rank3]: self.advance() +[rank3]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/fit_loop.py", line 359, in advance +[rank3]: self.epoch_loop.run(self._data_fetcher) +[rank3]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/training_epoch_loop.py", line 136, in run +[rank3]: self.advance(data_fetcher) +[rank3]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/training_epoch_loop.py", line 240, in advance +[rank3]: batch_output = self.automatic_optimization.run(trainer.optimizers[0], batch_idx, kwargs) +[rank3]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/optimization/automatic.py", line 187, in run +[rank3]: self._optimizer_step(batch_idx, closure) +[rank3]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/optimization/automatic.py", line 265, in _optimizer_step +[rank3]: call._call_lightning_module_hook( +[rank3]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/call.py", line 157, in _call_lightning_module_hook +[rank3]: output = fn(*args, **kwargs) +[rank3]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/algorithms/worldmem/df_base.py", line 65, in optimizer_step +[rank3]: optimizer.step(closure=optimizer_closure) +[rank3]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/core/optimizer.py", line 151, in step +[rank3]: step_output = self._strategy.optimizer_step(self._optimizer, closure, **kwargs) +[rank3]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/ddp.py", line 265, in optimizer_step +[rank3]: optimizer_output = super().optimizer_step(optimizer, closure, model, **kwargs) +[rank3]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/strategy.py", line 230, in optimizer_step +[rank3]: return self.precision_plugin.optimizer_step(optimizer, model=model, closure=closure, **kwargs) +[rank3]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/plugins/precision/amp.py", line 77, in optimizer_step +[rank3]: closure_result = closure() +[rank3]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/optimization/automatic.py", line 140, in __call__ +[rank3]: self._result = self.closure(*args, **kwargs) +[rank3]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 116, in decorate_context +[rank3]: return func(*args, **kwargs) +[rank3]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/optimization/automatic.py", line 126, in closure +[rank3]: step_output = self._step_fn() +[rank3]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/optimization/automatic.py", line 315, in _training_step +[rank3]: training_step_output = call._call_strategy_hook(trainer, "training_step", *kwargs.values()) +[rank3]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/call.py", line 309, in _call_strategy_hook +[rank3]: output = fn(*args, **kwargs) +[rank3]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/strategy.py", line 381, in training_step +[rank3]: return self._forward_redirection(self.model, self.lightning_module, "training_step", *args, **kwargs) +[rank3]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/strategy.py", line 633, in __call__ +[rank3]: wrapper_output = wrapper_module(*args, **kwargs) +[rank3]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1553, in _wrapped_call_impl +[rank3]: return self._call_impl(*args, **kwargs) +[rank3]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1562, in _call_impl +[rank3]: return forward_call(*args, **kwargs) +[rank3]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/parallel/distributed.py", line 1636, in forward +[rank3]: else self._run_ddp_forward(*inputs, **kwargs) +[rank3]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/parallel/distributed.py", line 1454, in _run_ddp_forward +[rank3]: return self.module(*inputs, **kwargs) # type: ignore[index] +[rank3]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1553, in _wrapped_call_impl +[rank3]: return self._call_impl(*args, **kwargs) +[rank3]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1562, in _call_impl +[rank3]: return forward_call(*args, **kwargs) +[rank3]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/strategy.py", line 626, in wrapped_forward +[rank3]: out = method(*_args, **_kwargs) +[rank3]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/algorithms/worldmem/df_video_mamba3stage.py", line 1073, in training_step +[rank3]: self.log("training/curriculum_phase", float(phase_idx)) +[rank3]: TypeError: float() argument must be a string or a real number, not 'NoneType' +Traceback (most recent call last): + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 300, in _run_finalizers + finalizer() + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 224, in __call__ + res = self._callback(*self._args, **self._kwargs) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 133, in _remove_temp_dir + rmtree(tempdir) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 725, in rmtree + _rmtree_safe_fd(fd, path, onerror) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 681, in _rmtree_safe_fd + onerror(os.unlink, fullname, sys.exc_info()) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 679, in _rmtree_safe_fd + os.unlink(entry.name, dir_fd=topfd) +OSError: [Errno 16] Device or resource busy: '.nfs6f4d583e4f241199000002f3' +Error executing job with overrides: ['+name=train_stage_b_mamba', 'algorithm=df_video_mamba3stage', 'experiment.num_nodes=1', 'dataset.save_dir=/proj/cvl/users/x_fahkh2/WorldMem_Repro/datasets/minecraft', 'dataset.n_frames=200', '+dataset.n_frames_valid=200', '+dataset.angle_range=110', '+dataset.pos_range=8', '+dataset.wo_updown=false', '+dataset.customized_validation=true', '+dataset.add_timestamp_embedding=true', '+dataset.use_explicit_memory_frames=false', 'algorithm.training_stage=stage_b_diffusion_frozen_memory', 'algorithm.use_mamba_memory_pipeline=true', 'algorithm.use_oracle_pose_eval=false', 'algorithm.enable_memory_noise_curriculum=false', '+algorithm.require_pose_prediction=false', '+algorithm.use_memory_attention=false', '+algorithm.relative_embedding=false', '+algorithm.memory_retrieval_topk=32', 'algorithm.diff_window_size=8', 'algorithm.memory_condition_length=0', 'algorithm.context_frames=100', '+algorithm.n_tokens=8', 'experiment.training.batch_size=8', 'experiment.training.checkpointing.every_n_train_steps=2500', 'experiment.training.max_steps=60000', 'experiment.validation.val_every_n_step=2500', 'resume=stage_b_offline', '+output_dir=/proj/cvl/users/x_fahkh2/WorldMem_Repro/checkpoints/bimamba_stage_b/'] +wandb: - 0.000 MB of 0.000 MB uploaded wandb: You can sync this run to the cloud by running: +wandb: wandb sync /proj/cvl/users/x_fahkh2/WorldMem_Repro/checkpoints/bimamba_stage_b/wandb/offline-run-20260311_191215-stage_b_offline +wandb: Find logs at: ./checkpoints/bimamba_stage_b/wandb/offline-run-20260311_191215-stage_b_offline/logs +wandb: WARNING The new W&B backend becomes opt-out in version 0.18.0; try it out with `wandb.require("core")`! See https://wandb.me/wandb-core for more information. +[rank4]: Traceback (most recent call last): +[rank4]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/runpy.py", line 196, in _run_module_as_main +[rank4]: return _run_code(code, main_globals, None, +[rank4]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/runpy.py", line 86, in _run_code +[rank4]: exec(code, run_globals) +[rank4]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/main.py", line 202, in +[rank4]: run() # pylint: disable=no-value-for-parameter +[rank4]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/main.py", line 94, in decorated_main +[rank4]: _run_hydra( +[rank4]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/utils.py", line 394, in _run_hydra +[rank4]: _run_app( +[rank4]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/utils.py", line 457, in _run_app +[rank4]: run_and_report( +[rank4]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/utils.py", line 223, in run_and_report +[rank4]: raise ex +[rank4]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/utils.py", line 220, in run_and_report +[rank4]: return func() +[rank4]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/utils.py", line 458, in +[rank4]: lambda: hydra.run( +[rank4]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/hydra.py", line 132, in run +[rank4]: _ = ret.return_value +[rank4]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/core/utils.py", line 260, in return_value +[rank4]: raise self._return_value +[rank4]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/core/utils.py", line 186, in run_job +[rank4]: ret.return_value = task_function(task_cfg) +[rank4]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/main.py", line 198, in run +[rank4]: run_local(cfg) +[rank4]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/main.py", line 122, in run_local +[rank4]: experiment.exec_task(task) +[rank4]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/experiments/exp_base.py", line 172, in exec_task +[rank4]: getattr(self, task)() +[rank4]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/experiments/exp_base.py", line 371, in training +[rank4]: trainer.fit( +[rank4]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/trainer.py", line 544, in fit +[rank4]: call._call_and_handle_interrupt( +[rank4]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/call.py", line 43, in _call_and_handle_interrupt +[rank4]: return trainer.strategy.launcher.launch(trainer_fn, *args, trainer=trainer, **kwargs) +[rank4]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/launchers/subprocess_script.py", line 102, in launch +[rank4]: return function(*args, **kwargs) +[rank4]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/trainer.py", line 580, in _fit_impl +[rank4]: self._run(model, ckpt_path=ckpt_path) +[rank4]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/trainer.py", line 989, in _run +[rank4]: results = self._run_stage() +[rank4]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/trainer.py", line 1035, in _run_stage +[rank4]: self.fit_loop.run() +[rank4]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/fit_loop.py", line 202, in run +[rank4]: self.advance() +[rank4]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/fit_loop.py", line 359, in advance +[rank4]: self.epoch_loop.run(self._data_fetcher) +[rank4]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/training_epoch_loop.py", line 136, in run +[rank4]: self.advance(data_fetcher) +[rank4]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/training_epoch_loop.py", line 240, in advance +[rank4]: batch_output = self.automatic_optimization.run(trainer.optimizers[0], batch_idx, kwargs) +[rank4]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/optimization/automatic.py", line 187, in run +[rank4]: self._optimizer_step(batch_idx, closure) +[rank4]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/optimization/automatic.py", line 265, in _optimizer_step +[rank4]: call._call_lightning_module_hook( +[rank4]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/call.py", line 157, in _call_lightning_module_hook +[rank4]: output = fn(*args, **kwargs) +[rank4]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/algorithms/worldmem/df_base.py", line 65, in optimizer_step +[rank4]: optimizer.step(closure=optimizer_closure) +[rank4]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/core/optimizer.py", line 151, in step +[rank4]: step_output = self._strategy.optimizer_step(self._optimizer, closure, **kwargs) +[rank4]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/ddp.py", line 265, in optimizer_step +[rank4]: optimizer_output = super().optimizer_step(optimizer, closure, model, **kwargs) +[rank4]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/strategy.py", line 230, in optimizer_step +[rank4]: return self.precision_plugin.optimizer_step(optimizer, model=model, closure=closure, **kwargs) +[rank4]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/plugins/precision/amp.py", line 77, in optimizer_step +[rank4]: closure_result = closure() +[rank4]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/optimization/automatic.py", line 140, in __call__ +[rank4]: self._result = self.closure(*args, **kwargs) +[rank4]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 116, in decorate_context +[rank4]: return func(*args, **kwargs) +[rank4]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/optimization/automatic.py", line 126, in closure +[rank4]: step_output = self._step_fn() +[rank4]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/optimization/automatic.py", line 315, in _training_step +[rank4]: training_step_output = call._call_strategy_hook(trainer, "training_step", *kwargs.values()) +[rank4]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/call.py", line 309, in _call_strategy_hook +[rank4]: output = fn(*args, **kwargs) +[rank4]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/strategy.py", line 381, in training_step +[rank4]: return self._forward_redirection(self.model, self.lightning_module, "training_step", *args, **kwargs) +[rank4]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/strategy.py", line 633, in __call__ +[rank4]: wrapper_output = wrapper_module(*args, **kwargs) +[rank4]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1553, in _wrapped_call_impl +[rank4]: return self._call_impl(*args, **kwargs) +[rank4]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1562, in _call_impl +[rank4]: return forward_call(*args, **kwargs) +[rank4]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/parallel/distributed.py", line 1636, in forward +[rank4]: else self._run_ddp_forward(*inputs, **kwargs) +[rank4]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/parallel/distributed.py", line 1454, in _run_ddp_forward +[rank4]: return self.module(*inputs, **kwargs) # type: ignore[index] +[rank4]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1553, in _wrapped_call_impl +[rank4]: return self._call_impl(*args, **kwargs) +[rank4]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1562, in _call_impl +[rank4]: return forward_call(*args, **kwargs) +[rank4]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/strategy.py", line 626, in wrapped_forward +[rank4]: out = method(*_args, **_kwargs) +[rank4]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/algorithms/worldmem/df_video_mamba3stage.py", line 1073, in training_step +[rank4]: self.log("training/curriculum_phase", float(phase_idx)) +[rank4]: TypeError: float() argument must be a string or a real number, not 'NoneType' +Error executing job with overrides: ['+name=train_stage_b_mamba', 'algorithm=df_video_mamba3stage', 'experiment.num_nodes=1', 'dataset.save_dir=/proj/cvl/users/x_fahkh2/WorldMem_Repro/datasets/minecraft', 'dataset.n_frames=200', '+dataset.n_frames_valid=200', '+dataset.angle_range=110', '+dataset.pos_range=8', '+dataset.wo_updown=false', '+dataset.customized_validation=true', '+dataset.add_timestamp_embedding=true', '+dataset.use_explicit_memory_frames=false', 'algorithm.training_stage=stage_b_diffusion_frozen_memory', 'algorithm.use_mamba_memory_pipeline=true', 'algorithm.use_oracle_pose_eval=false', 'algorithm.enable_memory_noise_curriculum=false', '+algorithm.require_pose_prediction=false', '+algorithm.use_memory_attention=false', '+algorithm.relative_embedding=false', '+algorithm.memory_retrieval_topk=32', 'algorithm.diff_window_size=8', 'algorithm.memory_condition_length=0', 'algorithm.context_frames=100', '+algorithm.n_tokens=8', 'experiment.training.batch_size=8', 'experiment.training.checkpointing.every_n_train_steps=2500', 'experiment.training.max_steps=60000', 'experiment.validation.val_every_n_step=2500', 'resume=stage_b_offline', '+output_dir=/proj/cvl/users/x_fahkh2/WorldMem_Repro/checkpoints/bimamba_stage_b/'] +[rank2]: Traceback (most recent call last): +[rank2]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/runpy.py", line 196, in _run_module_as_main +[rank2]: return _run_code(code, main_globals, None, +[rank2]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/runpy.py", line 86, in _run_code +[rank2]: exec(code, run_globals) +[rank2]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/main.py", line 202, in +[rank2]: run() # pylint: disable=no-value-for-parameter +[rank2]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/main.py", line 94, in decorated_main +[rank2]: _run_hydra( +[rank2]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/utils.py", line 394, in _run_hydra +[rank2]: _run_app( +[rank2]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/utils.py", line 457, in _run_app +[rank2]: run_and_report( +[rank2]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/utils.py", line 223, in run_and_report +[rank2]: raise ex +[rank2]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/utils.py", line 220, in run_and_report +[rank2]: return func() +[rank2]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/utils.py", line 458, in +[rank2]: lambda: hydra.run( +[rank2]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/hydra.py", line 132, in run +[rank2]: _ = ret.return_value +[rank2]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/core/utils.py", line 260, in return_value +[rank2]: raise self._return_value +[rank2]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/core/utils.py", line 186, in run_job +[rank2]: ret.return_value = task_function(task_cfg) +[rank2]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/main.py", line 198, in run +[rank2]: run_local(cfg) +[rank2]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/main.py", line 122, in run_local +[rank2]: experiment.exec_task(task) +[rank2]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/experiments/exp_base.py", line 172, in exec_task +[rank2]: getattr(self, task)() +[rank2]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/experiments/exp_base.py", line 371, in training +[rank2]: trainer.fit( +[rank2]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/trainer.py", line 544, in fit +[rank2]: call._call_and_handle_interrupt( +[rank2]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/call.py", line 43, in _call_and_handle_interrupt +[rank2]: return trainer.strategy.launcher.launch(trainer_fn, *args, trainer=trainer, **kwargs) +[rank2]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/launchers/subprocess_script.py", line 102, in launch +[rank2]: return function(*args, **kwargs) +[rank2]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/trainer.py", line 580, in _fit_impl +[rank2]: self._run(model, ckpt_path=ckpt_path) +[rank2]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/trainer.py", line 989, in _run +[rank2]: results = self._run_stage() +[rank2]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/trainer.py", line 1035, in _run_stage +[rank2]: self.fit_loop.run() +[rank2]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/fit_loop.py", line 202, in run +[rank2]: self.advance() +[rank2]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/fit_loop.py", line 359, in advance +[rank2]: self.epoch_loop.run(self._data_fetcher) +[rank2]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/training_epoch_loop.py", line 136, in run +[rank2]: self.advance(data_fetcher) +[rank2]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/training_epoch_loop.py", line 240, in advance +[rank2]: batch_output = self.automatic_optimization.run(trainer.optimizers[0], batch_idx, kwargs) +[rank2]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/optimization/automatic.py", line 187, in run +[rank2]: self._optimizer_step(batch_idx, closure) +[rank2]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/optimization/automatic.py", line 265, in _optimizer_step +[rank2]: call._call_lightning_module_hook( +[rank2]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/call.py", line 157, in _call_lightning_module_hook +[rank2]: output = fn(*args, **kwargs) +[rank2]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/algorithms/worldmem/df_base.py", line 65, in optimizer_step +[rank2]: optimizer.step(closure=optimizer_closure) +[rank2]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/core/optimizer.py", line 151, in step +[rank2]: step_output = self._strategy.optimizer_step(self._optimizer, closure, **kwargs) +[rank2]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/ddp.py", line 265, in optimizer_step +[rank2]: optimizer_output = super().optimizer_step(optimizer, closure, model, **kwargs) +[rank2]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/strategy.py", line 230, in optimizer_step +[rank2]: return self.precision_plugin.optimizer_step(optimizer, model=model, closure=closure, **kwargs) +[rank2]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/plugins/precision/amp.py", line 77, in optimizer_step +[rank2]: closure_result = closure() +[rank2]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/optimization/automatic.py", line 140, in __call__ +[rank2]: self._result = self.closure(*args, **kwargs) +[rank2]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 116, in decorate_context +[rank2]: return func(*args, **kwargs) +[rank2]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/optimization/automatic.py", line 126, in closure +[rank2]: step_output = self._step_fn() +[rank2]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/optimization/automatic.py", line 315, in _training_step +[rank2]: training_step_output = call._call_strategy_hook(trainer, "training_step", *kwargs.values()) +[rank2]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/call.py", line 309, in _call_strategy_hook +[rank2]: output = fn(*args, **kwargs) +[rank2]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/strategy.py", line 381, in training_step +[rank2]: return self._forward_redirection(self.model, self.lightning_module, "training_step", *args, **kwargs) +[rank2]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/strategy.py", line 633, in __call__ +[rank2]: wrapper_output = wrapper_module(*args, **kwargs) +[rank2]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1553, in _wrapped_call_impl +[rank2]: return self._call_impl(*args, **kwargs) +[rank2]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1562, in _call_impl +[rank2]: return forward_call(*args, **kwargs) +[rank2]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/parallel/distributed.py", line 1636, in forward +[rank2]: else self._run_ddp_forward(*inputs, **kwargs) +[rank2]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/parallel/distributed.py", line 1454, in _run_ddp_forward +[rank2]: return self.module(*inputs, **kwargs) # type: ignore[index] +[rank2]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1553, in _wrapped_call_impl +[rank2]: return self._call_impl(*args, **kwargs) +[rank2]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1562, in _call_impl +[rank2]: return forward_call(*args, **kwargs) +[rank2]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/strategy.py", line 626, in wrapped_forward +[rank2]: out = method(*_args, **_kwargs) +[rank2]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/algorithms/worldmem/df_video_mamba3stage.py", line 1073, in training_step +[rank2]: self.log("training/curriculum_phase", float(phase_idx)) +[rank2]: TypeError: float() argument must be a string or a real number, not 'NoneType' +Traceback (most recent call last): + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 300, in _run_finalizers + finalizer() + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 224, in __call__ + res = self._callback(*self._args, **self._kwargs) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 133, in _remove_temp_dir + rmtree(tempdir) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 725, in rmtree + _rmtree_safe_fd(fd, path, onerror) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 681, in _rmtree_safe_fd + onerror(os.unlink, fullname, sys.exc_info()) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 679, in _rmtree_safe_fd + os.unlink(entry.name, dir_fd=topfd) +OSError: [Errno 16] Device or resource busy: '.nfs8dc2a2bf5c4b6424000002f4' +Error executing job with overrides: ['+name=train_stage_b_mamba', 'algorithm=df_video_mamba3stage', 'experiment.num_nodes=1', 'dataset.save_dir=/proj/cvl/users/x_fahkh2/WorldMem_Repro/datasets/minecraft', 'dataset.n_frames=200', '+dataset.n_frames_valid=200', '+dataset.angle_range=110', '+dataset.pos_range=8', '+dataset.wo_updown=false', '+dataset.customized_validation=true', '+dataset.add_timestamp_embedding=true', '+dataset.use_explicit_memory_frames=false', 'algorithm.training_stage=stage_b_diffusion_frozen_memory', 'algorithm.use_mamba_memory_pipeline=true', 'algorithm.use_oracle_pose_eval=false', 'algorithm.enable_memory_noise_curriculum=false', '+algorithm.require_pose_prediction=false', '+algorithm.use_memory_attention=false', '+algorithm.relative_embedding=false', '+algorithm.memory_retrieval_topk=32', 'algorithm.diff_window_size=8', 'algorithm.memory_condition_length=0', 'algorithm.context_frames=100', '+algorithm.n_tokens=8', 'experiment.training.batch_size=8', 'experiment.training.checkpointing.every_n_train_steps=2500', 'experiment.training.max_steps=60000', 'experiment.validation.val_every_n_step=2500', 'resume=stage_b_offline', '+output_dir=/proj/cvl/users/x_fahkh2/WorldMem_Repro/checkpoints/bimamba_stage_b/'] +[rank5]: Traceback (most recent call last): +[rank5]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/runpy.py", line 196, in _run_module_as_main +[rank5]: return _run_code(code, main_globals, None, +[rank5]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/runpy.py", line 86, in _run_code +[rank5]: exec(code, run_globals) +[rank5]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/main.py", line 202, in +[rank5]: run() # pylint: disable=no-value-for-parameter +[rank5]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/main.py", line 94, in decorated_main +[rank5]: _run_hydra( +[rank5]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/utils.py", line 394, in _run_hydra +[rank5]: _run_app( +[rank5]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/utils.py", line 457, in _run_app +[rank5]: run_and_report( +[rank5]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/utils.py", line 223, in run_and_report +[rank5]: raise ex +[rank5]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/utils.py", line 220, in run_and_report +[rank5]: return func() +[rank5]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/utils.py", line 458, in +[rank5]: lambda: hydra.run( +[rank5]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/hydra.py", line 132, in run +[rank5]: _ = ret.return_value +[rank5]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/core/utils.py", line 260, in return_value +[rank5]: raise self._return_value +[rank5]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/core/utils.py", line 186, in run_job +[rank5]: ret.return_value = task_function(task_cfg) +[rank5]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/main.py", line 198, in run +[rank5]: run_local(cfg) +[rank5]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/main.py", line 122, in run_local +[rank5]: experiment.exec_task(task) +[rank5]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/experiments/exp_base.py", line 172, in exec_task +[rank5]: getattr(self, task)() +[rank5]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/experiments/exp_base.py", line 371, in training +[rank5]: trainer.fit( +[rank5]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/trainer.py", line 544, in fit +[rank5]: call._call_and_handle_interrupt( +[rank5]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/call.py", line 43, in _call_and_handle_interrupt +[rank5]: return trainer.strategy.launcher.launch(trainer_fn, *args, trainer=trainer, **kwargs) +[rank5]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/launchers/subprocess_script.py", line 102, in launch +[rank5]: return function(*args, **kwargs) +[rank5]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/trainer.py", line 580, in _fit_impl +[rank5]: self._run(model, ckpt_path=ckpt_path) +[rank5]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/trainer.py", line 989, in _run +[rank5]: results = self._run_stage() +[rank5]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/trainer.py", line 1035, in _run_stage +[rank5]: self.fit_loop.run() +[rank5]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/fit_loop.py", line 202, in run +[rank5]: self.advance() +[rank5]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/fit_loop.py", line 359, in advance +[rank5]: self.epoch_loop.run(self._data_fetcher) +[rank5]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/training_epoch_loop.py", line 136, in run +[rank5]: self.advance(data_fetcher) +[rank5]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/training_epoch_loop.py", line 240, in advance +[rank5]: batch_output = self.automatic_optimization.run(trainer.optimizers[0], batch_idx, kwargs) +[rank5]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/optimization/automatic.py", line 187, in run +[rank5]: self._optimizer_step(batch_idx, closure) +[rank5]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/optimization/automatic.py", line 265, in _optimizer_step +[rank5]: call._call_lightning_module_hook( +[rank5]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/call.py", line 157, in _call_lightning_module_hook +[rank5]: output = fn(*args, **kwargs) +[rank5]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/algorithms/worldmem/df_base.py", line 65, in optimizer_step +[rank5]: optimizer.step(closure=optimizer_closure) +[rank5]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/core/optimizer.py", line 151, in step +[rank5]: step_output = self._strategy.optimizer_step(self._optimizer, closure, **kwargs) +[rank5]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/ddp.py", line 265, in optimizer_step +[rank5]: optimizer_output = super().optimizer_step(optimizer, closure, model, **kwargs) +[rank5]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/strategy.py", line 230, in optimizer_step +[rank5]: return self.precision_plugin.optimizer_step(optimizer, model=model, closure=closure, **kwargs) +[rank5]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/plugins/precision/amp.py", line 77, in optimizer_step +[rank5]: closure_result = closure() +[rank5]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/optimization/automatic.py", line 140, in __call__ +[rank5]: self._result = self.closure(*args, **kwargs) +[rank5]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 116, in decorate_context +[rank5]: return func(*args, **kwargs) +[rank5]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/optimization/automatic.py", line 126, in closure +[rank5]: step_output = self._step_fn() +[rank5]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/optimization/automatic.py", line 315, in _training_step +[rank5]: training_step_output = call._call_strategy_hook(trainer, "training_step", *kwargs.values()) +[rank5]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/call.py", line 309, in _call_strategy_hook +[rank5]: output = fn(*args, **kwargs) +[rank5]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/strategy.py", line 381, in training_step +[rank5]: return self._forward_redirection(self.model, self.lightning_module, "training_step", *args, **kwargs) +[rank5]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/strategy.py", line 633, in __call__ +[rank5]: wrapper_output = wrapper_module(*args, **kwargs) +[rank5]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1553, in _wrapped_call_impl +[rank5]: return self._call_impl(*args, **kwargs) +[rank5]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1562, in _call_impl +[rank5]: return forward_call(*args, **kwargs) +[rank5]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/parallel/distributed.py", line 1636, in forward +[rank5]: else self._run_ddp_forward(*inputs, **kwargs) +[rank5]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/parallel/distributed.py", line 1454, in _run_ddp_forward +[rank5]: return self.module(*inputs, **kwargs) # type: ignore[index] +[rank5]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1553, in _wrapped_call_impl +[rank5]: return self._call_impl(*args, **kwargs) +[rank5]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1562, in _call_impl +[rank5]: return forward_call(*args, **kwargs) +[rank5]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/strategy.py", line 626, in wrapped_forward +[rank5]: out = method(*_args, **_kwargs) +[rank5]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/algorithms/worldmem/df_video_mamba3stage.py", line 1073, in training_step +[rank5]: self.log("training/curriculum_phase", float(phase_idx)) +[rank5]: TypeError: float() argument must be a string or a real number, not 'NoneType' +Error executing job with overrides: ['+name=train_stage_b_mamba', 'algorithm=df_video_mamba3stage', 'experiment.num_nodes=1', 'dataset.save_dir=/proj/cvl/users/x_fahkh2/WorldMem_Repro/datasets/minecraft', 'dataset.n_frames=200', '+dataset.n_frames_valid=200', '+dataset.angle_range=110', '+dataset.pos_range=8', '+dataset.wo_updown=false', '+dataset.customized_validation=true', '+dataset.add_timestamp_embedding=true', '+dataset.use_explicit_memory_frames=false', 'algorithm.training_stage=stage_b_diffusion_frozen_memory', 'algorithm.use_mamba_memory_pipeline=true', 'algorithm.use_oracle_pose_eval=false', 'algorithm.enable_memory_noise_curriculum=false', '+algorithm.require_pose_prediction=false', '+algorithm.use_memory_attention=false', '+algorithm.relative_embedding=false', '+algorithm.memory_retrieval_topk=32', 'algorithm.diff_window_size=8', 'algorithm.memory_condition_length=0', 'algorithm.context_frames=100', '+algorithm.n_tokens=8', 'experiment.training.batch_size=8', 'experiment.training.checkpointing.every_n_train_steps=2500', 'experiment.training.max_steps=60000', 'experiment.validation.val_every_n_step=2500', 'resume=stage_b_offline', '+output_dir=/proj/cvl/users/x_fahkh2/WorldMem_Repro/checkpoints/bimamba_stage_b/'] +[rank1]: Traceback (most recent call last): +[rank1]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/runpy.py", line 196, in _run_module_as_main +[rank1]: return _run_code(code, main_globals, None, +[rank1]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/runpy.py", line 86, in _run_code +[rank1]: exec(code, run_globals) +[rank1]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/main.py", line 202, in +[rank1]: run() # pylint: disable=no-value-for-parameter +[rank1]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/main.py", line 94, in decorated_main +[rank1]: _run_hydra( +[rank1]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/utils.py", line 394, in _run_hydra +[rank1]: _run_app( +[rank1]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/utils.py", line 457, in _run_app +[rank1]: run_and_report( +[rank1]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/utils.py", line 223, in run_and_report +[rank1]: raise ex +[rank1]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/utils.py", line 220, in run_and_report +[rank1]: return func() +[rank1]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/utils.py", line 458, in +[rank1]: lambda: hydra.run( +[rank1]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/hydra.py", line 132, in run +[rank1]: _ = ret.return_value +[rank1]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/core/utils.py", line 260, in return_value +[rank1]: raise self._return_value +[rank1]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/core/utils.py", line 186, in run_job +[rank1]: ret.return_value = task_function(task_cfg) +[rank1]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/main.py", line 198, in run +[rank1]: run_local(cfg) +[rank1]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/main.py", line 122, in run_local +[rank1]: experiment.exec_task(task) +[rank1]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/experiments/exp_base.py", line 172, in exec_task +[rank1]: getattr(self, task)() +[rank1]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/experiments/exp_base.py", line 371, in training +[rank1]: trainer.fit( +[rank1]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/trainer.py", line 544, in fit +[rank1]: call._call_and_handle_interrupt( +[rank1]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/call.py", line 43, in _call_and_handle_interrupt +[rank1]: return trainer.strategy.launcher.launch(trainer_fn, *args, trainer=trainer, **kwargs) +[rank1]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/launchers/subprocess_script.py", line 102, in launch +[rank1]: return function(*args, **kwargs) +[rank1]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/trainer.py", line 580, in _fit_impl +[rank1]: self._run(model, ckpt_path=ckpt_path) +[rank1]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/trainer.py", line 989, in _run +[rank1]: results = self._run_stage() +[rank1]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/trainer.py", line 1035, in _run_stage +[rank1]: self.fit_loop.run() +[rank1]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/fit_loop.py", line 202, in run +[rank1]: self.advance() +[rank1]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/fit_loop.py", line 359, in advance +[rank1]: self.epoch_loop.run(self._data_fetcher) +[rank1]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/training_epoch_loop.py", line 136, in run +[rank1]: self.advance(data_fetcher) +[rank1]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/training_epoch_loop.py", line 240, in advance +[rank1]: batch_output = self.automatic_optimization.run(trainer.optimizers[0], batch_idx, kwargs) +[rank1]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/optimization/automatic.py", line 187, in run +[rank1]: self._optimizer_step(batch_idx, closure) +[rank1]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/optimization/automatic.py", line 265, in _optimizer_step +[rank1]: call._call_lightning_module_hook( +[rank1]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/call.py", line 157, in _call_lightning_module_hook +[rank1]: output = fn(*args, **kwargs) +[rank1]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/algorithms/worldmem/df_base.py", line 65, in optimizer_step +[rank1]: optimizer.step(closure=optimizer_closure) +[rank1]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/core/optimizer.py", line 151, in step +[rank1]: step_output = self._strategy.optimizer_step(self._optimizer, closure, **kwargs) +[rank1]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/ddp.py", line 265, in optimizer_step +[rank1]: optimizer_output = super().optimizer_step(optimizer, closure, model, **kwargs) +[rank1]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/strategy.py", line 230, in optimizer_step +[rank1]: return self.precision_plugin.optimizer_step(optimizer, model=model, closure=closure, **kwargs) +[rank1]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/plugins/precision/amp.py", line 77, in optimizer_step +[rank1]: closure_result = closure() +[rank1]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/optimization/automatic.py", line 140, in __call__ +[rank1]: self._result = self.closure(*args, **kwargs) +[rank1]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 116, in decorate_context +[rank1]: return func(*args, **kwargs) +[rank1]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/optimization/automatic.py", line 126, in closure +[rank1]: step_output = self._step_fn() +[rank1]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/optimization/automatic.py", line 315, in _training_step +[rank1]: training_step_output = call._call_strategy_hook(trainer, "training_step", *kwargs.values()) +[rank1]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/call.py", line 309, in _call_strategy_hook +[rank1]: output = fn(*args, **kwargs) +[rank1]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/strategy.py", line 381, in training_step +[rank1]: return self._forward_redirection(self.model, self.lightning_module, "training_step", *args, **kwargs) +[rank1]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/strategy.py", line 633, in __call__ +[rank1]: wrapper_output = wrapper_module(*args, **kwargs) +[rank1]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1553, in _wrapped_call_impl +[rank1]: return self._call_impl(*args, **kwargs) +[rank1]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1562, in _call_impl +[rank1]: return forward_call(*args, **kwargs) +[rank1]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/parallel/distributed.py", line 1636, in forward +[rank1]: else self._run_ddp_forward(*inputs, **kwargs) +[rank1]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/parallel/distributed.py", line 1454, in _run_ddp_forward +[rank1]: return self.module(*inputs, **kwargs) # type: ignore[index] +[rank1]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1553, in _wrapped_call_impl +[rank1]: return self._call_impl(*args, **kwargs) +[rank1]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1562, in _call_impl +[rank1]: return forward_call(*args, **kwargs) +[rank1]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/strategy.py", line 626, in wrapped_forward +[rank1]: out = method(*_args, **_kwargs) +[rank1]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/algorithms/worldmem/df_video_mamba3stage.py", line 1073, in training_step +[rank1]: self.log("training/curriculum_phase", float(phase_idx)) +[rank1]: TypeError: float() argument must be a string or a real number, not 'NoneType' +Error executing job with overrides: ['+name=train_stage_b_mamba', 'algorithm=df_video_mamba3stage', 'experiment.num_nodes=1', 'dataset.save_dir=/proj/cvl/users/x_fahkh2/WorldMem_Repro/datasets/minecraft', 'dataset.n_frames=200', '+dataset.n_frames_valid=200', '+dataset.angle_range=110', '+dataset.pos_range=8', '+dataset.wo_updown=false', '+dataset.customized_validation=true', '+dataset.add_timestamp_embedding=true', '+dataset.use_explicit_memory_frames=false', 'algorithm.training_stage=stage_b_diffusion_frozen_memory', 'algorithm.use_mamba_memory_pipeline=true', 'algorithm.use_oracle_pose_eval=false', 'algorithm.enable_memory_noise_curriculum=false', '+algorithm.require_pose_prediction=false', '+algorithm.use_memory_attention=false', '+algorithm.relative_embedding=false', '+algorithm.memory_retrieval_topk=32', 'algorithm.diff_window_size=8', 'algorithm.memory_condition_length=0', 'algorithm.context_frames=100', '+algorithm.n_tokens=8', 'experiment.training.batch_size=8', 'experiment.training.checkpointing.every_n_train_steps=2500', 'experiment.training.max_steps=60000', 'experiment.validation.val_every_n_step=2500', 'resume=stage_b_offline', '+output_dir=/proj/cvl/users/x_fahkh2/WorldMem_Repro/checkpoints/bimamba_stage_b/'] +[rank7]: Traceback (most recent call last): +[rank7]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/runpy.py", line 196, in _run_module_as_main +[rank7]: return _run_code(code, main_globals, None, +[rank7]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/runpy.py", line 86, in _run_code +[rank7]: exec(code, run_globals) +[rank7]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/main.py", line 202, in +[rank7]: run() # pylint: disable=no-value-for-parameter +[rank7]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/main.py", line 94, in decorated_main +[rank7]: _run_hydra( +[rank7]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/utils.py", line 394, in _run_hydra +[rank7]: _run_app( +[rank7]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/utils.py", line 457, in _run_app +[rank7]: run_and_report( +[rank7]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/utils.py", line 223, in run_and_report +[rank7]: raise ex +[rank7]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/utils.py", line 220, in run_and_report +[rank7]: return func() +[rank7]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/utils.py", line 458, in +[rank7]: lambda: hydra.run( +[rank7]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/hydra.py", line 132, in run +[rank7]: _ = ret.return_value +[rank7]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/core/utils.py", line 260, in return_value +[rank7]: raise self._return_value +[rank7]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/core/utils.py", line 186, in run_job +[rank7]: ret.return_value = task_function(task_cfg) +[rank7]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/main.py", line 198, in run +[rank7]: run_local(cfg) +[rank7]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/main.py", line 122, in run_local +[rank7]: experiment.exec_task(task) +[rank7]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/experiments/exp_base.py", line 172, in exec_task +[rank7]: getattr(self, task)() +[rank7]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/experiments/exp_base.py", line 371, in training +[rank7]: trainer.fit( +[rank7]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/trainer.py", line 544, in fit +[rank7]: call._call_and_handle_interrupt( +[rank7]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/call.py", line 43, in _call_and_handle_interrupt +[rank7]: return trainer.strategy.launcher.launch(trainer_fn, *args, trainer=trainer, **kwargs) +[rank7]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/launchers/subprocess_script.py", line 102, in launch +[rank7]: return function(*args, **kwargs) +[rank7]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/trainer.py", line 580, in _fit_impl +[rank7]: self._run(model, ckpt_path=ckpt_path) +[rank7]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/trainer.py", line 989, in _run +[rank7]: results = self._run_stage() +[rank7]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/trainer.py", line 1035, in _run_stage +[rank7]: self.fit_loop.run() +[rank7]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/fit_loop.py", line 202, in run +[rank7]: self.advance() +[rank7]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/fit_loop.py", line 359, in advance +[rank7]: self.epoch_loop.run(self._data_fetcher) +[rank7]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/training_epoch_loop.py", line 136, in run +[rank7]: self.advance(data_fetcher) +[rank7]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/training_epoch_loop.py", line 240, in advance +[rank7]: batch_output = self.automatic_optimization.run(trainer.optimizers[0], batch_idx, kwargs) +[rank7]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/optimization/automatic.py", line 187, in run +[rank7]: self._optimizer_step(batch_idx, closure) +[rank7]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/optimization/automatic.py", line 265, in _optimizer_step +[rank7]: call._call_lightning_module_hook( +[rank7]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/call.py", line 157, in _call_lightning_module_hook +[rank7]: output = fn(*args, **kwargs) +[rank7]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/algorithms/worldmem/df_base.py", line 65, in optimizer_step +[rank7]: optimizer.step(closure=optimizer_closure) +[rank7]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/core/optimizer.py", line 151, in step +[rank7]: step_output = self._strategy.optimizer_step(self._optimizer, closure, **kwargs) +[rank7]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/ddp.py", line 265, in optimizer_step +[rank7]: optimizer_output = super().optimizer_step(optimizer, closure, model, **kwargs) +[rank7]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/strategy.py", line 230, in optimizer_step +[rank7]: return self.precision_plugin.optimizer_step(optimizer, model=model, closure=closure, **kwargs) +[rank7]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/plugins/precision/amp.py", line 77, in optimizer_step +[rank7]: closure_result = closure() +[rank7]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/optimization/automatic.py", line 140, in __call__ +[rank7]: self._result = self.closure(*args, **kwargs) +[rank7]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 116, in decorate_context +[rank7]: return func(*args, **kwargs) +[rank7]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/optimization/automatic.py", line 126, in closure +[rank7]: step_output = self._step_fn() +[rank7]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/optimization/automatic.py", line 315, in _training_step +[rank7]: training_step_output = call._call_strategy_hook(trainer, "training_step", *kwargs.values()) +[rank7]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/call.py", line 309, in _call_strategy_hook +[rank7]: output = fn(*args, **kwargs) +[rank7]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/strategy.py", line 381, in training_step +[rank7]: return self._forward_redirection(self.model, self.lightning_module, "training_step", *args, **kwargs) +[rank7]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/strategy.py", line 633, in __call__ +[rank7]: wrapper_output = wrapper_module(*args, **kwargs) +[rank7]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1553, in _wrapped_call_impl +[rank7]: return self._call_impl(*args, **kwargs) +[rank7]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1562, in _call_impl +[rank7]: return forward_call(*args, **kwargs) +[rank7]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/parallel/distributed.py", line 1636, in forward +[rank7]: else self._run_ddp_forward(*inputs, **kwargs) +[rank7]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/parallel/distributed.py", line 1454, in _run_ddp_forward +[rank7]: return self.module(*inputs, **kwargs) # type: ignore[index] +[rank7]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1553, in _wrapped_call_impl +[rank7]: return self._call_impl(*args, **kwargs) +[rank7]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1562, in _call_impl +[rank7]: return forward_call(*args, **kwargs) +[rank7]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/strategy.py", line 626, in wrapped_forward +[rank7]: out = method(*_args, **_kwargs) +[rank7]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/algorithms/worldmem/df_video_mamba3stage.py", line 1073, in training_step +[rank7]: self.log("training/curriculum_phase", float(phase_idx)) +[rank7]: TypeError: float() argument must be a string or a real number, not 'NoneType' +srun: error: node109: task 6: Exited with exit code 1 +srun: Terminating StepId=7382.1 +[2026-03-11T19:12:56.307] error: *** STEP 7382.1 ON node109 CANCELLED AT 2026-03-11T19:12:56 DUE TO TASK FAILURE *** +srun: error: node109: task 4: Exited with exit code 1 +srun: error: node109: task 3: Exited with exit code 1 + Training: | | 0/? [00:00 +[rank3]: run() # pylint: disable=no-value-for-parameter +[rank3]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/main.py", line 94, in decorated_main +[rank3]: _run_hydra( +[rank3]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/utils.py", line 394, in _run_hydra +[rank3]: _run_app( +[rank3]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/utils.py", line 457, in _run_app +[rank3]: run_and_report( +[rank3]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/utils.py", line 223, in run_and_report +[rank3]: raise ex +[rank3]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/utils.py", line 220, in run_and_report +[rank3]: return func() +[rank3]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/utils.py", line 458, in +[rank3]: lambda: hydra.run( +[rank3]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/hydra.py", line 132, in run +[rank3]: _ = ret.return_value +[rank3]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/core/utils.py", line 260, in return_value +[rank3]: raise self._return_value +[rank3]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/core/utils.py", line 186, in run_job +[rank3]: ret.return_value = task_function(task_cfg) +[rank3]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/main.py", line 198, in run +[rank3]: run_local(cfg) +[rank3]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/main.py", line 122, in run_local +[rank3]: experiment.exec_task(task) +[rank3]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/experiments/exp_base.py", line 172, in exec_task +[rank3]: getattr(self, task)() +[rank3]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/experiments/exp_base.py", line 371, in training +[rank3]: trainer.fit( +[rank3]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/trainer.py", line 544, in fit +[rank3]: call._call_and_handle_interrupt( +[rank3]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/call.py", line 43, in _call_and_handle_interrupt +[rank3]: return trainer.strategy.launcher.launch(trainer_fn, *args, trainer=trainer, **kwargs) +[rank3]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/launchers/subprocess_script.py", line 102, in launch +[rank3]: return function(*args, **kwargs) +[rank3]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/trainer.py", line 580, in _fit_impl +[rank3]: self._run(model, ckpt_path=ckpt_path) +[rank3]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/trainer.py", line 989, in _run +[rank3]: results = self._run_stage() +[rank3]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/trainer.py", line 1035, in _run_stage +[rank3]: self.fit_loop.run() +[rank3]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/fit_loop.py", line 202, in run +[rank3]: self.advance() +[rank3]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/fit_loop.py", line 359, in advance +[rank3]: self.epoch_loop.run(self._data_fetcher) +[rank3]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/training_epoch_loop.py", line 136, in run +[rank3]: self.advance(data_fetcher) +[rank3]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/training_epoch_loop.py", line 240, in advance +[rank3]: batch_output = self.automatic_optimization.run(trainer.optimizers[0], batch_idx, kwargs) +[rank3]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/optimization/automatic.py", line 187, in run +[rank3]: self._optimizer_step(batch_idx, closure) +[rank3]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/optimization/automatic.py", line 265, in _optimizer_step +[rank3]: call._call_lightning_module_hook( +[rank3]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/call.py", line 157, in _call_lightning_module_hook +[rank3]: output = fn(*args, **kwargs) +[rank3]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/algorithms/worldmem/df_base.py", line 65, in optimizer_step +[rank3]: optimizer.step(closure=optimizer_closure) +[rank3]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/core/optimizer.py", line 151, in step +[rank3]: step_output = self._strategy.optimizer_step(self._optimizer, closure, **kwargs) +[rank3]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/ddp.py", line 265, in optimizer_step +[rank3]: optimizer_output = super().optimizer_step(optimizer, closure, model, **kwargs) +[rank3]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/strategy.py", line 230, in optimizer_step +[rank3]: return self.precision_plugin.optimizer_step(optimizer, model=model, closure=closure, **kwargs) +[rank3]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/plugins/precision/amp.py", line 77, in optimizer_step +[rank3]: closure_result = closure() +[rank3]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/optimization/automatic.py", line 140, in __call__ +[rank3]: self._result = self.closure(*args, **kwargs) +[rank3]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 116, in decorate_context +[rank3]: return func(*args, **kwargs) +[rank3]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/optimization/automatic.py", line 126, in closure +[rank3]: step_output = self._step_fn() +[rank3]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/optimization/automatic.py", line 315, in _training_step +[rank3]: training_step_output = call._call_strategy_hook(trainer, "training_step", *kwargs.values()) +[rank3]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/call.py", line 309, in _call_strategy_hook +[rank3]: output = fn(*args, **kwargs) +[rank3]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/strategy.py", line 381, in training_step +[rank3]: return self._forward_redirection(self.model, self.lightning_module, "training_step", *args, **kwargs) +[rank3]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/strategy.py", line 633, in __call__ +[rank3]: wrapper_output = wrapper_module(*args, **kwargs) +[rank3]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1553, in _wrapped_call_impl +[rank3]: return self._call_impl(*args, **kwargs) +[rank3]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1562, in _call_impl +[rank3]: return forward_call(*args, **kwargs) +[rank3]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/parallel/distributed.py", line 1636, in forward +[rank3]: else self._run_ddp_forward(*inputs, **kwargs) +[rank3]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/parallel/distributed.py", line 1454, in _run_ddp_forward +[rank3]: return self.module(*inputs, **kwargs) # type: ignore[index] +[rank3]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1553, in _wrapped_call_impl +[rank3]: return self._call_impl(*args, **kwargs) +[rank3]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1562, in _call_impl +[rank3]: return forward_call(*args, **kwargs) +[rank3]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/strategy.py", line 626, in wrapped_forward +[rank3]: out = method(*_args, **_kwargs) +[rank3]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/algorithms/worldmem/df_video_mamba3stage.py", line 1073, in training_step +[rank3]: self.log("training/curriculum_phase", float(phase_idx)) +[rank3]: TypeError: float() argument must be a string or a real number, not 'NoneType' +Traceback (most recent call last): + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 300, in _run_finalizers + finalizer() + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 224, in __call__ + res = self._callback(*self._args, **self._kwargs) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 133, in _remove_temp_dir + rmtree(tempdir) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 725, in rmtree + _rmtree_safe_fd(fd, path, onerror) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 681, in _rmtree_safe_fd + onerror(os.unlink, fullname, sys.exc_info()) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 679, in _rmtree_safe_fd + os.unlink(entry.name, dir_fd=topfd) +OSError: [Errno 16] Device or resource busy: '.nfs951f1e300f55a554000002fe' +Traceback (most recent call last): + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 300, in _run_finalizers + finalizer() + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 224, in __call__ + res = self._callback(*self._args, **self._kwargs) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 133, in _remove_temp_dir + rmtree(tempdir) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 725, in rmtree + _rmtree_safe_fd(fd, path, onerror) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 681, in _rmtree_safe_fd + onerror(os.unlink, fullname, sys.exc_info()) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 679, in _rmtree_safe_fd + os.unlink(entry.name, dir_fd=topfd) +OSError: [Errno 16] Device or resource busy: '.nfse088d6b4e1f9aead000002ff' +Traceback (most recent call last): + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 300, in _run_finalizers + finalizer() + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 224, in __call__ + res = self._callback(*self._args, **self._kwargs) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 133, in _remove_temp_dir + rmtree(tempdir) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 725, in rmtree + _rmtree_safe_fd(fd, path, onerror) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 681, in _rmtree_safe_fd + onerror(os.unlink, fullname, sys.exc_info()) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 679, in _rmtree_safe_fd + os.unlink(entry.name, dir_fd=topfd) +OSError: [Errno 16] Device or resource busy: '.nfsfd7795ed81f092f900000300' +Traceback (most recent call last): + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 300, in _run_finalizers + finalizer() + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 224, in __call__ + res = self._callback(*self._args, **self._kwargs) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 133, in _remove_temp_dir + rmtree(tempdir) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 725, in rmtree + _rmtree_safe_fd(fd, path, onerror) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 681, in _rmtree_safe_fd + onerror(os.unlink, fullname, sys.exc_info()) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 679, in _rmtree_safe_fd + os.unlink(entry.name, dir_fd=topfd) +OSError: [Errno 16] Device or resource busy: '.nfs3e945a9669e9ce9a00000301' +Traceback (most recent call last): + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 300, in _run_finalizers + finalizer() + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 224, in __call__ + res = self._callback(*self._args, **self._kwargs) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 133, in _remove_temp_dir + rmtree(tempdir) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 725, in rmtree + _rmtree_safe_fd(fd, path, onerror) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 681, in _rmtree_safe_fd + onerror(os.unlink, fullname, sys.exc_info()) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 679, in _rmtree_safe_fd + os.unlink(entry.name, dir_fd=topfd) +OSError: [Errno 16] Device or resource busy: '.nfsb49412da2ae7fef600000303' +Traceback (most recent call last): + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 300, in _run_finalizers + finalizer() + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 224, in __call__ + res = self._callback(*self._args, **self._kwargs) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 133, in _remove_temp_dir + rmtree(tempdir) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 725, in rmtree + _rmtree_safe_fd(fd, path, onerror) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 681, in _rmtree_safe_fd + onerror(os.unlink, fullname, sys.exc_info()) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 679, in _rmtree_safe_fd + os.unlink(entry.name, dir_fd=topfd) +OSError: [Errno 16] Device or resource busy: '.nfs25efc39f9888a1f200000302' +Traceback (most recent call last): + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 300, in _run_finalizers + finalizer() + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 224, in __call__ + res = self._callback(*self._args, **self._kwargs) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 133, in _remove_temp_dir + rmtree(tempdir) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 725, in rmtree + _rmtree_safe_fd(fd, path, onerror) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 681, in _rmtree_safe_fd + onerror(os.unlink, fullname, sys.exc_info()) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 679, in _rmtree_safe_fd + os.unlink(entry.name, dir_fd=topfd) +OSError: [Errno 16] Device or resource busy: '.nfsd696dd4acbab45c400000304' +Traceback (most recent call last): + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 300, in _run_finalizers + finalizer() + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 224, in __call__ + res = self._callback(*self._args, **self._kwargs) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 133, in _remove_temp_dir + rmtree(tempdir) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 725, in rmtree + _rmtree_safe_fd(fd, path, onerror) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 681, in _rmtree_safe_fd + onerror(os.unlink, fullname, sys.exc_info()) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 679, in _rmtree_safe_fd + os.unlink(entry.name, dir_fd=topfd) +OSError: [Errno 16] Device or resource busy: '.nfs72672062820b00e400000305' +Traceback (most recent call last): + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 300, in _run_finalizers + finalizer() + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 224, in __call__ + res = self._callback(*self._args, **self._kwargs) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 133, in _remove_temp_dir + rmtree(tempdir) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 725, in rmtree + _rmtree_safe_fd(fd, path, onerror) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 681, in _rmtree_safe_fd + onerror(os.unlink, fullname, sys.exc_info()) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 679, in _rmtree_safe_fd + os.unlink(entry.name, dir_fd=topfd) +OSError: [Errno 16] Device or resource busy: '.nfs43facad8025e4ec900000306' +Traceback (most recent call last): + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 300, in _run_finalizers + finalizer() + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 224, in __call__ + res = self._callback(*self._args, **self._kwargs) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 133, in _remove_temp_dir + rmtree(tempdir) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 725, in rmtree + _rmtree_safe_fd(fd, path, onerror) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 681, in _rmtree_safe_fd + onerror(os.unlink, fullname, sys.exc_info()) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 679, in _rmtree_safe_fd + os.unlink(entry.name, dir_fd=topfd) +OSError: [Errno 16] Device or resource busy: '.nfsfc1cd3d0ddef284100000307' +Traceback (most recent call last): + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 300, in _run_finalizers + finalizer() + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 224, in __call__ + res = self._callback(*self._args, **self._kwargs) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 133, in _remove_temp_dir + rmtree(tempdir) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 725, in rmtree + _rmtree_safe_fd(fd, path, onerror) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 681, in _rmtree_safe_fd + onerror(os.unlink, fullname, sys.exc_info()) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 679, in _rmtree_safe_fd + os.unlink(entry.name, dir_fd=topfd) +OSError: [Errno 16] Device or resource busy: '.nfsb0116cb4f59b393100000308' +Traceback (most recent call last): + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 300, in _run_finalizers + finalizer() + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 224, in __call__ + res = self._callback(*self._args, **self._kwargs) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 133, in _remove_temp_dir + rmtree(tempdir) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 725, in rmtree + _rmtree_safe_fd(fd, path, onerror) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 681, in _rmtree_safe_fd + onerror(os.unlink, fullname, sys.exc_info()) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 679, in _rmtree_safe_fd + os.unlink(entry.name, dir_fd=topfd) +OSError: [Errno 16] Device or resource busy: '.nfs8bccb6146f87903000000309' +Traceback (most recent call last): + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 300, in _run_finalizers + finalizer() + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 224, in __call__ + res = self._callback(*self._args, **self._kwargs) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 133, in _remove_temp_dir + rmtree(tempdir) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 725, in rmtree + _rmtree_safe_fd(fd, path, onerror) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 681, in _rmtree_safe_fd + onerror(os.unlink, fullname, sys.exc_info()) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 679, in _rmtree_safe_fd + os.unlink(entry.name, dir_fd=topfd) +OSError: [Errno 16] Device or resource busy: '.nfs2fab6ba82e6afd0a0000030a' +Traceback (most recent call last): + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 300, in _run_finalizers + finalizer() + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 224, in __call__ + res = self._callback(*self._args, **self._kwargs) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 133, in _remove_temp_dir + rmtree(tempdir) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 725, in rmtree + _rmtree_safe_fd(fd, path, onerror) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 681, in _rmtree_safe_fd + onerror(os.unlink, fullname, sys.exc_info()) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 679, in _rmtree_safe_fd + os.unlink(entry.name, dir_fd=topfd) +OSError: [Errno 16] Device or resource busy: '.nfs2f013097f85abe080000030b' +Traceback (most recent call last): + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 300, in _run_finalizers + finalizer() + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 224, in __call__ + res = self._callback(*self._args, **self._kwargs) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 133, in _remove_temp_dir + rmtree(tempdir) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 725, in rmtree + _rmtree_safe_fd(fd, path, onerror) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 681, in _rmtree_safe_fd + onerror(os.unlink, fullname, sys.exc_info()) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 679, in _rmtree_safe_fd + os.unlink(entry.name, dir_fd=topfd) +OSError: [Errno 16] Device or resource busy: '.nfs440182216121e5b80000030c' +Traceback (most recent call last): + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 300, in _run_finalizers + finalizer() + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 224, in __call__ + res = self._callback(*self._args, **self._kwargs) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 133, in _remove_temp_dir + rmtree(tempdir) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 725, in rmtree + _rmtree_safe_fd(fd, path, onerror) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 681, in _rmtree_safe_fd + onerror(os.unlink, fullname, sys.exc_info()) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 679, in _rmtree_safe_fd + os.unlink(entry.name, dir_fd=topfd) +OSError: [Errno 16] Device or resource busy: '.nfse6d490efff902e300000030d' +Traceback (most recent call last): + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 300, in _run_finalizers + finalizer() + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 224, in __call__ + res = self._callback(*self._args, **self._kwargs) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 133, in _remove_temp_dir + rmtree(tempdir) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 725, in rmtree + _rmtree_safe_fd(fd, path, onerror) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 681, in _rmtree_safe_fd + onerror(os.unlink, fullname, sys.exc_info()) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 679, in _rmtree_safe_fd + os.unlink(entry.name, dir_fd=topfd) +OSError: [Errno 16] Device or resource busy: '.nfs5f328fe42087769d0000030e' +Traceback (most recent call last): + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 300, in _run_finalizers + finalizer() + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 224, in __call__ + res = self._callback(*self._args, **self._kwargs) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 133, in _remove_temp_dir + rmtree(tempdir) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 725, in rmtree + _rmtree_safe_fd(fd, path, onerror) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 681, in _rmtree_safe_fd + onerror(os.unlink, fullname, sys.exc_info()) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 679, in _rmtree_safe_fd + os.unlink(entry.name, dir_fd=topfd) +OSError: [Errno 16] Device or resource busy: '.nfs97044d8b9d1cc1aa0000030f' +Traceback (most recent call last): + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 300, in _run_finalizers + finalizer() + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 224, in __call__ + res = self._callback(*self._args, **self._kwargs) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 133, in _remove_temp_dir + rmtree(tempdir) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 725, in rmtree + _rmtree_safe_fd(fd, path, onerror) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 681, in _rmtree_safe_fd + onerror(os.unlink, fullname, sys.exc_info()) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 679, in _rmtree_safe_fd + os.unlink(entry.name, dir_fd=topfd) +OSError: [Errno 16] Device or resource busy: '.nfs2d62f34d94bd1e7500000310' +Error executing job with overrides: ['+name=train_stage_b_mamba', 'algorithm=df_video_mamba3stage', 'experiment.num_nodes=1', 'dataset.save_dir=/proj/cvl/users/x_fahkh2/WorldMem_Repro/datasets/minecraft', 'dataset.n_frames=200', '+dataset.n_frames_valid=200', '+dataset.angle_range=110', '+dataset.pos_range=8', '+dataset.wo_updown=false', '+dataset.customized_validation=true', '+dataset.add_timestamp_embedding=true', '+dataset.use_explicit_memory_frames=false', 'algorithm.training_stage=stage_b_diffusion_frozen_memory', 'algorithm.use_mamba_memory_pipeline=true', 'algorithm.use_oracle_pose_eval=false', 'algorithm.enable_memory_noise_curriculum=false', '+algorithm.require_pose_prediction=false', '+algorithm.use_memory_attention=false', '+algorithm.relative_embedding=false', '+algorithm.memory_retrieval_topk=32', 'algorithm.diff_window_size=8', 'algorithm.memory_condition_length=0', 'algorithm.context_frames=100', '+algorithm.n_tokens=8', 'experiment.training.batch_size=8', 'experiment.training.checkpointing.every_n_train_steps=2500', 'experiment.training.max_steps=175000', 'experiment.validation.val_every_n_step=2500', 'resume=stage_b_offline', '+output_dir=/proj/cvl/users/x_fahkh2/WorldMem_Repro/checkpoints/bimamba_stage_b/'] +Traceback (most recent call last): + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/runpy.py", line 196, in _run_module_as_main + return _run_code(code, main_globals, None, + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/runpy.py", line 86, in _run_code + exec(code, run_globals) + File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/main.py", line 202, in + run() # pylint: disable=no-value-for-parameter + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/main.py", line 94, in decorated_main + _run_hydra( + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/utils.py", line 394, in _run_hydra + _run_app( + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/utils.py", line 457, in _run_app + run_and_report( + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/utils.py", line 223, in run_and_report + raise ex + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/utils.py", line 220, in run_and_report + return func() + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/utils.py", line 458, in + lambda: hydra.run( + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/hydra.py", line 132, in run + _ = ret.return_value + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/core/utils.py", line 260, in return_value + raise self._return_value + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/core/utils.py", line 186, in run_job + ret.return_value = task_function(task_cfg) + File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/main.py", line 198, in run + run_local(cfg) + File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/main.py", line 122, in run_local + experiment.exec_task(task) + File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/experiments/exp_base.py", line 172, in exec_task + getattr(self, task)() + File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/experiments/exp_base.py", line 371, in training + trainer.fit( + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/trainer.py", line 544, in fit + call._call_and_handle_interrupt( + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/call.py", line 43, in _call_and_handle_interrupt + return trainer.strategy.launcher.launch(trainer_fn, *args, trainer=trainer, **kwargs) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/launchers/subprocess_script.py", line 102, in launch + return function(*args, **kwargs) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/trainer.py", line 580, in _fit_impl + self._run(model, ckpt_path=ckpt_path) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/trainer.py", line 989, in _run + results = self._run_stage() + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/trainer.py", line 1035, in _run_stage + self.fit_loop.run() + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/fit_loop.py", line 202, in run + self.advance() + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/fit_loop.py", line 359, in advance + self.epoch_loop.run(self._data_fetcher) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/training_epoch_loop.py", line 136, in run + self.advance(data_fetcher) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/training_epoch_loop.py", line 240, in advance + batch_output = self.automatic_optimization.run(trainer.optimizers[0], batch_idx, kwargs) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/optimization/automatic.py", line 187, in run + self._optimizer_step(batch_idx, closure) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/optimization/automatic.py", line 265, in _optimizer_step + call._call_lightning_module_hook( + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/call.py", line 157, in _call_lightning_module_hook + output = fn(*args, **kwargs) + File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/algorithms/worldmem/df_base.py", line 65, in optimizer_step + optimizer.step(closure=optimizer_closure) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/core/optimizer.py", line 151, in step + step_output = self._strategy.optimizer_step(self._optimizer, closure, **kwargs) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/ddp.py", line 265, in optimizer_step + optimizer_output = super().optimizer_step(optimizer, closure, model, **kwargs) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/strategy.py", line 230, in optimizer_step + return self.precision_plugin.optimizer_step(optimizer, model=model, closure=closure, **kwargs) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/plugins/precision/amp.py", line 77, in optimizer_step + closure_result = closure() + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/optimization/automatic.py", line 140, in __call__ + self._result = self.closure(*args, **kwargs) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 116, in decorate_context + return func(*args, **kwargs) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/optimization/automatic.py", line 126, in closure + step_output = self._step_fn() + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/optimization/automatic.py", line 315, in _training_step + training_step_output = call._call_strategy_hook(trainer, "training_step", *kwargs.values()) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/call.py", line 309, in _call_strategy_hook + output = fn(*args, **kwargs) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/strategy.py", line 381, in training_step + return self._forward_redirection(self.model, self.lightning_module, "training_step", *args, **kwargs) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/strategy.py", line 633, in __call__ + wrapper_output = wrapper_module(*args, **kwargs) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1553, in _wrapped_call_impl + return self._call_impl(*args, **kwargs) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1562, in _call_impl + return forward_call(*args, **kwargs) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/parallel/distributed.py", line 1636, in forward + else self._run_ddp_forward(*inputs, **kwargs) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/parallel/distributed.py", line 1454, in _run_ddp_forward + return self.module(*inputs, **kwargs) # type: ignore[index] + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1553, in _wrapped_call_impl + return self._call_impl(*args, **kwargs) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1562, in _call_impl + return forward_call(*args, **kwargs) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/strategy.py", line 626, in wrapped_forward + out = method(*_args, **_kwargs) + File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/algorithms/worldmem/df_video_mamba3stage.py", line 1073, in training_step + self.log("training/curriculum_phase", float(phase_idx)) +TypeError: float() argument must be a string or a real number, not 'NoneType' +[rank0]: Traceback (most recent call last): +[rank0]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/runpy.py", line 196, in _run_module_as_main +[rank0]: return _run_code(code, main_globals, None, +[rank0]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/runpy.py", line 86, in _run_code +[rank0]: exec(code, run_globals) +[rank0]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/main.py", line 202, in +[rank0]: run() # pylint: disable=no-value-for-parameter +[rank0]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/main.py", line 94, in decorated_main +[rank0]: _run_hydra( +[rank0]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/utils.py", line 394, in _run_hydra +[rank0]: _run_app( +[rank0]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/utils.py", line 457, in _run_app +[rank0]: run_and_report( +[rank0]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/utils.py", line 223, in run_and_report +[rank0]: raise ex +[rank0]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/utils.py", line 220, in run_and_report +[rank0]: return func() +[rank0]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/utils.py", line 458, in +[rank0]: lambda: hydra.run( +[rank0]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/hydra.py", line 132, in run +[rank0]: _ = ret.return_value +[rank0]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/core/utils.py", line 260, in return_value +[rank0]: raise self._return_value +[rank0]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/core/utils.py", line 186, in run_job +[rank0]: ret.return_value = task_function(task_cfg) +[rank0]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/main.py", line 198, in run +[rank0]: run_local(cfg) +[rank0]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/main.py", line 122, in run_local +[rank0]: experiment.exec_task(task) +[rank0]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/experiments/exp_base.py", line 172, in exec_task +[rank0]: getattr(self, task)() +[rank0]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/experiments/exp_base.py", line 371, in training +[rank0]: trainer.fit( +[rank0]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/trainer.py", line 544, in fit +[rank0]: call._call_and_handle_interrupt( +[rank0]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/call.py", line 43, in _call_and_handle_interrupt +[rank0]: return trainer.strategy.launcher.launch(trainer_fn, *args, trainer=trainer, **kwargs) +[rank0]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/launchers/subprocess_script.py", line 102, in launch +[rank0]: return function(*args, **kwargs) +[rank0]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/trainer.py", line 580, in _fit_impl +[rank0]: self._run(model, ckpt_path=ckpt_path) +[rank0]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/trainer.py", line 989, in _run +[rank0]: results = self._run_stage() +[rank0]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/trainer.py", line 1035, in _run_stage +[rank0]: self.fit_loop.run() +[rank0]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/fit_loop.py", line 202, in run +[rank0]: self.advance() +[rank0]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/fit_loop.py", line 359, in advance +[rank0]: self.epoch_loop.run(self._data_fetcher) +[rank0]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/training_epoch_loop.py", line 136, in run +[rank0]: self.advance(data_fetcher) +[rank0]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/training_epoch_loop.py", line 240, in advance +[rank0]: batch_output = self.automatic_optimization.run(trainer.optimizers[0], batch_idx, kwargs) +[rank0]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/optimization/automatic.py", line 187, in run +[rank0]: self._optimizer_step(batch_idx, closure) +[rank0]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/optimization/automatic.py", line 265, in _optimizer_step +[rank0]: call._call_lightning_module_hook( +[rank0]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/call.py", line 157, in _call_lightning_module_hook +[rank0]: output = fn(*args, **kwargs) +[rank0]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/algorithms/worldmem/df_base.py", line 65, in optimizer_step +[rank0]: optimizer.step(closure=optimizer_closure) +[rank0]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/core/optimizer.py", line 151, in step +[rank0]: step_output = self._strategy.optimizer_step(self._optimizer, closure, **kwargs) +[rank0]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/ddp.py", line 265, in optimizer_step +[rank0]: optimizer_output = super().optimizer_step(optimizer, closure, model, **kwargs) +[rank0]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/strategy.py", line 230, in optimizer_step +[rank0]: return self.precision_plugin.optimizer_step(optimizer, model=model, closure=closure, **kwargs) +[rank0]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/plugins/precision/amp.py", line 77, in optimizer_step +[rank0]: closure_result = closure() +[rank0]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/optimization/automatic.py", line 140, in __call__ +[rank0]: self._result = self.closure(*args, **kwargs) +[rank0]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 116, in decorate_context +[rank0]: return func(*args, **kwargs) +[rank0]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/optimization/automatic.py", line 126, in closure +[rank0]: step_output = self._step_fn() +[rank0]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/optimization/automatic.py", line 315, in _training_step +[rank0]: training_step_output = call._call_strategy_hook(trainer, "training_step", *kwargs.values()) +[rank0]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/call.py", line 309, in _call_strategy_hook +[rank0]: output = fn(*args, **kwargs) +[rank0]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/strategy.py", line 381, in training_step +[rank0]: return self._forward_redirection(self.model, self.lightning_module, "training_step", *args, **kwargs) +[rank0]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/strategy.py", line 633, in __call__ +[rank0]: wrapper_output = wrapper_module(*args, **kwargs) +[rank0]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1553, in _wrapped_call_impl +[rank0]: return self._call_impl(*args, **kwargs) +[rank0]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1562, in _call_impl +[rank0]: return forward_call(*args, **kwargs) +[rank0]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/parallel/distributed.py", line 1636, in forward +[rank0]: else self._run_ddp_forward(*inputs, **kwargs) +[rank0]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/parallel/distributed.py", line 1454, in _run_ddp_forward +[rank0]: return self.module(*inputs, **kwargs) # type: ignore[index] +[rank0]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1553, in _wrapped_call_impl +[rank0]: return self._call_impl(*args, **kwargs) +[rank0]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1562, in _call_impl +[rank0]: return forward_call(*args, **kwargs) +[rank0]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/strategy.py", line 626, in wrapped_forward +[rank0]: out = method(*_args, **_kwargs) +[rank0]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/algorithms/worldmem/df_video_mamba3stage.py", line 1073, in training_step +[rank0]: self.log("training/curriculum_phase", float(phase_idx)) +[rank0]: TypeError: float() argument must be a string or a real number, not 'NoneType' +Traceback (most recent call last): + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 300, in _run_finalizers + finalizer() + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 224, in __call__ + res = self._callback(*self._args, **self._kwargs) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 133, in _remove_temp_dir + rmtree(tempdir) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 725, in rmtree + _rmtree_safe_fd(fd, path, onerror) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 681, in _rmtree_safe_fd + onerror(os.unlink, fullname, sys.exc_info()) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 679, in _rmtree_safe_fd + os.unlink(entry.name, dir_fd=topfd) +OSError: [Errno 16] Device or resource busy: '.nfs90df101c141fa00c00000311' +Traceback (most recent call last): + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 300, in _run_finalizers + finalizer() + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 224, in __call__ + res = self._callback(*self._args, **self._kwargs) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 133, in _remove_temp_dir + rmtree(tempdir) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 725, in rmtree + _rmtree_safe_fd(fd, path, onerror) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 681, in _rmtree_safe_fd + onerror(os.unlink, fullname, sys.exc_info()) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 679, in _rmtree_safe_fd + os.unlink(entry.name, dir_fd=topfd) +OSError: [Errno 16] Device or resource busy: '.nfsca22b33c7e37fd3900000312' +Traceback (most recent call last): + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 300, in _run_finalizers + finalizer() + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 224, in __call__ + res = self._callback(*self._args, **self._kwargs) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 133, in _remove_temp_dir + rmtree(tempdir) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 725, in rmtree + _rmtree_safe_fd(fd, path, onerror) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 681, in _rmtree_safe_fd + onerror(os.unlink, fullname, sys.exc_info()) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 679, in _rmtree_safe_fd + os.unlink(entry.name, dir_fd=topfd) +OSError: [Errno 16] Device or resource busy: '.nfs32ec70a740f41e1e00000313' +Error executing job with overrides: ['+name=train_stage_b_mamba', 'algorithm=df_video_mamba3stage', 'experiment.num_nodes=1', 'dataset.save_dir=/proj/cvl/users/x_fahkh2/WorldMem_Repro/datasets/minecraft', 'dataset.n_frames=200', '+dataset.n_frames_valid=200', '+dataset.angle_range=110', '+dataset.pos_range=8', '+dataset.wo_updown=false', '+dataset.customized_validation=true', '+dataset.add_timestamp_embedding=true', '+dataset.use_explicit_memory_frames=false', 'algorithm.training_stage=stage_b_diffusion_frozen_memory', 'algorithm.use_mamba_memory_pipeline=true', 'algorithm.use_oracle_pose_eval=false', 'algorithm.enable_memory_noise_curriculum=false', '+algorithm.require_pose_prediction=false', '+algorithm.use_memory_attention=false', '+algorithm.relative_embedding=false', '+algorithm.memory_retrieval_topk=32', 'algorithm.diff_window_size=8', 'algorithm.memory_condition_length=0', 'algorithm.context_frames=100', '+algorithm.n_tokens=8', 'experiment.training.batch_size=8', 'experiment.training.checkpointing.every_n_train_steps=2500', 'experiment.training.max_steps=175000', 'experiment.validation.val_every_n_step=2500', 'resume=stage_b_offline', '+output_dir=/proj/cvl/users/x_fahkh2/WorldMem_Repro/checkpoints/bimamba_stage_b/'] +[rank7]: Traceback (most recent call last): +[rank7]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/runpy.py", line 196, in _run_module_as_main +[rank7]: return _run_code(code, main_globals, None, +[rank7]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/runpy.py", line 86, in _run_code +[rank7]: exec(code, run_globals) +[rank7]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/main.py", line 202, in +[rank7]: run() # pylint: disable=no-value-for-parameter +[rank7]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/main.py", line 94, in decorated_main +[rank7]: _run_hydra( +[rank7]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/utils.py", line 394, in _run_hydra +[rank7]: _run_app( +[rank7]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/utils.py", line 457, in _run_app +[rank7]: run_and_report( +[rank7]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/utils.py", line 223, in run_and_report +[rank7]: raise ex +[rank7]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/utils.py", line 220, in run_and_report +[rank7]: return func() +[rank7]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/utils.py", line 458, in +[rank7]: lambda: hydra.run( +[rank7]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/hydra.py", line 132, in run +[rank7]: _ = ret.return_value +[rank7]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/core/utils.py", line 260, in return_value +[rank7]: raise self._return_value +[rank7]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/core/utils.py", line 186, in run_job +[rank7]: ret.return_value = task_function(task_cfg) +[rank7]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/main.py", line 198, in run +[rank7]: run_local(cfg) +[rank7]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/main.py", line 122, in run_local +[rank7]: experiment.exec_task(task) +[rank7]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/experiments/exp_base.py", line 172, in exec_task +[rank7]: getattr(self, task)() +[rank7]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/experiments/exp_base.py", line 371, in training +[rank7]: trainer.fit( +[rank7]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/trainer.py", line 544, in fit +[rank7]: call._call_and_handle_interrupt( +[rank7]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/call.py", line 43, in _call_and_handle_interrupt +[rank7]: return trainer.strategy.launcher.launch(trainer_fn, *args, trainer=trainer, **kwargs) +[rank7]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/launchers/subprocess_script.py", line 102, in launch +[rank7]: return function(*args, **kwargs) +[rank7]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/trainer.py", line 580, in _fit_impl +[rank7]: self._run(model, ckpt_path=ckpt_path) +[rank7]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/trainer.py", line 989, in _run +[rank7]: results = self._run_stage() +[rank7]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/trainer.py", line 1035, in _run_stage +[rank7]: self.fit_loop.run() +[rank7]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/fit_loop.py", line 202, in run +[rank7]: self.advance() +[rank7]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/fit_loop.py", line 359, in advance +[rank7]: self.epoch_loop.run(self._data_fetcher) +[rank7]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/training_epoch_loop.py", line 136, in run +[rank7]: self.advance(data_fetcher) +[rank7]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/training_epoch_loop.py", line 240, in advance +[rank7]: batch_output = self.automatic_optimization.run(trainer.optimizers[0], batch_idx, kwargs) +[rank7]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/optimization/automatic.py", line 187, in run +[rank7]: self._optimizer_step(batch_idx, closure) +[rank7]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/optimization/automatic.py", line 265, in _optimizer_step +[rank7]: call._call_lightning_module_hook( +[rank7]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/call.py", line 157, in _call_lightning_module_hook +[rank7]: output = fn(*args, **kwargs) +[rank7]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/algorithms/worldmem/df_base.py", line 65, in optimizer_step +[rank7]: optimizer.step(closure=optimizer_closure) +[rank7]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/core/optimizer.py", line 151, in step +[rank7]: step_output = self._strategy.optimizer_step(self._optimizer, closure, **kwargs) +[rank7]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/ddp.py", line 265, in optimizer_step +[rank7]: optimizer_output = super().optimizer_step(optimizer, closure, model, **kwargs) +[rank7]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/strategy.py", line 230, in optimizer_step +[rank7]: return self.precision_plugin.optimizer_step(optimizer, model=model, closure=closure, **kwargs) +[rank7]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/plugins/precision/amp.py", line 77, in optimizer_step +[rank7]: closure_result = closure() +[rank7]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/optimization/automatic.py", line 140, in __call__ +[rank7]: self._result = self.closure(*args, **kwargs) +[rank7]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 116, in decorate_context +[rank7]: return func(*args, **kwargs) +[rank7]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/optimization/automatic.py", line 126, in closure +[rank7]: step_output = self._step_fn() +[rank7]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/optimization/automatic.py", line 315, in _training_step +[rank7]: training_step_output = call._call_strategy_hook(trainer, "training_step", *kwargs.values()) +[rank7]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/call.py", line 309, in _call_strategy_hook +[rank7]: output = fn(*args, **kwargs) +[rank7]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/strategy.py", line 381, in training_step +[rank7]: return self._forward_redirection(self.model, self.lightning_module, "training_step", *args, **kwargs) +[rank7]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/strategy.py", line 633, in __call__ +[rank7]: wrapper_output = wrapper_module(*args, **kwargs) +[rank7]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1553, in _wrapped_call_impl +[rank7]: return self._call_impl(*args, **kwargs) +[rank7]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1562, in _call_impl +[rank7]: return forward_call(*args, **kwargs) +[rank7]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/parallel/distributed.py", line 1636, in forward +[rank7]: else self._run_ddp_forward(*inputs, **kwargs) +[rank7]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/parallel/distributed.py", line 1454, in _run_ddp_forward +[rank7]: return self.module(*inputs, **kwargs) # type: ignore[index] +[rank7]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1553, in _wrapped_call_impl +[rank7]: return self._call_impl(*args, **kwargs) +[rank7]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1562, in _call_impl +[rank7]: return forward_call(*args, **kwargs) +[rank7]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/strategy.py", line 626, in wrapped_forward +[rank7]: out = method(*_args, **_kwargs) +[rank7]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/algorithms/worldmem/df_video_mamba3stage.py", line 1073, in training_step +[rank7]: self.log("training/curriculum_phase", float(phase_idx)) +[rank7]: TypeError: float() argument must be a string or a real number, not 'NoneType' +Error executing job with overrides: ['+name=train_stage_b_mamba', 'algorithm=df_video_mamba3stage', 'experiment.num_nodes=1', 'dataset.save_dir=/proj/cvl/users/x_fahkh2/WorldMem_Repro/datasets/minecraft', 'dataset.n_frames=200', '+dataset.n_frames_valid=200', '+dataset.angle_range=110', '+dataset.pos_range=8', '+dataset.wo_updown=false', '+dataset.customized_validation=true', '+dataset.add_timestamp_embedding=true', '+dataset.use_explicit_memory_frames=false', 'algorithm.training_stage=stage_b_diffusion_frozen_memory', 'algorithm.use_mamba_memory_pipeline=true', 'algorithm.use_oracle_pose_eval=false', 'algorithm.enable_memory_noise_curriculum=false', '+algorithm.require_pose_prediction=false', '+algorithm.use_memory_attention=false', '+algorithm.relative_embedding=false', '+algorithm.memory_retrieval_topk=32', 'algorithm.diff_window_size=8', 'algorithm.memory_condition_length=0', 'algorithm.context_frames=100', '+algorithm.n_tokens=8', 'experiment.training.batch_size=8', 'experiment.training.checkpointing.every_n_train_steps=2500', 'experiment.training.max_steps=175000', 'experiment.validation.val_every_n_step=2500', 'resume=stage_b_offline', '+output_dir=/proj/cvl/users/x_fahkh2/WorldMem_Repro/checkpoints/bimamba_stage_b/'] +[rank4]: Traceback (most recent call last): +[rank4]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/runpy.py", line 196, in _run_module_as_main +[rank4]: return _run_code(code, main_globals, None, +[rank4]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/runpy.py", line 86, in _run_code +[rank4]: exec(code, run_globals) +[rank4]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/main.py", line 202, in +[rank4]: run() # pylint: disable=no-value-for-parameter +[rank4]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/main.py", line 94, in decorated_main +[rank4]: _run_hydra( +[rank4]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/utils.py", line 394, in _run_hydra +[rank4]: _run_app( +[rank4]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/utils.py", line 457, in _run_app +[rank4]: run_and_report( +[rank4]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/utils.py", line 223, in run_and_report +[rank4]: raise ex +[rank4]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/utils.py", line 220, in run_and_report +[rank4]: return func() +[rank4]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/utils.py", line 458, in +[rank4]: lambda: hydra.run( +[rank4]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/hydra.py", line 132, in run +[rank4]: _ = ret.return_value +[rank4]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/core/utils.py", line 260, in return_value +[rank4]: raise self._return_value +[rank4]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/core/utils.py", line 186, in run_job +[rank4]: ret.return_value = task_function(task_cfg) +[rank4]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/main.py", line 198, in run +[rank4]: run_local(cfg) +[rank4]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/main.py", line 122, in run_local +[rank4]: experiment.exec_task(task) +[rank4]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/experiments/exp_base.py", line 172, in exec_task +[rank4]: getattr(self, task)() +[rank4]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/experiments/exp_base.py", line 371, in training +[rank4]: trainer.fit( +[rank4]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/trainer.py", line 544, in fit +[rank4]: call._call_and_handle_interrupt( +[rank4]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/call.py", line 43, in _call_and_handle_interrupt +[rank4]: return trainer.strategy.launcher.launch(trainer_fn, *args, trainer=trainer, **kwargs) +[rank4]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/launchers/subprocess_script.py", line 102, in launch +[rank4]: return function(*args, **kwargs) +[rank4]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/trainer.py", line 580, in _fit_impl +[rank4]: self._run(model, ckpt_path=ckpt_path) +[rank4]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/trainer.py", line 989, in _run +[rank4]: results = self._run_stage() +[rank4]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/trainer.py", line 1035, in _run_stage +[rank4]: self.fit_loop.run() +[rank4]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/fit_loop.py", line 202, in run +[rank4]: self.advance() +[rank4]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/fit_loop.py", line 359, in advance +[rank4]: self.epoch_loop.run(self._data_fetcher) +[rank4]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/training_epoch_loop.py", line 136, in run +[rank4]: self.advance(data_fetcher) +[rank4]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/training_epoch_loop.py", line 240, in advance +[rank4]: batch_output = self.automatic_optimization.run(trainer.optimizers[0], batch_idx, kwargs) +[rank4]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/optimization/automatic.py", line 187, in run +[rank4]: self._optimizer_step(batch_idx, closure) +[rank4]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/optimization/automatic.py", line 265, in _optimizer_step +[rank4]: call._call_lightning_module_hook( +[rank4]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/call.py", line 157, in _call_lightning_module_hook +[rank4]: output = fn(*args, **kwargs) +[rank4]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/algorithms/worldmem/df_base.py", line 65, in optimizer_step +[rank4]: optimizer.step(closure=optimizer_closure) +[rank4]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/core/optimizer.py", line 151, in step +[rank4]: step_output = self._strategy.optimizer_step(self._optimizer, closure, **kwargs) +[rank4]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/ddp.py", line 265, in optimizer_step +[rank4]: optimizer_output = super().optimizer_step(optimizer, closure, model, **kwargs) +[rank4]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/strategy.py", line 230, in optimizer_step +[rank4]: return self.precision_plugin.optimizer_step(optimizer, model=model, closure=closure, **kwargs) +[rank4]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/plugins/precision/amp.py", line 77, in optimizer_step +[rank4]: closure_result = closure() +[rank4]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/optimization/automatic.py", line 140, in __call__ +[rank4]: self._result = self.closure(*args, **kwargs) +[rank4]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 116, in decorate_context +[rank4]: return func(*args, **kwargs) +[rank4]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/optimization/automatic.py", line 126, in closure +[rank4]: step_output = self._step_fn() +[rank4]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/optimization/automatic.py", line 315, in _training_step +[rank4]: training_step_output = call._call_strategy_hook(trainer, "training_step", *kwargs.values()) +[rank4]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/call.py", line 309, in _call_strategy_hook +[rank4]: output = fn(*args, **kwargs) +[rank4]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/strategy.py", line 381, in training_step +[rank4]: return self._forward_redirection(self.model, self.lightning_module, "training_step", *args, **kwargs) +[rank4]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/strategy.py", line 633, in __call__ +[rank4]: wrapper_output = wrapper_module(*args, **kwargs) +[rank4]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1553, in _wrapped_call_impl +[rank4]: return self._call_impl(*args, **kwargs) +[rank4]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1562, in _call_impl +[rank4]: return forward_call(*args, **kwargs) +[rank4]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/parallel/distributed.py", line 1636, in forward +[rank4]: else self._run_ddp_forward(*inputs, **kwargs) +[rank4]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/parallel/distributed.py", line 1454, in _run_ddp_forward +[rank4]: return self.module(*inputs, **kwargs) # type: ignore[index] +[rank4]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1553, in _wrapped_call_impl +[rank4]: return self._call_impl(*args, **kwargs) +[rank4]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1562, in _call_impl +[rank4]: return forward_call(*args, **kwargs) +[rank4]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/strategy.py", line 626, in wrapped_forward +[rank4]: out = method(*_args, **_kwargs) +[rank4]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/algorithms/worldmem/df_video_mamba3stage.py", line 1073, in training_step +[rank4]: self.log("training/curriculum_phase", float(phase_idx)) +[rank4]: TypeError: float() argument must be a string or a real number, not 'NoneType' +Error executing job with overrides: ['+name=train_stage_b_mamba', 'algorithm=df_video_mamba3stage', 'experiment.num_nodes=1', 'dataset.save_dir=/proj/cvl/users/x_fahkh2/WorldMem_Repro/datasets/minecraft', 'dataset.n_frames=200', '+dataset.n_frames_valid=200', '+dataset.angle_range=110', '+dataset.pos_range=8', '+dataset.wo_updown=false', '+dataset.customized_validation=true', '+dataset.add_timestamp_embedding=true', '+dataset.use_explicit_memory_frames=false', 'algorithm.training_stage=stage_b_diffusion_frozen_memory', 'algorithm.use_mamba_memory_pipeline=true', 'algorithm.use_oracle_pose_eval=false', 'algorithm.enable_memory_noise_curriculum=false', '+algorithm.require_pose_prediction=false', '+algorithm.use_memory_attention=false', '+algorithm.relative_embedding=false', '+algorithm.memory_retrieval_topk=32', 'algorithm.diff_window_size=8', 'algorithm.memory_condition_length=0', 'algorithm.context_frames=100', '+algorithm.n_tokens=8', 'experiment.training.batch_size=8', 'experiment.training.checkpointing.every_n_train_steps=2500', 'experiment.training.max_steps=175000', 'experiment.validation.val_every_n_step=2500', 'resume=stage_b_offline', '+output_dir=/proj/cvl/users/x_fahkh2/WorldMem_Repro/checkpoints/bimamba_stage_b/'] +[rank1]: Traceback (most recent call last): +[rank1]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/runpy.py", line 196, in _run_module_as_main +[rank1]: return _run_code(code, main_globals, None, +[rank1]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/runpy.py", line 86, in _run_code +[rank1]: exec(code, run_globals) +[rank1]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/main.py", line 202, in +[rank1]: run() # pylint: disable=no-value-for-parameter +[rank1]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/main.py", line 94, in decorated_main +[rank1]: _run_hydra( +[rank1]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/utils.py", line 394, in _run_hydra +[rank1]: _run_app( +[rank1]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/utils.py", line 457, in _run_app +[rank1]: run_and_report( +[rank1]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/utils.py", line 223, in run_and_report +[rank1]: raise ex +[rank1]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/utils.py", line 220, in run_and_report +[rank1]: return func() +[rank1]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/utils.py", line 458, in +[rank1]: lambda: hydra.run( +[rank1]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/hydra.py", line 132, in run +[rank1]: _ = ret.return_value +[rank1]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/core/utils.py", line 260, in return_value +[rank1]: raise self._return_value +[rank1]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/core/utils.py", line 186, in run_job +[rank1]: ret.return_value = task_function(task_cfg) +[rank1]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/main.py", line 198, in run +[rank1]: run_local(cfg) +[rank1]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/main.py", line 122, in run_local +[rank1]: experiment.exec_task(task) +[rank1]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/experiments/exp_base.py", line 172, in exec_task +[rank1]: getattr(self, task)() +[rank1]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/experiments/exp_base.py", line 371, in training +[rank1]: trainer.fit( +[rank1]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/trainer.py", line 544, in fit +[rank1]: call._call_and_handle_interrupt( +[rank1]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/call.py", line 43, in _call_and_handle_interrupt +[rank1]: return trainer.strategy.launcher.launch(trainer_fn, *args, trainer=trainer, **kwargs) +[rank1]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/launchers/subprocess_script.py", line 102, in launch +[rank1]: return function(*args, **kwargs) +[rank1]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/trainer.py", line 580, in _fit_impl +[rank1]: self._run(model, ckpt_path=ckpt_path) +[rank1]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/trainer.py", line 989, in _run +[rank1]: results = self._run_stage() +[rank1]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/trainer.py", line 1035, in _run_stage +[rank1]: self.fit_loop.run() +[rank1]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/fit_loop.py", line 202, in run +[rank1]: self.advance() +[rank1]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/fit_loop.py", line 359, in advance +[rank1]: self.epoch_loop.run(self._data_fetcher) +[rank1]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/training_epoch_loop.py", line 136, in run +[rank1]: self.advance(data_fetcher) +[rank1]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/training_epoch_loop.py", line 240, in advance +[rank1]: batch_output = self.automatic_optimization.run(trainer.optimizers[0], batch_idx, kwargs) +[rank1]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/optimization/automatic.py", line 187, in run +[rank1]: self._optimizer_step(batch_idx, closure) +[rank1]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/optimization/automatic.py", line 265, in _optimizer_step +[rank1]: call._call_lightning_module_hook( +[rank1]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/call.py", line 157, in _call_lightning_module_hook +[rank1]: output = fn(*args, **kwargs) +[rank1]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/algorithms/worldmem/df_base.py", line 65, in optimizer_step +[rank1]: optimizer.step(closure=optimizer_closure) +[rank1]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/core/optimizer.py", line 151, in step +[rank1]: step_output = self._strategy.optimizer_step(self._optimizer, closure, **kwargs) +[rank1]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/ddp.py", line 265, in optimizer_step +[rank1]: optimizer_output = super().optimizer_step(optimizer, closure, model, **kwargs) +[rank1]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/strategy.py", line 230, in optimizer_step +[rank1]: return self.precision_plugin.optimizer_step(optimizer, model=model, closure=closure, **kwargs) +[rank1]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/plugins/precision/amp.py", line 77, in optimizer_step +[rank1]: closure_result = closure() +[rank1]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/optimization/automatic.py", line 140, in __call__ +[rank1]: self._result = self.closure(*args, **kwargs) +[rank1]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 116, in decorate_context +[rank1]: return func(*args, **kwargs) +[rank1]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/optimization/automatic.py", line 126, in closure +[rank1]: step_output = self._step_fn() +[rank1]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/optimization/automatic.py", line 315, in _training_step +[rank1]: training_step_output = call._call_strategy_hook(trainer, "training_step", *kwargs.values()) +[rank1]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/call.py", line 309, in _call_strategy_hook +[rank1]: output = fn(*args, **kwargs) +[rank1]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/strategy.py", line 381, in training_step +[rank1]: return self._forward_redirection(self.model, self.lightning_module, "training_step", *args, **kwargs) +[rank1]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/strategy.py", line 633, in __call__ +[rank1]: wrapper_output = wrapper_module(*args, **kwargs) +[rank1]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1553, in _wrapped_call_impl +[rank1]: return self._call_impl(*args, **kwargs) +[rank1]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1562, in _call_impl +[rank1]: return forward_call(*args, **kwargs) +[rank1]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/parallel/distributed.py", line 1636, in forward +[rank1]: else self._run_ddp_forward(*inputs, **kwargs) +[rank1]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/parallel/distributed.py", line 1454, in _run_ddp_forward +[rank1]: return self.module(*inputs, **kwargs) # type: ignore[index] +[rank1]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1553, in _wrapped_call_impl +[rank1]: return self._call_impl(*args, **kwargs) +[rank1]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1562, in _call_impl +[rank1]: return forward_call(*args, **kwargs) +[rank1]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/strategy.py", line 626, in wrapped_forward +[rank1]: out = method(*_args, **_kwargs) +[rank1]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/algorithms/worldmem/df_video_mamba3stage.py", line 1073, in training_step +[rank1]: self.log("training/curriculum_phase", float(phase_idx)) +[rank1]: TypeError: float() argument must be a string or a real number, not 'NoneType' +Traceback (most recent call last): + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 300, in _run_finalizers + finalizer() + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 224, in __call__ + res = self._callback(*self._args, **self._kwargs) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/multiprocessing/util.py", line 133, in _remove_temp_dir + rmtree(tempdir) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 725, in rmtree + _rmtree_safe_fd(fd, path, onerror) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 681, in _rmtree_safe_fd + onerror(os.unlink, fullname, sys.exc_info()) + File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/shutil.py", line 679, in _rmtree_safe_fd + os.unlink(entry.name, dir_fd=topfd) +OSError: [Errno 16] Device or resource busy: '.nfsa5f3c5809fcbd7d300000314' +wandb: - 0.000 MB of 0.000 MB uploaded wandb: You can sync this run to the cloud by running: +wandb: wandb sync /proj/cvl/users/x_fahkh2/WorldMem_Repro/checkpoints/bimamba_stage_b/wandb/offline-run-20260311_191349-stage_b_offline +wandb: Find logs at: ./checkpoints/bimamba_stage_b/wandb/offline-run-20260311_191349-stage_b_offline/logs +wandb: WARNING The new W&B backend becomes opt-out in version 0.18.0; try it out with `wandb.require("core")`! See https://wandb.me/wandb-core for more information. +srun: error: node109: task 3: Exited with exit code 1 +srun: Terminating StepId=7382.2 +[2026-03-11T19:14:28.754] error: *** STEP 7382.2 ON node109 CANCELLED AT 2026-03-11T19:14:28 DUE TO TASK FAILURE *** +INFO: [rank: 2] Received SIGTERM: 15 +[2026-03-11 19:14:28,755][lightning.pytorch.trainer.connectors.signal_connector][INFO] - [rank: 2] Received SIGTERM: 15 +INFO: [rank: 5] Received SIGTERM: 15 +INFO: [rank: 6] Received SIGTERM: 15 +[2026-03-11 19:14:28,755][lightning.pytorch.trainer.connectors.signal_connector][INFO] - [rank: 5] Received SIGTERM: 15 +[2026-03-11 19:14:28,755][lightning.pytorch.trainer.connectors.signal_connector][INFO] - [rank: 6] Received SIGTERM: 15 +INFO: Bypassing SIGTERM: 15 +[2026-03-11 19:14:28,756][lightning.pytorch.trainer.connectors.signal_connector][INFO] - Bypassing SIGTERM: 15 +INFO: Bypassing SIGTERM: 15 +[2026-03-11 19:14:28,757][lightning.pytorch.trainer.connectors.signal_connector][INFO] - Bypassing SIGTERM: 15 +INFO: Bypassing SIGTERM: 15 +[2026-03-11 19:14:28,757][lightning.pytorch.trainer.connectors.signal_connector][INFO] - Bypassing SIGTERM: 15 +Error executing job with overrides: ['+name=train_stage_b_mamba', 'algorithm=df_video_mamba3stage', 'experiment.num_nodes=1', 'dataset.save_dir=/proj/cvl/users/x_fahkh2/WorldMem_Repro/datasets/minecraft', 'dataset.n_frames=200', '+dataset.n_frames_valid=200', '+dataset.angle_range=110', '+dataset.pos_range=8', '+dataset.wo_updown=false', '+dataset.customized_validation=true', '+dataset.add_timestamp_embedding=true', '+dataset.use_explicit_memory_frames=false', 'algorithm.training_stage=stage_b_diffusion_frozen_memory', 'algorithm.use_mamba_memory_pipeline=true', 'algorithm.use_oracle_pose_eval=false', 'algorithm.enable_memory_noise_curriculum=false', '+algorithm.require_pose_prediction=false', '+algorithm.use_memory_attention=false', '+algorithm.relative_embedding=false', '+algorithm.memory_retrieval_topk=32', 'algorithm.diff_window_size=8', 'algorithm.memory_condition_length=0', 'algorithm.context_frames=100', '+algorithm.n_tokens=8', 'experiment.training.batch_size=8', 'experiment.training.checkpointing.every_n_train_steps=2500', 'experiment.training.max_steps=175000', 'experiment.validation.val_every_n_step=2500', 'resume=stage_b_offline', '+output_dir=/proj/cvl/users/x_fahkh2/WorldMem_Repro/checkpoints/bimamba_stage_b/'] +Error executing job with overrides: ['+name=train_stage_b_mamba', 'algorithm=df_video_mamba3stage', 'experiment.num_nodes=1', 'dataset.save_dir=/proj/cvl/users/x_fahkh2/WorldMem_Repro/datasets/minecraft', 'dataset.n_frames=200', '+dataset.n_frames_valid=200', '+dataset.angle_range=110', '+dataset.pos_range=8', '+dataset.wo_updown=false', '+dataset.customized_validation=true', '+dataset.add_timestamp_embedding=true', '+dataset.use_explicit_memory_frames=false', 'algorithm.training_stage=stage_b_diffusion_frozen_memory', 'algorithm.use_mamba_memory_pipeline=true', 'algorithm.use_oracle_pose_eval=false', 'algorithm.enable_memory_noise_curriculum=false', '+algorithm.require_pose_prediction=false', '+algorithm.use_memory_attention=false', '+algorithm.relative_embedding=false', '+algorithm.memory_retrieval_topk=32', 'algorithm.diff_window_size=8', 'algorithm.memory_condition_length=0', 'algorithm.context_frames=100', '+algorithm.n_tokens=8', 'experiment.training.batch_size=8', 'experiment.training.checkpointing.every_n_train_steps=2500', 'experiment.training.max_steps=175000', 'experiment.validation.val_every_n_step=2500', 'resume=stage_b_offline', '+output_dir=/proj/cvl/users/x_fahkh2/WorldMem_Repro/checkpoints/bimamba_stage_b/'] +[rank6]: Traceback (most recent call last): +[rank6]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/runpy.py", line 196, in _run_module_as_main +[rank6]: return _run_code(code, main_globals, None, +[rank6]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/runpy.py", line 86, in _run_code +[rank6]: exec(code, run_globals) +[rank6]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/main.py", line 202, in +[rank6]: run() # pylint: disable=no-value-for-parameter +[rank6]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/main.py", line 94, in decorated_main +[rank6]: _run_hydra( +[rank6]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/utils.py", line 394, in _run_hydra +[rank6]: _run_app( +[rank6]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/utils.py", line 457, in _run_app +[rank6]: run_and_report( +[rank6]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/utils.py", line 223, in run_and_report +[rank6]: raise ex +[rank6]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/utils.py", line 220, in run_and_report +[rank6]: return func() +[rank6]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/utils.py", line 458, in +[rank6]: lambda: hydra.run( +[rank6]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/hydra.py", line 132, in run +[rank6]: _ = ret.return_value +[rank6]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/core/utils.py", line 260, in return_value +[rank6]: raise self._return_value +[rank6]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/core/utils.py", line 186, in run_job +[rank6]: ret.return_value = task_function(task_cfg) +[rank6]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/main.py", line 198, in run +[rank6]: run_local(cfg) +[rank6]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/main.py", line 122, in run_local +[rank6]: experiment.exec_task(task) +[rank6]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/experiments/exp_base.py", line 172, in exec_task +[rank6]: getattr(self, task)() +[rank6]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/experiments/exp_base.py", line 371, in training +[rank6]: trainer.fit( +[rank6]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/trainer.py", line 544, in fit +[rank6]: call._call_and_handle_interrupt( +[rank6]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/call.py", line 43, in _call_and_handle_interrupt +[rank6]: return trainer.strategy.launcher.launch(trainer_fn, *args, trainer=trainer, **kwargs) +[rank6]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/launchers/subprocess_script.py", line 102, in launch +[rank6]: return function(*args, **kwargs) +[rank6]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/trainer.py", line 580, in _fit_impl +[rank6]: self._run(model, ckpt_path=ckpt_path) +[rank6]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/trainer.py", line 989, in _run +[rank6]: results = self._run_stage() +[rank6]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/trainer.py", line 1035, in _run_stage +[rank6]: self.fit_loop.run() +[rank6]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/fit_loop.py", line 202, in run +[rank6]: self.advance() +[rank6]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/fit_loop.py", line 359, in advance +[rank6]: self.epoch_loop.run(self._data_fetcher) +[rank6]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/training_epoch_loop.py", line 136, in run +[rank6]: self.advance(data_fetcher) +[rank6]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/training_epoch_loop.py", line 240, in advance +[rank6]: batch_output = self.automatic_optimization.run(trainer.optimizers[0], batch_idx, kwargs) +[rank6]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/optimization/automatic.py", line 187, in run +[rank6]: self._optimizer_step(batch_idx, closure) +[rank6]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/optimization/automatic.py", line 265, in _optimizer_step +[rank6]: call._call_lightning_module_hook( +[rank6]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/call.py", line 157, in _call_lightning_module_hook +[rank6]: output = fn(*args, **kwargs) +[rank6]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/algorithms/worldmem/df_base.py", line 65, in optimizer_step +[rank6]: optimizer.step(closure=optimizer_closure) +[rank6]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/core/optimizer.py", line 151, in step +[rank6]: step_output = self._strategy.optimizer_step(self._optimizer, closure, **kwargs) +[rank6]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/ddp.py", line 265, in optimizer_step +[rank6]: optimizer_output = super().optimizer_step(optimizer, closure, model, **kwargs) +[rank6]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/strategy.py", line 230, in optimizer_step +[rank6]: return self.precision_plugin.optimizer_step(optimizer, model=model, closure=closure, **kwargs) +[rank6]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/plugins/precision/amp.py", line 77, in optimizer_step +[rank6]: closure_result = closure() +[rank6]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/optimization/automatic.py", line 140, in __call__ +[rank6]: self._result = self.closure(*args, **kwargs) +[rank6]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 116, in decorate_context +[rank6]: return func(*args, **kwargs) +[rank6]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/optimization/automatic.py", line 126, in closure +[rank6]: step_output = self._step_fn() +[rank6]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/optimization/automatic.py", line 315, in _training_step +[rank6]: training_step_output = call._call_strategy_hook(trainer, "training_step", *kwargs.values()) +[rank6]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/call.py", line 309, in _call_strategy_hook +[rank6]: output = fn(*args, **kwargs) +[rank6]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/strategy.py", line 381, in training_step +[rank6]: return self._forward_redirection(self.model, self.lightning_module, "training_step", *args, **kwargs) +[rank6]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/strategy.py", line 633, in __call__ +[rank6]: wrapper_output = wrapper_module(*args, **kwargs) +[rank6]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1553, in _wrapped_call_impl +[rank6]: return self._call_impl(*args, **kwargs) +[rank6]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1562, in _call_impl +[rank6]: return forward_call(*args, **kwargs) +[rank6]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/parallel/distributed.py", line 1636, in forward +[rank6]: else self._run_ddp_forward(*inputs, **kwargs) +[rank6]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/parallel/distributed.py", line 1454, in _run_ddp_forward +[rank6]: return self.module(*inputs, **kwargs) # type: ignore[index] +[rank6]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1553, in _wrapped_call_impl +[rank6]: return self._call_impl(*args, **kwargs) +[rank6]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1562, in _call_impl +[rank6]: return forward_call(*args, **kwargs) +[rank6]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/strategy.py", line 626, in wrapped_forward +[rank6]: out = method(*_args, **_kwargs) +[rank6]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/algorithms/worldmem/df_video_mamba3stage.py", line 1073, in training_step +[rank6]: self.log("training/curriculum_phase", float(phase_idx)) +[rank6]: TypeError: float() argument must be a string or a real number, not 'NoneType' +[rank2]: Traceback (most recent call last): +[rank2]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/runpy.py", line 196, in _run_module_as_main +[rank2]: return _run_code(code, main_globals, None, +[rank2]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/runpy.py", line 86, in _run_code +[rank2]: exec(code, run_globals) +[rank2]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/main.py", line 202, in +[rank2]: run() # pylint: disable=no-value-for-parameter +[rank2]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/main.py", line 94, in decorated_main +[rank2]: _run_hydra( +[rank2]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/utils.py", line 394, in _run_hydra +[rank2]: _run_app( +[rank2]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/utils.py", line 457, in _run_app +[rank2]: run_and_report( +[rank2]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/utils.py", line 223, in run_and_report +[rank2]: raise ex +[rank2]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/utils.py", line 220, in run_and_report +[rank2]: return func() +[rank2]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/utils.py", line 458, in +[rank2]: lambda: hydra.run( +[rank2]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/hydra.py", line 132, in run +[rank2]: _ = ret.return_value +[rank2]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/core/utils.py", line 260, in return_value +[rank2]: raise self._return_value +[rank2]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/core/utils.py", line 186, in run_job +[rank2]: ret.return_value = task_function(task_cfg) +[rank2]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/main.py", line 198, in run +[rank2]: run_local(cfg) +[rank2]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/main.py", line 122, in run_local +[rank2]: experiment.exec_task(task) +[rank2]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/experiments/exp_base.py", line 172, in exec_task +[rank2]: getattr(self, task)() +[rank2]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/experiments/exp_base.py", line 371, in training +[rank2]: trainer.fit( +[rank2]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/trainer.py", line 544, in fit +[rank2]: call._call_and_handle_interrupt( +[rank2]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/call.py", line 43, in _call_and_handle_interrupt +[rank2]: return trainer.strategy.launcher.launch(trainer_fn, *args, trainer=trainer, **kwargs) +[rank2]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/launchers/subprocess_script.py", line 102, in launch +[rank2]: return function(*args, **kwargs) +[rank2]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/trainer.py", line 580, in _fit_impl +[rank2]: self._run(model, ckpt_path=ckpt_path) +[rank2]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/trainer.py", line 989, in _run +[rank2]: results = self._run_stage() +[rank2]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/trainer.py", line 1035, in _run_stage +[rank2]: self.fit_loop.run() +[rank2]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/fit_loop.py", line 202, in run +[rank2]: self.advance() +[rank2]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/fit_loop.py", line 359, in advance +[rank2]: self.epoch_loop.run(self._data_fetcher) +[rank2]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/training_epoch_loop.py", line 136, in run +[rank2]: self.advance(data_fetcher) +[rank2]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/training_epoch_loop.py", line 240, in advance +[rank2]: batch_output = self.automatic_optimization.run(trainer.optimizers[0], batch_idx, kwargs) +[rank2]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/optimization/automatic.py", line 187, in run +[rank2]: self._optimizer_step(batch_idx, closure) +[rank2]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/optimization/automatic.py", line 265, in _optimizer_step +[rank2]: call._call_lightning_module_hook( +[rank2]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/call.py", line 157, in _call_lightning_module_hook +[rank2]: output = fn(*args, **kwargs) +[rank2]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/algorithms/worldmem/df_base.py", line 65, in optimizer_step +[rank2]: optimizer.step(closure=optimizer_closure) +[rank2]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/core/optimizer.py", line 151, in step +[rank2]: step_output = self._strategy.optimizer_step(self._optimizer, closure, **kwargs) +[rank2]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/ddp.py", line 265, in optimizer_step +[rank2]: optimizer_output = super().optimizer_step(optimizer, closure, model, **kwargs) +[rank2]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/strategy.py", line 230, in optimizer_step +[rank2]: return self.precision_plugin.optimizer_step(optimizer, model=model, closure=closure, **kwargs) +[rank2]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/plugins/precision/amp.py", line 77, in optimizer_step +[rank2]: closure_result = closure() +[rank2]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/optimization/automatic.py", line 140, in __call__ +[rank2]: self._result = self.closure(*args, **kwargs) +[rank2]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 116, in decorate_context +[rank2]: return func(*args, **kwargs) +[rank2]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/optimization/automatic.py", line 126, in closure +[rank2]: step_output = self._step_fn() +[rank2]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/optimization/automatic.py", line 315, in _training_step +[rank2]: training_step_output = call._call_strategy_hook(trainer, "training_step", *kwargs.values()) +[rank2]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/call.py", line 309, in _call_strategy_hook +[rank2]: output = fn(*args, **kwargs) +[rank2]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/strategy.py", line 381, in training_step +[rank2]: return self._forward_redirection(self.model, self.lightning_module, "training_step", *args, **kwargs) +[rank2]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/strategy.py", line 633, in __call__ +[rank2]: wrapper_output = wrapper_module(*args, **kwargs) +[rank2]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1553, in _wrapped_call_impl +[rank2]: return self._call_impl(*args, **kwargs) +[rank2]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1562, in _call_impl +[rank2]: return forward_call(*args, **kwargs) +[rank2]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/parallel/distributed.py", line 1636, in forward +[rank2]: else self._run_ddp_forward(*inputs, **kwargs) +[rank2]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/parallel/distributed.py", line 1454, in _run_ddp_forward +[rank2]: return self.module(*inputs, **kwargs) # type: ignore[index] +[rank2]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1553, in _wrapped_call_impl +[rank2]: return self._call_impl(*args, **kwargs) +[rank2]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1562, in _call_impl +[rank2]: return forward_call(*args, **kwargs) +[rank2]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/strategy.py", line 626, in wrapped_forward +[rank2]: out = method(*_args, **_kwargs) +[rank2]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/algorithms/worldmem/df_video_mamba3stage.py", line 1073, in training_step +[rank2]: self.log("training/curriculum_phase", float(phase_idx)) +[rank2]: TypeError: float() argument must be a string or a real number, not 'NoneType' +srun: error: node109: tasks 0-1,4,7: Terminated +Error executing job with overrides: ['+name=train_stage_b_mamba', 'algorithm=df_video_mamba3stage', 'experiment.num_nodes=1', 'dataset.save_dir=/proj/cvl/users/x_fahkh2/WorldMem_Repro/datasets/minecraft', 'dataset.n_frames=200', '+dataset.n_frames_valid=200', '+dataset.angle_range=110', '+dataset.pos_range=8', '+dataset.wo_updown=false', '+dataset.customized_validation=true', '+dataset.add_timestamp_embedding=true', '+dataset.use_explicit_memory_frames=false', 'algorithm.training_stage=stage_b_diffusion_frozen_memory', 'algorithm.use_mamba_memory_pipeline=true', 'algorithm.use_oracle_pose_eval=false', 'algorithm.enable_memory_noise_curriculum=false', '+algorithm.require_pose_prediction=false', '+algorithm.use_memory_attention=false', '+algorithm.relative_embedding=false', '+algorithm.memory_retrieval_topk=32', 'algorithm.diff_window_size=8', 'algorithm.memory_condition_length=0', 'algorithm.context_frames=100', '+algorithm.n_tokens=8', 'experiment.training.batch_size=8', 'experiment.training.checkpointing.every_n_train_steps=2500', 'experiment.training.max_steps=175000', 'experiment.validation.val_every_n_step=2500', 'resume=stage_b_offline', '+output_dir=/proj/cvl/users/x_fahkh2/WorldMem_Repro/checkpoints/bimamba_stage_b/'] +[rank5]: Traceback (most recent call last): +[rank5]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/runpy.py", line 196, in _run_module_as_main +[rank5]: return _run_code(code, main_globals, None, +[rank5]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/runpy.py", line 86, in _run_code +[rank5]: exec(code, run_globals) +[rank5]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/main.py", line 202, in +[rank5]: run() # pylint: disable=no-value-for-parameter +[rank5]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/main.py", line 94, in decorated_main +[rank5]: _run_hydra( +[rank5]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/utils.py", line 394, in _run_hydra +[rank5]: _run_app( +[rank5]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/utils.py", line 457, in _run_app +[rank5]: run_and_report( +[rank5]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/utils.py", line 223, in run_and_report +[rank5]: raise ex +[rank5]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/utils.py", line 220, in run_and_report +[rank5]: return func() +[rank5]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/utils.py", line 458, in +[rank5]: lambda: hydra.run( +[rank5]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/_internal/hydra.py", line 132, in run +[rank5]: _ = ret.return_value +[rank5]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/core/utils.py", line 260, in return_value +[rank5]: raise self._return_value +[rank5]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/hydra/core/utils.py", line 186, in run_job +[rank5]: ret.return_value = task_function(task_cfg) +[rank5]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/main.py", line 198, in run +[rank5]: run_local(cfg) +[rank5]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/main.py", line 122, in run_local +[rank5]: experiment.exec_task(task) +[rank5]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/experiments/exp_base.py", line 172, in exec_task +[rank5]: getattr(self, task)() +[rank5]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/experiments/exp_base.py", line 371, in training +[rank5]: trainer.fit( +[rank5]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/trainer.py", line 544, in fit +[rank5]: call._call_and_handle_interrupt( +[rank5]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/call.py", line 43, in _call_and_handle_interrupt +[rank5]: return trainer.strategy.launcher.launch(trainer_fn, *args, trainer=trainer, **kwargs) +[rank5]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/launchers/subprocess_script.py", line 102, in launch +[rank5]: return function(*args, **kwargs) +[rank5]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/trainer.py", line 580, in _fit_impl +[rank5]: self._run(model, ckpt_path=ckpt_path) +[rank5]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/trainer.py", line 989, in _run +[rank5]: results = self._run_stage() +[rank5]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/trainer.py", line 1035, in _run_stage +[rank5]: self.fit_loop.run() +[rank5]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/fit_loop.py", line 202, in run +[rank5]: self.advance() +[rank5]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/fit_loop.py", line 359, in advance +[rank5]: self.epoch_loop.run(self._data_fetcher) +[rank5]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/training_epoch_loop.py", line 136, in run +[rank5]: self.advance(data_fetcher) +[rank5]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/training_epoch_loop.py", line 240, in advance +[rank5]: batch_output = self.automatic_optimization.run(trainer.optimizers[0], batch_idx, kwargs) +[rank5]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/optimization/automatic.py", line 187, in run +[rank5]: self._optimizer_step(batch_idx, closure) +[rank5]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/optimization/automatic.py", line 265, in _optimizer_step +[rank5]: call._call_lightning_module_hook( +[rank5]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/call.py", line 157, in _call_lightning_module_hook +[rank5]: output = fn(*args, **kwargs) +[rank5]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/algorithms/worldmem/df_base.py", line 65, in optimizer_step +[rank5]: optimizer.step(closure=optimizer_closure) +[rank5]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/core/optimizer.py", line 151, in step +[rank5]: step_output = self._strategy.optimizer_step(self._optimizer, closure, **kwargs) +[rank5]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/ddp.py", line 265, in optimizer_step +[rank5]: optimizer_output = super().optimizer_step(optimizer, closure, model, **kwargs) +[rank5]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/strategy.py", line 230, in optimizer_step +[rank5]: return self.precision_plugin.optimizer_step(optimizer, model=model, closure=closure, **kwargs) +[rank5]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/plugins/precision/amp.py", line 77, in optimizer_step +[rank5]: closure_result = closure() +[rank5]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/optimization/automatic.py", line 140, in __call__ +[rank5]: self._result = self.closure(*args, **kwargs) +[rank5]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 116, in decorate_context +[rank5]: return func(*args, **kwargs) +[rank5]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/optimization/automatic.py", line 126, in closure +[rank5]: step_output = self._step_fn() +[rank5]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/loops/optimization/automatic.py", line 315, in _training_step +[rank5]: training_step_output = call._call_strategy_hook(trainer, "training_step", *kwargs.values()) +[rank5]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/trainer/call.py", line 309, in _call_strategy_hook +[rank5]: output = fn(*args, **kwargs) +[rank5]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/strategy.py", line 381, in training_step +[rank5]: return self._forward_redirection(self.model, self.lightning_module, "training_step", *args, **kwargs) +[rank5]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/strategy.py", line 633, in __call__ +[rank5]: wrapper_output = wrapper_module(*args, **kwargs) +[rank5]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1553, in _wrapped_call_impl +[rank5]: return self._call_impl(*args, **kwargs) +[rank5]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1562, in _call_impl +[rank5]: return forward_call(*args, **kwargs) +[rank5]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/parallel/distributed.py", line 1636, in forward +[rank5]: else self._run_ddp_forward(*inputs, **kwargs) +[rank5]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/parallel/distributed.py", line 1454, in _run_ddp_forward +[rank5]: return self.module(*inputs, **kwargs) # type: ignore[index] +[rank5]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1553, in _wrapped_call_impl +[rank5]: return self._call_impl(*args, **kwargs) +[rank5]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1562, in _call_impl +[rank5]: return forward_call(*args, **kwargs) +[rank5]: File "/proj/cvl/users/x_fahkh2/envs/worldmem/lib/python3.10/site-packages/lightning/pytorch/strategies/strategy.py", line 626, in wrapped_forward +[rank5]: out = method(*_args, **_kwargs) +[rank5]: File "/proj/cvl/users/x_fahkh2/WorldMem_Repro/algorithms/worldmem/df_video_mamba3stage.py", line 1073, in training_step +[rank5]: self.log("training/curriculum_phase", float(phase_idx)) +[rank5]: TypeError: float() argument must be a string or a real number, not 'NoneType' + Training: | | 0/? [00:00