{ "data": [ [ [ 1, "{\"task_id\": \"1c0e9c2e-1719-11ed-8c29-312016f08e28\"}", 0, 5.555555555555555 ], [ 2147483647.0, 5.45588493347168, { "__enum__": "StatusType.CRASHED" }, 1659963219.4038615, 1659963225.3871603, { "traceback": "Traceback (most recent call last):\n File \"/home/robby/miniconda3/envs/auto-pytorch/lib/python3.8/site-packages/autoPyTorch/evaluation/tae.py\", line 61, in fit_predict_try_except_decorator\n ta(queue=queue, **kwargs)\n File \"/home/robby/miniconda3/envs/auto-pytorch/lib/python3.8/site-packages/autoPyTorch/evaluation/time_series_forecasting_train_evaluator.py\", line 558, in forecasting_eval_train_function\n evaluator.fit_predict_and_loss()\n File \"/home/robby/miniconda3/envs/auto-pytorch/lib/python3.8/site-packages/autoPyTorch/evaluation/time_series_forecasting_train_evaluator.py\", line 176, in fit_predict_and_loss\n y_train_pred, y_opt_pred, y_valid_pred, y_test_pred = self._fit_and_predict(pipeline, split_id,\n File \"/home/robby/miniconda3/envs/auto-pytorch/lib/python3.8/site-packages/autoPyTorch/evaluation/train_evaluator.py\", line 364, in _fit_and_predict\n fit_and_suppress_warnings(self.logger, pipeline, X, y)\n File \"/home/robby/miniconda3/envs/auto-pytorch/lib/python3.8/site-packages/autoPyTorch/evaluation/abstract_evaluator.py\", line 338, in fit_and_suppress_warnings\n pipeline.fit(X, y)\n File \"/home/robby/miniconda3/envs/auto-pytorch/lib/python3.8/site-packages/autoPyTorch/pipeline/base_pipeline.py\", line 158, in fit\n self.fit_estimator(X, y, **fit_params)\n File \"/home/robby/miniconda3/envs/auto-pytorch/lib/python3.8/site-packages/autoPyTorch/pipeline/base_pipeline.py\", line 177, in fit_estimator\n self._final_estimator.fit(X, y, **fit_params)\n File \"/home/robby/miniconda3/envs/auto-pytorch/lib/python3.8/site-packages/autoPyTorch/pipeline/components/training/trainer/__init__.py\", line 211, in fit\n self._fit(\n File \"/home/robby/miniconda3/envs/auto-pytorch/lib/python3.8/site-packages/autoPyTorch/pipeline/components/training/trainer/__init__.py\", line 310, in _fit\n train_loss, train_metrics = self.choice.train_epoch(\n File \"/home/robby/miniconda3/envs/auto-pytorch/lib/python3.8/site-packages/autoPyTorch/pipeline/components/training/trainer/forecasting_trainer/forecasting_base_trainer.py\", line 106, in train_epoch\n loss, outputs = self.train_step(data, targets)\n File \"/home/robby/miniconda3/envs/auto-pytorch/lib/python3.8/site-packages/autoPyTorch/pipeline/components/training/trainer/forecasting_trainer/forecasting_base_trainer.py\", line 206, in train_step\n outputs = self.model(past_targets=past_target,\n File \"/home/robby/miniconda3/envs/auto-pytorch/lib/python3.8/site-packages/torch/nn/modules/module.py\", line 1130, in _call_impl\n return forward_call(*input, **kwargs)\n File \"/home/robby/miniconda3/envs/auto-pytorch/lib/python3.8/site-packages/autoPyTorch/pipeline/components/setup/network/forecasting_architecture.py\", line 602, in forward\n output = self.head(decoder_output)\n File \"/home/robby/miniconda3/envs/auto-pytorch/lib/python3.8/site-packages/torch/nn/modules/module.py\", line 1130, in _call_impl\n return forward_call(*input, **kwargs)\n File \"/home/robby/miniconda3/envs/auto-pytorch/lib/python3.8/site-packages/autoPyTorch/pipeline/components/setup/network_head/forecasting_network_head/distribution.py\", line 100, in forward\n return self.dist_cls(*self.domain_map(*params_unbounded))\n File \"/home/robby/miniconda3/envs/auto-pytorch/lib/python3.8/site-packages/torch/distributions/studentT.py\", line 50, in __init__\n self._chi2 = Chi2(self.df)\n File \"/home/robby/miniconda3/envs/auto-pytorch/lib/python3.8/site-packages/torch/distributions/chi2.py\", line 22, in __init__\n super(Chi2, self).__init__(0.5 * df, 0.5, validate_args=validate_args)\n File \"/home/robby/miniconda3/envs/auto-pytorch/lib/python3.8/site-packages/torch/distributions/gamma.py\", line 52, in __init__\n super(Gamma, self).__init__(batch_shape, validate_args=validate_args)\n File \"/home/robby/miniconda3/envs/auto-pytorch/lib/python3.8/site-packages/torch/distributions/distribution.py\", line 55, in __init__\n raise ValueError(\nValueError: Expected parameter df (Tensor of shape (32, 3, 1)) of distribution Chi2() to satisfy the constraint GreaterThan(lower_bound=0.0), but found invalid values:\ntensor([[[nan],\n [nan],\n [nan]],\n\n [[nan],\n [nan],\n [nan]],\n\n [[nan],\n [nan],\n [nan]],\n\n [[nan],\n [nan],\n [nan]],\n\n [[nan],\n [nan],\n [nan]],\n\n [[nan],\n [nan],\n [nan]],\n\n [[nan],\n [nan],\n [nan]],\n\n [[nan],\n [nan],\n [nan]],\n\n [[nan],\n [nan],\n [nan]],\n\n [[nan],\n [nan],\n [nan]],\n\n [[nan],\n [nan],\n [nan]],\n\n [[nan],\n [nan],\n [nan]],\n\n [[nan],\n [nan],\n [nan]],\n\n [[nan],\n [nan],\n [nan]],\n\n [[nan],\n [nan],\n [nan]],\n\n [[nan],\n [nan],\n [nan]],\n\n [[nan],\n [nan],\n [nan]],\n\n [[nan],\n [nan],\n [nan]],\n\n [[nan],\n [nan],\n [nan]],\n\n [[nan],\n [nan],\n [nan]],\n\n [[nan],\n [nan],\n [nan]],\n\n [[nan],\n [nan],\n [nan]],\n\n [[nan],\n [nan],\n [nan]],\n\n [[nan],\n [nan],\n [nan]],\n\n [[nan],\n [nan],\n [nan]],\n\n [[nan],\n [nan],\n [nan]],\n\n [[nan],\n [nan],\n [nan]],\n\n [[nan],\n [nan],\n [nan]],\n\n [[nan],\n [nan],\n [nan]],\n\n [[nan],\n [nan],\n [nan]],\n\n [[nan],\n [nan],\n [nan]],\n\n [[nan],\n [nan],\n [nan]]], device='cuda:0', grad_fn=)\n", "error": "ValueError(\"Expected parameter df (Tensor of shape (32, 3, 1)) of distribution Chi2() to satisfy the constraint GreaterThan(lower_bound=0.0), but found invalid values:\\ntensor([[[nan],\\n [nan],\\n [nan]],\\n\\n [[nan],\\n [nan],\\n [nan]],\\n\\n [[nan],\\n [nan],\\n [nan]],\\n\\n [[nan],\\n [nan],\\n [nan]],\\n\\n [[nan],\\n [nan],\\n [nan]],\\n\\n [[nan],\\n [nan],\\n [nan]],\\n\\n [[nan],\\n [nan],\\n [nan]],\\n\\n [[nan],\\n [nan],\\n [nan]],\\n\\n [[nan],\\n [nan],\\n [nan]],\\n\\n [[nan],\\n [nan],\\n [nan]],\\n\\n [[nan],\\n [nan],\\n [nan]],\\n\\n [[nan],\\n [nan],\\n [nan]],\\n\\n [[nan],\\n [nan],\\n [nan]],\\n\\n [[nan],\\n [nan],\\n [nan]],\\n\\n [[nan],\\n [nan],\\n [nan]],\\n\\n [[nan],\\n [nan],\\n [nan]],\\n\\n [[nan],\\n [nan],\\n [nan]],\\n\\n [[nan],\\n [nan],\\n [nan]],\\n\\n [[nan],\\n [nan],\\n [nan]],\\n\\n [[nan],\\n [nan],\\n [nan]],\\n\\n [[nan],\\n [nan],\\n [nan]],\\n\\n [[nan],\\n [nan],\\n [nan]],\\n\\n [[nan],\\n [nan],\\n [nan]],\\n\\n [[nan],\\n [nan],\\n [nan]],\\n\\n [[nan],\\n [nan],\\n [nan]],\\n\\n [[nan],\\n [nan],\\n [nan]],\\n\\n [[nan],\\n [nan],\\n [nan]],\\n\\n [[nan],\\n [nan],\\n [nan]],\\n\\n [[nan],\\n [nan],\\n [nan]],\\n\\n [[nan],\\n [nan],\\n [nan]],\\n\\n [[nan],\\n [nan],\\n [nan]],\\n\\n [[nan],\\n [nan],\\n [nan]]], device='cuda:0', grad_fn=)\")", "configuration_origin": "Initial design" } ] ], [ [ 2, "{\"task_id\": \"1c0e9c2e-1719-11ed-8c29-312016f08e28\"}", 0, 5.555555555555555 ], [ 2147483647.0, 5.376392126083374, { "__enum__": "StatusType.CRASHED" }, 1659963227.1163032, 1659963233.1124558, { "traceback": "Traceback (most recent call last):\n File \"/home/robby/miniconda3/envs/auto-pytorch/lib/python3.8/site-packages/autoPyTorch/evaluation/tae.py\", line 61, in fit_predict_try_except_decorator\n ta(queue=queue, **kwargs)\n File \"/home/robby/miniconda3/envs/auto-pytorch/lib/python3.8/site-packages/autoPyTorch/evaluation/time_series_forecasting_train_evaluator.py\", line 558, in forecasting_eval_train_function\n evaluator.fit_predict_and_loss()\n File \"/home/robby/miniconda3/envs/auto-pytorch/lib/python3.8/site-packages/autoPyTorch/evaluation/time_series_forecasting_train_evaluator.py\", line 176, in fit_predict_and_loss\n y_train_pred, y_opt_pred, y_valid_pred, y_test_pred = self._fit_and_predict(pipeline, split_id,\n File \"/home/robby/miniconda3/envs/auto-pytorch/lib/python3.8/site-packages/autoPyTorch/evaluation/train_evaluator.py\", line 364, in _fit_and_predict\n fit_and_suppress_warnings(self.logger, pipeline, X, y)\n File \"/home/robby/miniconda3/envs/auto-pytorch/lib/python3.8/site-packages/autoPyTorch/evaluation/abstract_evaluator.py\", line 338, in fit_and_suppress_warnings\n pipeline.fit(X, y)\n File \"/home/robby/miniconda3/envs/auto-pytorch/lib/python3.8/site-packages/autoPyTorch/pipeline/base_pipeline.py\", line 158, in fit\n self.fit_estimator(X, y, **fit_params)\n File \"/home/robby/miniconda3/envs/auto-pytorch/lib/python3.8/site-packages/autoPyTorch/pipeline/base_pipeline.py\", line 177, in fit_estimator\n self._final_estimator.fit(X, y, **fit_params)\n File \"/home/robby/miniconda3/envs/auto-pytorch/lib/python3.8/site-packages/autoPyTorch/pipeline/components/training/trainer/__init__.py\", line 211, in fit\n self._fit(\n File \"/home/robby/miniconda3/envs/auto-pytorch/lib/python3.8/site-packages/autoPyTorch/pipeline/components/training/trainer/__init__.py\", line 310, in _fit\n train_loss, train_metrics = self.choice.train_epoch(\n File \"/home/robby/miniconda3/envs/auto-pytorch/lib/python3.8/site-packages/autoPyTorch/pipeline/components/training/trainer/forecasting_trainer/forecasting_base_trainer.py\", line 106, in train_epoch\n loss, outputs = self.train_step(data, targets)\n File \"/home/robby/miniconda3/envs/auto-pytorch/lib/python3.8/site-packages/autoPyTorch/pipeline/components/training/trainer/forecasting_trainer/forecasting_base_trainer.py\", line 206, in train_step\n outputs = self.model(past_targets=past_target,\n File \"/home/robby/miniconda3/envs/auto-pytorch/lib/python3.8/site-packages/torch/nn/modules/module.py\", line 1130, in _call_impl\n return forward_call(*input, **kwargs)\n File \"/home/robby/miniconda3/envs/auto-pytorch/lib/python3.8/site-packages/autoPyTorch/pipeline/components/setup/network/forecasting_architecture.py\", line 1063, in forward\n net_output = self.head(self.decoder(x_future=None, encoder_output=encoder2decoder))\n File \"/home/robby/miniconda3/envs/auto-pytorch/lib/python3.8/site-packages/torch/nn/modules/module.py\", line 1130, in _call_impl\n return forward_call(*input, **kwargs)\n File \"/home/robby/miniconda3/envs/auto-pytorch/lib/python3.8/site-packages/autoPyTorch/pipeline/components/setup/network_head/forecasting_network_head/distribution.py\", line 100, in forward\n return self.dist_cls(*self.domain_map(*params_unbounded))\n File \"/home/robby/miniconda3/envs/auto-pytorch/lib/python3.8/site-packages/torch/distributions/studentT.py\", line 50, in __init__\n self._chi2 = Chi2(self.df)\n File \"/home/robby/miniconda3/envs/auto-pytorch/lib/python3.8/site-packages/torch/distributions/chi2.py\", line 22, in __init__\n super(Chi2, self).__init__(0.5 * df, 0.5, validate_args=validate_args)\n File \"/home/robby/miniconda3/envs/auto-pytorch/lib/python3.8/site-packages/torch/distributions/gamma.py\", line 52, in __init__\n super(Gamma, self).__init__(batch_shape, validate_args=validate_args)\n File \"/home/robby/miniconda3/envs/auto-pytorch/lib/python3.8/site-packages/torch/distributions/distribution.py\", line 55, in __init__\n raise ValueError(\nValueError: Expected parameter df (Tensor of shape (32, 4, 1)) of distribution Chi2() to satisfy the constraint GreaterThan(lower_bound=0.0), but found invalid values:\ntensor([[[nan],\n [nan],\n [nan],\n [nan]],\n\n [[nan],\n [nan],\n [nan],\n [nan]],\n\n [[nan],\n [nan],\n [nan],\n [nan]],\n\n [[nan],\n [nan],\n [nan],\n [nan]],\n\n [[nan],\n [nan],\n [nan],\n [nan]],\n\n [[nan],\n [nan],\n [nan],\n [nan]],\n\n [[nan],\n [nan],\n [nan],\n [nan]],\n\n [[nan],\n [nan],\n [nan],\n [nan]],\n\n [[nan],\n [nan],\n [nan],\n [nan]],\n\n [[nan],\n [nan],\n [nan],\n [nan]],\n\n [[nan],\n [nan],\n [nan],\n [nan]],\n\n [[nan],\n [nan],\n [nan],\n [nan]],\n\n [[nan],\n [nan],\n [nan],\n [nan]],\n\n [[nan],\n [nan],\n [nan],\n [nan]],\n\n [[nan],\n [nan],\n [nan],\n [nan]],\n\n [[nan],\n [nan],\n [nan],\n [nan]],\n\n [[nan],\n [nan],\n [nan],\n [nan]],\n\n [[nan],\n [nan],\n [nan],\n [nan]],\n\n [[nan],\n [nan],\n [nan],\n [nan]],\n\n [[nan],\n [nan],\n [nan],\n [nan]],\n\n [[nan],\n [nan],\n [nan],\n [nan]],\n\n [[nan],\n [nan],\n [nan],\n [nan]],\n\n [[nan],\n [nan],\n [nan],\n [nan]],\n\n [[nan],\n [nan],\n [nan],\n [nan]],\n\n [[nan],\n [nan],\n [nan],\n [nan]],\n\n [[nan],\n [nan],\n [nan],\n [nan]],\n\n [[nan],\n [nan],\n [nan],\n [nan]],\n\n [[nan],\n [nan],\n [nan],\n [nan]],\n\n [[nan],\n [nan],\n [nan],\n [nan]],\n\n [[nan],\n [nan],\n [nan],\n [nan]],\n\n [[nan],\n [nan],\n [nan],\n [nan]],\n\n [[nan],\n [nan],\n [nan],\n [nan]]], device='cuda:0', grad_fn=)\n", "error": "ValueError(\"Expected parameter df (Tensor of shape (32, 4, 1)) of distribution Chi2() to satisfy the constraint GreaterThan(lower_bound=0.0), but found invalid values:\\ntensor([[[nan],\\n [nan],\\n [nan],\\n [nan]],\\n\\n [[nan],\\n [nan],\\n [nan],\\n [nan]],\\n\\n [[nan],\\n [nan],\\n [nan],\\n [nan]],\\n\\n [[nan],\\n [nan],\\n [nan],\\n [nan]],\\n\\n [[nan],\\n [nan],\\n [nan],\\n [nan]],\\n\\n [[nan],\\n [nan],\\n [nan],\\n [nan]],\\n\\n [[nan],\\n [nan],\\n [nan],\\n [nan]],\\n\\n [[nan],\\n [nan],\\n [nan],\\n [nan]],\\n\\n [[nan],\\n [nan],\\n [nan],\\n [nan]],\\n\\n [[nan],\\n [nan],\\n [nan],\\n [nan]],\\n\\n [[nan],\\n [nan],\\n [nan],\\n [nan]],\\n\\n [[nan],\\n [nan],\\n [nan],\\n [nan]],\\n\\n [[nan],\\n [nan],\\n [nan],\\n [nan]],\\n\\n [[nan],\\n [nan],\\n [nan],\\n [nan]],\\n\\n [[nan],\\n [nan],\\n [nan],\\n [nan]],\\n\\n [[nan],\\n [nan],\\n [nan],\\n [nan]],\\n\\n [[nan],\\n [nan],\\n [nan],\\n [nan]],\\n\\n [[nan],\\n [nan],\\n [nan],\\n [nan]],\\n\\n [[nan],\\n [nan],\\n [nan],\\n [nan]],\\n\\n [[nan],\\n [nan],\\n [nan],\\n [nan]],\\n\\n [[nan],\\n [nan],\\n [nan],\\n [nan]],\\n\\n [[nan],\\n [nan],\\n [nan],\\n [nan]],\\n\\n [[nan],\\n [nan],\\n [nan],\\n [nan]],\\n\\n [[nan],\\n [nan],\\n [nan],\\n [nan]],\\n\\n [[nan],\\n [nan],\\n [nan],\\n [nan]],\\n\\n [[nan],\\n [nan],\\n [nan],\\n [nan]],\\n\\n [[nan],\\n [nan],\\n [nan],\\n [nan]],\\n\\n [[nan],\\n [nan],\\n [nan],\\n [nan]],\\n\\n [[nan],\\n [nan],\\n [nan],\\n [nan]],\\n\\n [[nan],\\n [nan],\\n [nan],\\n [nan]],\\n\\n [[nan],\\n [nan],\\n [nan],\\n [nan]],\\n\\n [[nan],\\n [nan],\\n [nan],\\n [nan]]], device='cuda:0', grad_fn=)\")", "configuration_origin": "Initial design" } ] ], [ [ 3, "{\"task_id\": \"1c0e9c2e-1719-11ed-8c29-312016f08e28\"}", 0, 5.555555555555555 ], [ 2147483647.0, 5.148428916931152, { "__enum__": "StatusType.CRASHED" }, 1659963234.8051095, 1659963240.5553904, { "traceback": "Traceback (most recent call last):\n File \"/home/robby/miniconda3/envs/auto-pytorch/lib/python3.8/site-packages/autoPyTorch/evaluation/tae.py\", line 61, in fit_predict_try_except_decorator\n ta(queue=queue, **kwargs)\n File \"/home/robby/miniconda3/envs/auto-pytorch/lib/python3.8/site-packages/autoPyTorch/evaluation/time_series_forecasting_train_evaluator.py\", line 558, in forecasting_eval_train_function\n evaluator.fit_predict_and_loss()\n File \"/home/robby/miniconda3/envs/auto-pytorch/lib/python3.8/site-packages/autoPyTorch/evaluation/time_series_forecasting_train_evaluator.py\", line 176, in fit_predict_and_loss\n y_train_pred, y_opt_pred, y_valid_pred, y_test_pred = self._fit_and_predict(pipeline, split_id,\n File \"/home/robby/miniconda3/envs/auto-pytorch/lib/python3.8/site-packages/autoPyTorch/evaluation/train_evaluator.py\", line 364, in _fit_and_predict\n fit_and_suppress_warnings(self.logger, pipeline, X, y)\n File \"/home/robby/miniconda3/envs/auto-pytorch/lib/python3.8/site-packages/autoPyTorch/evaluation/abstract_evaluator.py\", line 338, in fit_and_suppress_warnings\n pipeline.fit(X, y)\n File \"/home/robby/miniconda3/envs/auto-pytorch/lib/python3.8/site-packages/autoPyTorch/pipeline/base_pipeline.py\", line 158, in fit\n self.fit_estimator(X, y, **fit_params)\n File \"/home/robby/miniconda3/envs/auto-pytorch/lib/python3.8/site-packages/autoPyTorch/pipeline/base_pipeline.py\", line 177, in fit_estimator\n self._final_estimator.fit(X, y, **fit_params)\n File \"/home/robby/miniconda3/envs/auto-pytorch/lib/python3.8/site-packages/autoPyTorch/pipeline/components/training/trainer/__init__.py\", line 211, in fit\n self._fit(\n File \"/home/robby/miniconda3/envs/auto-pytorch/lib/python3.8/site-packages/autoPyTorch/pipeline/components/training/trainer/__init__.py\", line 310, in _fit\n train_loss, train_metrics = self.choice.train_epoch(\n File \"/home/robby/miniconda3/envs/auto-pytorch/lib/python3.8/site-packages/autoPyTorch/pipeline/components/training/trainer/forecasting_trainer/forecasting_base_trainer.py\", line 106, in train_epoch\n loss, outputs = self.train_step(data, targets)\n File \"/home/robby/miniconda3/envs/auto-pytorch/lib/python3.8/site-packages/autoPyTorch/pipeline/components/training/trainer/forecasting_trainer/forecasting_base_trainer.py\", line 206, in train_step\n outputs = self.model(past_targets=past_target,\n File \"/home/robby/miniconda3/envs/auto-pytorch/lib/python3.8/site-packages/torch/nn/modules/module.py\", line 1130, in _call_impl\n return forward_call(*input, **kwargs)\n File \"/home/robby/miniconda3/envs/auto-pytorch/lib/python3.8/site-packages/autoPyTorch/pipeline/components/setup/network/forecasting_architecture.py\", line 602, in forward\n output = self.head(decoder_output)\n File \"/home/robby/miniconda3/envs/auto-pytorch/lib/python3.8/site-packages/torch/nn/modules/module.py\", line 1130, in _call_impl\n return forward_call(*input, **kwargs)\n File \"/home/robby/miniconda3/envs/auto-pytorch/lib/python3.8/site-packages/autoPyTorch/pipeline/components/setup/network_head/forecasting_network_head/distribution.py\", line 100, in forward\n return self.dist_cls(*self.domain_map(*params_unbounded))\n File \"/home/robby/miniconda3/envs/auto-pytorch/lib/python3.8/site-packages/torch/distributions/studentT.py\", line 50, in __init__\n self._chi2 = Chi2(self.df)\n File \"/home/robby/miniconda3/envs/auto-pytorch/lib/python3.8/site-packages/torch/distributions/chi2.py\", line 22, in __init__\n super(Chi2, self).__init__(0.5 * df, 0.5, validate_args=validate_args)\n File \"/home/robby/miniconda3/envs/auto-pytorch/lib/python3.8/site-packages/torch/distributions/gamma.py\", line 52, in __init__\n super(Gamma, self).__init__(batch_shape, validate_args=validate_args)\n File \"/home/robby/miniconda3/envs/auto-pytorch/lib/python3.8/site-packages/torch/distributions/distribution.py\", line 55, in __init__\n raise ValueError(\nValueError: Expected parameter df (Tensor of shape (32, 3, 1)) of distribution Chi2() to satisfy the constraint GreaterThan(lower_bound=0.0), but found invalid values:\ntensor([[[nan],\n [nan],\n [nan]],\n\n [[nan],\n [nan],\n [nan]],\n\n [[nan],\n [nan],\n [nan]],\n\n [[nan],\n [nan],\n [nan]],\n\n [[nan],\n [nan],\n [nan]],\n\n [[nan],\n [nan],\n [nan]],\n\n [[nan],\n [nan],\n [nan]],\n\n [[nan],\n [nan],\n [nan]],\n\n [[nan],\n [nan],\n [nan]],\n\n [[nan],\n [nan],\n [nan]],\n\n [[nan],\n [nan],\n [nan]],\n\n [[nan],\n [nan],\n [nan]],\n\n [[nan],\n [nan],\n [nan]],\n\n [[nan],\n [nan],\n [nan]],\n\n [[nan],\n [nan],\n [nan]],\n\n [[nan],\n [nan],\n [nan]],\n\n [[nan],\n [nan],\n [nan]],\n\n [[nan],\n [nan],\n [nan]],\n\n [[nan],\n [nan],\n [nan]],\n\n [[nan],\n [nan],\n [nan]],\n\n [[nan],\n [nan],\n [nan]],\n\n [[nan],\n [nan],\n [nan]],\n\n [[nan],\n [nan],\n [nan]],\n\n [[nan],\n [nan],\n [nan]],\n\n [[nan],\n [nan],\n [nan]],\n\n [[nan],\n [nan],\n [nan]],\n\n [[nan],\n [nan],\n [nan]],\n\n [[nan],\n [nan],\n [nan]],\n\n [[nan],\n [nan],\n [nan]],\n\n [[nan],\n [nan],\n [nan]],\n\n [[nan],\n [nan],\n [nan]],\n\n [[nan],\n [nan],\n [nan]]], device='cuda:0', grad_fn=)\n", "error": "ValueError(\"Expected parameter df (Tensor of shape (32, 3, 1)) of distribution Chi2() to satisfy the constraint GreaterThan(lower_bound=0.0), but found invalid values:\\ntensor([[[nan],\\n [nan],\\n [nan]],\\n\\n [[nan],\\n [nan],\\n [nan]],\\n\\n [[nan],\\n [nan],\\n [nan]],\\n\\n [[nan],\\n [nan],\\n [nan]],\\n\\n [[nan],\\n [nan],\\n [nan]],\\n\\n [[nan],\\n [nan],\\n [nan]],\\n\\n [[nan],\\n [nan],\\n [nan]],\\n\\n [[nan],\\n [nan],\\n [nan]],\\n\\n [[nan],\\n [nan],\\n [nan]],\\n\\n [[nan],\\n [nan],\\n [nan]],\\n\\n [[nan],\\n [nan],\\n [nan]],\\n\\n [[nan],\\n [nan],\\n [nan]],\\n\\n [[nan],\\n [nan],\\n [nan]],\\n\\n [[nan],\\n [nan],\\n [nan]],\\n\\n [[nan],\\n [nan],\\n [nan]],\\n\\n [[nan],\\n [nan],\\n [nan]],\\n\\n [[nan],\\n [nan],\\n [nan]],\\n\\n [[nan],\\n [nan],\\n [nan]],\\n\\n [[nan],\\n [nan],\\n [nan]],\\n\\n [[nan],\\n [nan],\\n [nan]],\\n\\n [[nan],\\n [nan],\\n [nan]],\\n\\n [[nan],\\n [nan],\\n [nan]],\\n\\n [[nan],\\n [nan],\\n [nan]],\\n\\n [[nan],\\n [nan],\\n [nan]],\\n\\n [[nan],\\n [nan],\\n [nan]],\\n\\n [[nan],\\n [nan],\\n [nan]],\\n\\n [[nan],\\n [nan],\\n [nan]],\\n\\n [[nan],\\n [nan],\\n [nan]],\\n\\n [[nan],\\n [nan],\\n [nan]],\\n\\n [[nan],\\n [nan],\\n [nan]],\\n\\n [[nan],\\n [nan],\\n [nan]],\\n\\n [[nan],\\n [nan],\\n [nan]]], device='cuda:0', grad_fn=)\")", "configuration_origin": "Initial design" } ] ], [ [ 4, "{\"task_id\": \"1c0e9c2e-1719-11ed-8c29-312016f08e28\"}", 0, 5.555555555555555 ], [ 2147483647.0, 6.664032697677612, { "__enum__": "StatusType.CRASHED" }, 1659963242.2424304, 1659963249.7442608, { "traceback": "Traceback (most recent call last):\n File \"/home/robby/miniconda3/envs/auto-pytorch/lib/python3.8/site-packages/autoPyTorch/evaluation/tae.py\", line 61, in fit_predict_try_except_decorator\n ta(queue=queue, **kwargs)\n File \"/home/robby/miniconda3/envs/auto-pytorch/lib/python3.8/site-packages/autoPyTorch/evaluation/time_series_forecasting_train_evaluator.py\", line 558, in forecasting_eval_train_function\n evaluator.fit_predict_and_loss()\n File \"/home/robby/miniconda3/envs/auto-pytorch/lib/python3.8/site-packages/autoPyTorch/evaluation/time_series_forecasting_train_evaluator.py\", line 176, in fit_predict_and_loss\n y_train_pred, y_opt_pred, y_valid_pred, y_test_pred = self._fit_and_predict(pipeline, split_id,\n File \"/home/robby/miniconda3/envs/auto-pytorch/lib/python3.8/site-packages/autoPyTorch/evaluation/train_evaluator.py\", line 364, in _fit_and_predict\n fit_and_suppress_warnings(self.logger, pipeline, X, y)\n File \"/home/robby/miniconda3/envs/auto-pytorch/lib/python3.8/site-packages/autoPyTorch/evaluation/abstract_evaluator.py\", line 338, in fit_and_suppress_warnings\n pipeline.fit(X, y)\n File \"/home/robby/miniconda3/envs/auto-pytorch/lib/python3.8/site-packages/autoPyTorch/pipeline/base_pipeline.py\", line 158, in fit\n self.fit_estimator(X, y, **fit_params)\n File \"/home/robby/miniconda3/envs/auto-pytorch/lib/python3.8/site-packages/autoPyTorch/pipeline/base_pipeline.py\", line 177, in fit_estimator\n self._final_estimator.fit(X, y, **fit_params)\n File \"/home/robby/miniconda3/envs/auto-pytorch/lib/python3.8/site-packages/autoPyTorch/pipeline/components/training/trainer/__init__.py\", line 211, in fit\n self._fit(\n File \"/home/robby/miniconda3/envs/auto-pytorch/lib/python3.8/site-packages/autoPyTorch/pipeline/components/training/trainer/__init__.py\", line 310, in _fit\n train_loss, train_metrics = self.choice.train_epoch(\n File \"/home/robby/miniconda3/envs/auto-pytorch/lib/python3.8/site-packages/autoPyTorch/pipeline/components/training/trainer/forecasting_trainer/forecasting_base_trainer.py\", line 106, in train_epoch\n loss, outputs = self.train_step(data, targets)\n File \"/home/robby/miniconda3/envs/auto-pytorch/lib/python3.8/site-packages/autoPyTorch/pipeline/components/training/trainer/forecasting_trainer/forecasting_base_trainer.py\", line 206, in train_step\n outputs = self.model(past_targets=past_target,\n File \"/home/robby/miniconda3/envs/auto-pytorch/lib/python3.8/site-packages/torch/nn/modules/module.py\", line 1130, in _call_impl\n return forward_call(*input, **kwargs)\n File \"/home/robby/miniconda3/envs/auto-pytorch/lib/python3.8/site-packages/autoPyTorch/pipeline/components/setup/network/forecasting_architecture.py\", line 602, in forward\n output = self.head(decoder_output)\n File \"/home/robby/miniconda3/envs/auto-pytorch/lib/python3.8/site-packages/torch/nn/modules/module.py\", line 1130, in _call_impl\n return forward_call(*input, **kwargs)\n File \"/home/robby/miniconda3/envs/auto-pytorch/lib/python3.8/site-packages/autoPyTorch/pipeline/components/setup/network_head/forecasting_network_head/distribution.py\", line 100, in forward\n return self.dist_cls(*self.domain_map(*params_unbounded))\n File \"/home/robby/miniconda3/envs/auto-pytorch/lib/python3.8/site-packages/torch/distributions/studentT.py\", line 50, in __init__\n self._chi2 = Chi2(self.df)\n File \"/home/robby/miniconda3/envs/auto-pytorch/lib/python3.8/site-packages/torch/distributions/chi2.py\", line 22, in __init__\n super(Chi2, self).__init__(0.5 * df, 0.5, validate_args=validate_args)\n File \"/home/robby/miniconda3/envs/auto-pytorch/lib/python3.8/site-packages/torch/distributions/gamma.py\", line 52, in __init__\n super(Gamma, self).__init__(batch_shape, validate_args=validate_args)\n File \"/home/robby/miniconda3/envs/auto-pytorch/lib/python3.8/site-packages/torch/distributions/distribution.py\", line 55, in __init__\n raise ValueError(\nValueError: Expected parameter df (Tensor of shape (32, 3, 1)) of distribution Chi2() to satisfy the constraint GreaterThan(lower_bound=0.0), but found invalid values:\ntensor([[[nan],\n [nan],\n [nan]],\n\n [[nan],\n [nan],\n [nan]],\n\n [[nan],\n [nan],\n [nan]],\n\n [[nan],\n [nan],\n [nan]],\n\n [[nan],\n [nan],\n [nan]],\n\n [[nan],\n [nan],\n [nan]],\n\n [[nan],\n [nan],\n [nan]],\n\n [[nan],\n [nan],\n [nan]],\n\n [[nan],\n [nan],\n [nan]],\n\n [[nan],\n [nan],\n [nan]],\n\n [[nan],\n [nan],\n [nan]],\n\n [[nan],\n [nan],\n [nan]],\n\n [[nan],\n [nan],\n [nan]],\n\n [[nan],\n [nan],\n [nan]],\n\n [[nan],\n [nan],\n [nan]],\n\n [[nan],\n [nan],\n [nan]],\n\n [[nan],\n [nan],\n [nan]],\n\n [[nan],\n [nan],\n [nan]],\n\n [[nan],\n [nan],\n [nan]],\n\n [[nan],\n [nan],\n [nan]],\n\n [[nan],\n [nan],\n [nan]],\n\n [[nan],\n [nan],\n [nan]],\n\n [[nan],\n [nan],\n [nan]],\n\n [[nan],\n [nan],\n [nan]],\n\n [[nan],\n [nan],\n [nan]],\n\n [[nan],\n [nan],\n [nan]],\n\n [[nan],\n [nan],\n [nan]],\n\n [[nan],\n [nan],\n [nan]],\n\n [[nan],\n [nan],\n [nan]],\n\n [[nan],\n [nan],\n [nan]],\n\n [[nan],\n [nan],\n [nan]],\n\n [[nan],\n [nan],\n [nan]]], device='cuda:0', grad_fn=)\n", "error": "ValueError(\"Expected parameter df (Tensor of shape (32, 3, 1)) of distribution Chi2() to satisfy the constraint GreaterThan(lower_bound=0.0), but found invalid values:\\ntensor([[[nan],\\n [nan],\\n [nan]],\\n\\n [[nan],\\n [nan],\\n [nan]],\\n\\n [[nan],\\n [nan],\\n [nan]],\\n\\n [[nan],\\n [nan],\\n [nan]],\\n\\n [[nan],\\n [nan],\\n [nan]],\\n\\n [[nan],\\n [nan],\\n [nan]],\\n\\n [[nan],\\n [nan],\\n [nan]],\\n\\n [[nan],\\n [nan],\\n [nan]],\\n\\n [[nan],\\n [nan],\\n [nan]],\\n\\n [[nan],\\n [nan],\\n [nan]],\\n\\n [[nan],\\n [nan],\\n [nan]],\\n\\n [[nan],\\n [nan],\\n [nan]],\\n\\n [[nan],\\n [nan],\\n [nan]],\\n\\n [[nan],\\n [nan],\\n [nan]],\\n\\n [[nan],\\n [nan],\\n [nan]],\\n\\n [[nan],\\n [nan],\\n [nan]],\\n\\n [[nan],\\n [nan],\\n [nan]],\\n\\n [[nan],\\n [nan],\\n [nan]],\\n\\n [[nan],\\n [nan],\\n [nan]],\\n\\n [[nan],\\n [nan],\\n [nan]],\\n\\n [[nan],\\n [nan],\\n [nan]],\\n\\n [[nan],\\n [nan],\\n [nan]],\\n\\n [[nan],\\n [nan],\\n [nan]],\\n\\n [[nan],\\n [nan],\\n [nan]],\\n\\n [[nan],\\n [nan],\\n [nan]],\\n\\n [[nan],\\n [nan],\\n [nan]],\\n\\n [[nan],\\n [nan],\\n [nan]],\\n\\n [[nan],\\n [nan],\\n [nan]],\\n\\n [[nan],\\n [nan],\\n [nan]],\\n\\n [[nan],\\n [nan],\\n [nan]],\\n\\n [[nan],\\n [nan],\\n [nan]],\\n\\n [[nan],\\n [nan],\\n [nan]]], device='cuda:0', grad_fn=)\")", "configuration_origin": "Initial design" } ] ], [ [ 5, "{\"task_id\": \"1c0e9c2e-1719-11ed-8c29-312016f08e28\"}", 0, 5.555555555555555 ], [ 2147483647.0, 5.322012662887573, { "__enum__": "StatusType.CRASHED" }, 1659963251.4298904, 1659963257.3337128, { "traceback": "Traceback (most recent call last):\n File \"/home/robby/miniconda3/envs/auto-pytorch/lib/python3.8/site-packages/autoPyTorch/evaluation/tae.py\", line 61, in fit_predict_try_except_decorator\n ta(queue=queue, **kwargs)\n File \"/home/robby/miniconda3/envs/auto-pytorch/lib/python3.8/site-packages/autoPyTorch/evaluation/time_series_forecasting_train_evaluator.py\", line 558, in forecasting_eval_train_function\n evaluator.fit_predict_and_loss()\n File \"/home/robby/miniconda3/envs/auto-pytorch/lib/python3.8/site-packages/autoPyTorch/evaluation/time_series_forecasting_train_evaluator.py\", line 176, in fit_predict_and_loss\n y_train_pred, y_opt_pred, y_valid_pred, y_test_pred = self._fit_and_predict(pipeline, split_id,\n File \"/home/robby/miniconda3/envs/auto-pytorch/lib/python3.8/site-packages/autoPyTorch/evaluation/train_evaluator.py\", line 364, in _fit_and_predict\n fit_and_suppress_warnings(self.logger, pipeline, X, y)\n File \"/home/robby/miniconda3/envs/auto-pytorch/lib/python3.8/site-packages/autoPyTorch/evaluation/abstract_evaluator.py\", line 338, in fit_and_suppress_warnings\n pipeline.fit(X, y)\n File \"/home/robby/miniconda3/envs/auto-pytorch/lib/python3.8/site-packages/autoPyTorch/pipeline/base_pipeline.py\", line 158, in fit\n self.fit_estimator(X, y, **fit_params)\n File \"/home/robby/miniconda3/envs/auto-pytorch/lib/python3.8/site-packages/autoPyTorch/pipeline/base_pipeline.py\", line 177, in fit_estimator\n self._final_estimator.fit(X, y, **fit_params)\n File \"/home/robby/miniconda3/envs/auto-pytorch/lib/python3.8/site-packages/autoPyTorch/pipeline/components/training/trainer/__init__.py\", line 211, in fit\n self._fit(\n File \"/home/robby/miniconda3/envs/auto-pytorch/lib/python3.8/site-packages/autoPyTorch/pipeline/components/training/trainer/__init__.py\", line 310, in _fit\n train_loss, train_metrics = self.choice.train_epoch(\n File \"/home/robby/miniconda3/envs/auto-pytorch/lib/python3.8/site-packages/autoPyTorch/pipeline/components/training/trainer/forecasting_trainer/forecasting_base_trainer.py\", line 106, in train_epoch\n loss, outputs = self.train_step(data, targets)\n File \"/home/robby/miniconda3/envs/auto-pytorch/lib/python3.8/site-packages/autoPyTorch/pipeline/components/training/trainer/forecasting_trainer/forecasting_base_trainer.py\", line 206, in train_step\n outputs = self.model(past_targets=past_target,\n File \"/home/robby/miniconda3/envs/auto-pytorch/lib/python3.8/site-packages/torch/nn/modules/module.py\", line 1130, in _call_impl\n return forward_call(*input, **kwargs)\n File \"/home/robby/miniconda3/envs/auto-pytorch/lib/python3.8/site-packages/autoPyTorch/pipeline/components/setup/network/forecasting_architecture.py\", line 742, in forward\n net_output = self.head(decoder_output)\n File \"/home/robby/miniconda3/envs/auto-pytorch/lib/python3.8/site-packages/torch/nn/modules/module.py\", line 1130, in _call_impl\n return forward_call(*input, **kwargs)\n File \"/home/robby/miniconda3/envs/auto-pytorch/lib/python3.8/site-packages/autoPyTorch/pipeline/components/setup/network_head/forecasting_network_head/distribution.py\", line 100, in forward\n return self.dist_cls(*self.domain_map(*params_unbounded))\n File \"/home/robby/miniconda3/envs/auto-pytorch/lib/python3.8/site-packages/torch/distributions/studentT.py\", line 50, in __init__\n self._chi2 = Chi2(self.df)\n File \"/home/robby/miniconda3/envs/auto-pytorch/lib/python3.8/site-packages/torch/distributions/chi2.py\", line 22, in __init__\n super(Chi2, self).__init__(0.5 * df, 0.5, validate_args=validate_args)\n File \"/home/robby/miniconda3/envs/auto-pytorch/lib/python3.8/site-packages/torch/distributions/gamma.py\", line 52, in __init__\n super(Gamma, self).__init__(batch_shape, validate_args=validate_args)\n File \"/home/robby/miniconda3/envs/auto-pytorch/lib/python3.8/site-packages/torch/distributions/distribution.py\", line 55, in __init__\n raise ValueError(\nValueError: Expected parameter df (Tensor of shape (32, 3, 1)) of distribution Chi2() to satisfy the constraint GreaterThan(lower_bound=0.0), but found invalid values:\ntensor([[[nan],\n [nan],\n [nan]],\n\n [[nan],\n [nan],\n [nan]],\n\n [[nan],\n [nan],\n [nan]],\n\n [[nan],\n [nan],\n [nan]],\n\n [[nan],\n [nan],\n [nan]],\n\n [[nan],\n [nan],\n [nan]],\n\n [[nan],\n [nan],\n [nan]],\n\n [[nan],\n [nan],\n [nan]],\n\n [[nan],\n [nan],\n [nan]],\n\n [[nan],\n [nan],\n [nan]],\n\n [[nan],\n [nan],\n [nan]],\n\n [[nan],\n [nan],\n [nan]],\n\n [[nan],\n [nan],\n [nan]],\n\n [[nan],\n [nan],\n [nan]],\n\n [[nan],\n [nan],\n [nan]],\n\n [[nan],\n [nan],\n [nan]],\n\n [[nan],\n [nan],\n [nan]],\n\n [[nan],\n [nan],\n [nan]],\n\n [[nan],\n [nan],\n [nan]],\n\n [[nan],\n [nan],\n [nan]],\n\n [[nan],\n [nan],\n [nan]],\n\n [[nan],\n [nan],\n [nan]],\n\n [[nan],\n [nan],\n [nan]],\n\n [[nan],\n [nan],\n [nan]],\n\n [[nan],\n [nan],\n [nan]],\n\n [[nan],\n [nan],\n [nan]],\n\n [[nan],\n [nan],\n [nan]],\n\n [[nan],\n [nan],\n [nan]],\n\n [[nan],\n [nan],\n [nan]],\n\n [[nan],\n [nan],\n [nan]],\n\n [[nan],\n [nan],\n [nan]],\n\n [[nan],\n [nan],\n [nan]]], device='cuda:0', grad_fn=)\n", "error": "ValueError(\"Expected parameter df (Tensor of shape (32, 3, 1)) of distribution Chi2() to satisfy the constraint GreaterThan(lower_bound=0.0), but found invalid values:\\ntensor([[[nan],\\n [nan],\\n [nan]],\\n\\n [[nan],\\n [nan],\\n [nan]],\\n\\n [[nan],\\n [nan],\\n [nan]],\\n\\n [[nan],\\n [nan],\\n [nan]],\\n\\n [[nan],\\n [nan],\\n [nan]],\\n\\n [[nan],\\n [nan],\\n [nan]],\\n\\n [[nan],\\n [nan],\\n [nan]],\\n\\n [[nan],\\n [nan],\\n [nan]],\\n\\n [[nan],\\n [nan],\\n [nan]],\\n\\n [[nan],\\n [nan],\\n [nan]],\\n\\n [[nan],\\n [nan],\\n [nan]],\\n\\n [[nan],\\n [nan],\\n [nan]],\\n\\n [[nan],\\n [nan],\\n [nan]],\\n\\n [[nan],\\n [nan],\\n [nan]],\\n\\n [[nan],\\n [nan],\\n [nan]],\\n\\n [[nan],\\n [nan],\\n [nan]],\\n\\n [[nan],\\n [nan],\\n [nan]],\\n\\n [[nan],\\n [nan],\\n [nan]],\\n\\n [[nan],\\n [nan],\\n [nan]],\\n\\n [[nan],\\n [nan],\\n [nan]],\\n\\n [[nan],\\n [nan],\\n [nan]],\\n\\n [[nan],\\n [nan],\\n [nan]],\\n\\n [[nan],\\n [nan],\\n [nan]],\\n\\n [[nan],\\n [nan],\\n [nan]],\\n\\n [[nan],\\n [nan],\\n [nan]],\\n\\n [[nan],\\n [nan],\\n [nan]],\\n\\n [[nan],\\n [nan],\\n [nan]],\\n\\n [[nan],\\n [nan],\\n [nan]],\\n\\n [[nan],\\n [nan],\\n [nan]],\\n\\n [[nan],\\n [nan],\\n [nan]],\\n\\n [[nan],\\n [nan],\\n [nan]],\\n\\n [[nan],\\n [nan],\\n [nan]]], device='cuda:0', grad_fn=)\")", "configuration_origin": "Initial design" } ] ], [ [ 6, "{\"task_id\": \"1c0e9c2e-1719-11ed-8c29-312016f08e28\"}", 0, 5.555555555555555 ], [ 2147483647.0, 4.806845664978027, { "__enum__": "StatusType.CRASHED" }, 1659963259.0329926, 1659963264.3047543, { "traceback": "Traceback (most recent call last):\n File \"/home/robby/miniconda3/envs/auto-pytorch/lib/python3.8/site-packages/autoPyTorch/evaluation/tae.py\", line 61, in fit_predict_try_except_decorator\n ta(queue=queue, **kwargs)\n File \"/home/robby/miniconda3/envs/auto-pytorch/lib/python3.8/site-packages/autoPyTorch/evaluation/time_series_forecasting_train_evaluator.py\", line 558, in forecasting_eval_train_function\n evaluator.fit_predict_and_loss()\n File \"/home/robby/miniconda3/envs/auto-pytorch/lib/python3.8/site-packages/autoPyTorch/evaluation/time_series_forecasting_train_evaluator.py\", line 176, in fit_predict_and_loss\n y_train_pred, y_opt_pred, y_valid_pred, y_test_pred = self._fit_and_predict(pipeline, split_id,\n File \"/home/robby/miniconda3/envs/auto-pytorch/lib/python3.8/site-packages/autoPyTorch/evaluation/train_evaluator.py\", line 364, in _fit_and_predict\n fit_and_suppress_warnings(self.logger, pipeline, X, y)\n File \"/home/robby/miniconda3/envs/auto-pytorch/lib/python3.8/site-packages/autoPyTorch/evaluation/abstract_evaluator.py\", line 338, in fit_and_suppress_warnings\n pipeline.fit(X, y)\n File \"/home/robby/miniconda3/envs/auto-pytorch/lib/python3.8/site-packages/autoPyTorch/pipeline/base_pipeline.py\", line 158, in fit\n self.fit_estimator(X, y, **fit_params)\n File \"/home/robby/miniconda3/envs/auto-pytorch/lib/python3.8/site-packages/autoPyTorch/pipeline/base_pipeline.py\", line 177, in fit_estimator\n self._final_estimator.fit(X, y, **fit_params)\n File \"/home/robby/miniconda3/envs/auto-pytorch/lib/python3.8/site-packages/autoPyTorch/pipeline/components/training/trainer/__init__.py\", line 211, in fit\n self._fit(\n File \"/home/robby/miniconda3/envs/auto-pytorch/lib/python3.8/site-packages/autoPyTorch/pipeline/components/training/trainer/__init__.py\", line 310, in _fit\n train_loss, train_metrics = self.choice.train_epoch(\n File \"/home/robby/miniconda3/envs/auto-pytorch/lib/python3.8/site-packages/autoPyTorch/pipeline/components/training/trainer/forecasting_trainer/forecasting_base_trainer.py\", line 106, in train_epoch\n loss, outputs = self.train_step(data, targets)\n File \"/home/robby/miniconda3/envs/auto-pytorch/lib/python3.8/site-packages/autoPyTorch/pipeline/components/training/trainer/forecasting_trainer/forecasting_base_trainer.py\", line 206, in train_step\n outputs = self.model(past_targets=past_target,\n File \"/home/robby/miniconda3/envs/auto-pytorch/lib/python3.8/site-packages/torch/nn/modules/module.py\", line 1130, in _call_impl\n return forward_call(*input, **kwargs)\n File \"/home/robby/miniconda3/envs/auto-pytorch/lib/python3.8/site-packages/autoPyTorch/pipeline/components/setup/network/forecasting_architecture.py\", line 742, in forward\n net_output = self.head(decoder_output)\n File \"/home/robby/miniconda3/envs/auto-pytorch/lib/python3.8/site-packages/torch/nn/modules/module.py\", line 1130, in _call_impl\n return forward_call(*input, **kwargs)\n File \"/home/robby/miniconda3/envs/auto-pytorch/lib/python3.8/site-packages/autoPyTorch/pipeline/components/setup/network_head/forecasting_network_head/distribution.py\", line 100, in forward\n return self.dist_cls(*self.domain_map(*params_unbounded))\n File \"/home/robby/miniconda3/envs/auto-pytorch/lib/python3.8/site-packages/torch/distributions/studentT.py\", line 50, in __init__\n self._chi2 = Chi2(self.df)\n File \"/home/robby/miniconda3/envs/auto-pytorch/lib/python3.8/site-packages/torch/distributions/chi2.py\", line 22, in __init__\n super(Chi2, self).__init__(0.5 * df, 0.5, validate_args=validate_args)\n File \"/home/robby/miniconda3/envs/auto-pytorch/lib/python3.8/site-packages/torch/distributions/gamma.py\", line 52, in __init__\n super(Gamma, self).__init__(batch_shape, validate_args=validate_args)\n File \"/home/robby/miniconda3/envs/auto-pytorch/lib/python3.8/site-packages/torch/distributions/distribution.py\", line 55, in __init__\n raise ValueError(\nValueError: Expected parameter df (Tensor of shape (32, 3, 1)) of distribution Chi2() to satisfy the constraint GreaterThan(lower_bound=0.0), but found invalid values:\ntensor([[[2.9394],\n [3.0530],\n [3.8216]],\n\n [[2.9324],\n [2.2284],\n [2.3810]],\n\n [[2.6721],\n [3.1236],\n [3.0310]],\n\n [[2.6917],\n [2.6721],\n [2.5101]],\n\n [[2.2820],\n [2.9875],\n [2.6193]],\n\n [[3.4583],\n [3.2486],\n [3.3281]],\n\n [[2.8403],\n [2.8453],\n [2.3180]],\n\n [[2.5606],\n [2.6047],\n [2.9728]],\n\n [[3.0099],\n [2.7906],\n [3.1544]],\n\n [[3.0271],\n [4.1641],\n [2.9934]],\n\n [[2.3275],\n [2.5720],\n [2.2980]],\n\n [[2.7129],\n [2.2905],\n [2.6476]],\n\n [[3.3294],\n [3.1389],\n [2.3412]],\n\n [[2.6240],\n [2.2084],\n [2.1619]],\n\n [[ nan],\n [ nan],\n [ nan]],\n\n [[2.2944],\n [2.6617],\n [2.8250]],\n\n [[2.4964],\n [3.4340],\n [2.7953]],\n\n [[3.6663],\n [3.6053],\n [2.5538]],\n\n [[3.2686],\n [2.8508],\n [2.6883]],\n\n [[2.2515],\n [2.4994],\n [2.2889]],\n\n [[2.5357],\n [2.3916],\n [2.9599]],\n\n [[3.0250],\n [3.0876],\n [2.5733]],\n\n [[3.4240],\n [2.8908],\n [3.0592]],\n\n [[2.3201],\n [2.8079],\n [3.1914]],\n\n [[3.2443],\n [3.0002],\n [2.5645]],\n\n [[2.0748],\n [2.5153],\n [2.9441]],\n\n [[3.0716],\n [2.6744],\n [2.7525]],\n\n [[2.6023],\n [2.5330],\n [2.3209]],\n\n [[2.5370],\n [2.3912],\n [3.2765]],\n\n [[2.8843],\n [3.4547],\n [2.8139]],\n\n [[3.5575],\n [2.8284],\n [2.5498]],\n\n [[2.5592],\n [2.6515],\n [2.6283]]], device='cuda:0', grad_fn=)\n", "error": "ValueError(\"Expected parameter df (Tensor of shape (32, 3, 1)) of distribution Chi2() to satisfy the constraint GreaterThan(lower_bound=0.0), but found invalid values:\\ntensor([[[2.9394],\\n [3.0530],\\n [3.8216]],\\n\\n [[2.9324],\\n [2.2284],\\n [2.3810]],\\n\\n [[2.6721],\\n [3.1236],\\n [3.0310]],\\n\\n [[2.6917],\\n [2.6721],\\n [2.5101]],\\n\\n [[2.2820],\\n [2.9875],\\n [2.6193]],\\n\\n [[3.4583],\\n [3.2486],\\n [3.3281]],\\n\\n [[2.8403],\\n [2.8453],\\n [2.3180]],\\n\\n [[2.5606],\\n [2.6047],\\n [2.9728]],\\n\\n [[3.0099],\\n [2.7906],\\n [3.1544]],\\n\\n [[3.0271],\\n [4.1641],\\n [2.9934]],\\n\\n [[2.3275],\\n [2.5720],\\n [2.2980]],\\n\\n [[2.7129],\\n [2.2905],\\n [2.6476]],\\n\\n [[3.3294],\\n [3.1389],\\n [2.3412]],\\n\\n [[2.6240],\\n [2.2084],\\n [2.1619]],\\n\\n [[ nan],\\n [ nan],\\n [ nan]],\\n\\n [[2.2944],\\n [2.6617],\\n [2.8250]],\\n\\n [[2.4964],\\n [3.4340],\\n [2.7953]],\\n\\n [[3.6663],\\n [3.6053],\\n [2.5538]],\\n\\n [[3.2686],\\n [2.8508],\\n [2.6883]],\\n\\n [[2.2515],\\n [2.4994],\\n [2.2889]],\\n\\n [[2.5357],\\n [2.3916],\\n [2.9599]],\\n\\n [[3.0250],\\n [3.0876],\\n [2.5733]],\\n\\n [[3.4240],\\n [2.8908],\\n [3.0592]],\\n\\n [[2.3201],\\n [2.8079],\\n [3.1914]],\\n\\n [[3.2443],\\n [3.0002],\\n [2.5645]],\\n\\n [[2.0748],\\n [2.5153],\\n [2.9441]],\\n\\n [[3.0716],\\n [2.6744],\\n [2.7525]],\\n\\n [[2.6023],\\n [2.5330],\\n [2.3209]],\\n\\n [[2.5370],\\n [2.3912],\\n [3.2765]],\\n\\n [[2.8843],\\n [3.4547],\\n [2.8139]],\\n\\n [[3.5575],\\n [2.8284],\\n [2.5498]],\\n\\n [[2.5592],\\n [2.6515],\\n [2.6283]]], device='cuda:0', grad_fn=)\")", "configuration_origin": "Initial design" } ] ], [ [ 7, "{\"task_id\": \"1c0e9c2e-1719-11ed-8c29-312016f08e28\"}", 0, 5.555555555555555 ], [ 3.174582441463027, 6.632695198059082, { "__enum__": "StatusType.SUCCESS" }, 1659963265.9889429, 1659963274.1501205, { "opt_loss": { "mean_MASE_forecasting": 3.174582441463027, "median_MASE_forecasting": 3.0473660757375334, "mean_MAE_forecasting": 1.4678176879882812, "median_MAE_forecasting": 1.4089972178141277, "mean_MAPE_forecasting": 0.042925144221087126, "median_MAPE_forecasting": 0.04088613733450868, "mean_MSE_forecasting": 4.622099920248244, "median_MSE_forecasting": 3.6709700277679076 }, "duration": 4.013500928878784, "num_run": 8, "test_loss": { "mean_MASE_forecasting": 4.569135710246319, "median_MASE_forecasting": 4.569135710246319, "mean_MAE_forecasting": 2.1126111348450727, "median_MAE_forecasting": 2.1126111348450727, "mean_MAPE_forecasting": 0.03527200057584899, "median_MAPE_forecasting": 0.03527200057584899, "mean_MSE_forecasting": 4.949642750326809, "median_MSE_forecasting": 4.949642750326809 }, "configuration_origin": "Initial design" } ] ], [ [ 8, "{\"task_id\": \"1c0e9c2e-1719-11ed-8c29-312016f08e28\"}", 0, 5.555555555555555 ], [ 12.1102410161218, 23.372284173965454, { "__enum__": "StatusType.SUCCESS" }, 1659963275.8896346, 1659963300.7993524, { "opt_loss": { "mean_MASE_forecasting": 12.1102410161218, "median_MASE_forecasting": 11.165838197220205, "mean_MAE_forecasting": 5.599358749389649, "median_MAE_forecasting": 5.162699381510417, "mean_MAPE_forecasting": 0.1578215783090819, "median_MAPE_forecasting": 0.15400703998796825, "mean_MSE_forecasting": 38.281705465301876, "median_MSE_forecasting": 30.35104915361565 }, "duration": 20.428600311279297, "num_run": 9, "test_loss": { "mean_MASE_forecasting": 11.756282983836806, "median_MASE_forecasting": 11.756282983836806, "mean_MAE_forecasting": 5.435700734462178, "median_MAE_forecasting": 5.435700734462178, "mean_MAPE_forecasting": 0.08886032314601582, "median_MAPE_forecasting": 0.08886032314601582, "mean_MSE_forecasting": 35.55626185148137, "median_MSE_forecasting": 35.55626185148137 }, "configuration_origin": "Initial design" } ] ], [ [ 9, "{\"task_id\": \"1c0e9c2e-1719-11ed-8c29-312016f08e28\"}", 0, 5.555555555555555 ], [ 13.009910760923876, 13.713093996047974, { "__enum__": "StatusType.SUCCESS" }, 1659963302.5281656, 1659963317.8661776, { "opt_loss": { "mean_MASE_forecasting": 13.009910760923876, "median_MASE_forecasting": 12.077649493550146, "mean_MAE_forecasting": 6.0153350830078125, "median_MAE_forecasting": 5.58428955078125, "mean_MAPE_forecasting": 0.16875494755745604, "median_MAPE_forecasting": 0.16556289672851562, "mean_MSE_forecasting": 42.974935707219025, "median_MSE_forecasting": 32.73115497228961 }, "duration": 11.059327125549316, "num_run": 10, "test_loss": { "mean_MASE_forecasting": 14.610833278934692, "median_MASE_forecasting": 14.610833278934692, "mean_MAE_forecasting": 6.755546569830017, "median_MAE_forecasting": 6.755546569830017, "mean_MAPE_forecasting": 0.1098852879700473, "median_MAPE_forecasting": 0.1098852879700473, "mean_MSE_forecasting": 51.76546191601738, "median_MSE_forecasting": 51.76546191601738 }, "configuration_origin": "Initial design" } ] ] ], "config_origins": { "1": "Initial design", "2": "Initial design", "3": "Initial design", "4": "Initial design", "5": "Initial design", "6": "Initial design", "7": "Initial design", "8": "Initial design", "9": "Initial design" }, "configs": { "1": { "data_loader:backcast": false, "data_loader:batch_size": 32, "data_loader:num_batches_per_epoch": 50, "data_loader:sample_strategy": "SeqUniform", "data_loader:transform_time_features": false, "loss:__choice__": "DistributionLoss", "lr_scheduler:__choice__": "ReduceLROnPlateau", "network_backbone:__choice__": "flat_encoder", "network_embedding:__choice__": "NoEmbedding", "network_init:__choice__": "XavierInit", "optimizer:__choice__": "AdamOptimizer", "target_scaler:scaling_mode": "mean_abs", "trainer:__choice__": "ForecastingStandardTrainer", "data_loader:window_size": 2, "loss:DistributionLoss:dist_cls": "studentT", "loss:DistributionLoss:forecast_strategy": "sample", "lr_scheduler:ReduceLROnPlateau:factor": 0.5, "lr_scheduler:ReduceLROnPlateau:mode": "max", "lr_scheduler:ReduceLROnPlateau:patience": 10, "network_backbone:flat_encoder:__choice__": "MLPEncoder", "network_init:XavierInit:bias_strategy": "Normal", "optimizer:AdamOptimizer:beta1": 0.9, "optimizer:AdamOptimizer:beta2": 0.999, "optimizer:AdamOptimizer:lr": 0.001, "optimizer:AdamOptimizer:weight_decay": 1e-08, "loss:DistributionLoss:aggregation": "median", "loss:DistributionLoss:num_samples": 100, "network_backbone:flat_encoder:MLPDecoder:has_local_layer": true, "network_backbone:flat_encoder:MLPDecoder:num_layers": 0, "network_backbone:flat_encoder:MLPEncoder:activation": "relu", "network_backbone:flat_encoder:MLPEncoder:normalization": "NoNorm", "network_backbone:flat_encoder:MLPEncoder:num_groups": 1, "network_backbone:flat_encoder:MLPEncoder:num_units_1": 40, "network_backbone:flat_encoder:MLPEncoder:use_dropout": false, "network_backbone:flat_encoder:MLPDecoder:units_local_layer": 40 }, "2": { "data_loader:backcast": false, "data_loader:batch_size": 32, "data_loader:num_batches_per_epoch": 50, "data_loader:sample_strategy": "SeqUniform", "data_loader:transform_time_features": false, "loss:__choice__": "DistributionLoss", "lr_scheduler:__choice__": "ReduceLROnPlateau", "network_backbone:__choice__": "seq_encoder", "network_embedding:__choice__": "NoEmbedding", "network_init:__choice__": "XavierInit", "optimizer:__choice__": "AdamOptimizer", "target_scaler:scaling_mode": "mean_abs", "trainer:__choice__": "ForecastingStandardTrainer", "data_loader:window_size": 2, "loss:DistributionLoss:dist_cls": "studentT", "loss:DistributionLoss:forecast_strategy": "sample", "lr_scheduler:ReduceLROnPlateau:factor": 0.5, "lr_scheduler:ReduceLROnPlateau:mode": "max", "lr_scheduler:ReduceLROnPlateau:patience": 10, "network_backbone:seq_encoder:block_1:__choice__": "RNNEncoder", "network_backbone:seq_encoder:decoder_auto_regressive": false, "network_backbone:seq_encoder:num_blocks": 1, "network_backbone:seq_encoder:skip_connection": false, "network_backbone:seq_encoder:use_temporal_fusion": false, "network_backbone:seq_encoder:variable_selection": false, "network_init:XavierInit:bias_strategy": "Normal", "optimizer:AdamOptimizer:beta1": 0.9, "optimizer:AdamOptimizer:beta2": 0.999, "optimizer:AdamOptimizer:lr": 0.001, "optimizer:AdamOptimizer:weight_decay": 1e-08, "loss:DistributionLoss:aggregation": "median", "loss:DistributionLoss:num_samples": 100, "network_backbone:seq_encoder:block_1:RNNEncoder:bidirectional": false, "network_backbone:seq_encoder:block_1:RNNEncoder:cell_type": "lstm", "network_backbone:seq_encoder:block_1:RNNEncoder:decoder_type": "MLPDecoder", "network_backbone:seq_encoder:block_1:RNNEncoder:hidden_size": 40, "network_backbone:seq_encoder:block_1:RNNEncoder:num_layers": 2, "network_backbone:seq_encoder:block_1:RNNEncoder:use_dropout": true, "network_backbone:seq_encoder:block_1:MLPDecoder:auto_regressive": true, "network_backbone:seq_encoder:block_1:MLPDecoder:num_layers": 0, "network_backbone:seq_encoder:block_1:RNNEncoder:dropout": 0.1 }, "3": { "data_loader:backcast": false, "data_loader:batch_size": 32, "data_loader:num_batches_per_epoch": 50, "data_loader:sample_strategy": "SeqUniform", "data_loader:transform_time_features": false, "loss:__choice__": "DistributionLoss", "lr_scheduler:__choice__": "ReduceLROnPlateau", "network_backbone:__choice__": "seq_encoder", "network_embedding:__choice__": "NoEmbedding", "network_init:__choice__": "XavierInit", "optimizer:__choice__": "AdamOptimizer", "target_scaler:scaling_mode": "mean_abs", "trainer:__choice__": "ForecastingStandardTrainer", "data_loader:window_size": 2, "loss:DistributionLoss:dist_cls": "studentT", "loss:DistributionLoss:forecast_strategy": "sample", "lr_scheduler:ReduceLROnPlateau:factor": 0.5, "lr_scheduler:ReduceLROnPlateau:mode": "max", "lr_scheduler:ReduceLROnPlateau:patience": 10, "network_backbone:seq_encoder:block_1:__choice__": "RNNEncoder", "network_backbone:seq_encoder:decoder_auto_regressive": false, "network_backbone:seq_encoder:num_blocks": 1, "network_backbone:seq_encoder:skip_connection": false, "network_backbone:seq_encoder:use_temporal_fusion": false, "network_backbone:seq_encoder:variable_selection": false, "network_init:XavierInit:bias_strategy": "Normal", "optimizer:AdamOptimizer:beta1": 0.9, "optimizer:AdamOptimizer:beta2": 0.999, "optimizer:AdamOptimizer:lr": 0.001, "optimizer:AdamOptimizer:weight_decay": 1e-08, "loss:DistributionLoss:aggregation": "median", "loss:DistributionLoss:num_samples": 100, "network_backbone:seq_encoder:block_1:RNNEncoder:bidirectional": false, "network_backbone:seq_encoder:block_1:RNNEncoder:cell_type": "gru", "network_backbone:seq_encoder:block_1:RNNEncoder:decoder_type": "MLPDecoder", "network_backbone:seq_encoder:block_1:RNNEncoder:hidden_size": 50, "network_backbone:seq_encoder:block_1:RNNEncoder:num_layers": 1, "network_backbone:seq_encoder:block_1:RNNEncoder:use_dropout": false, "network_backbone:seq_encoder:block_1:MLPDecoder:auto_regressive": false, "network_backbone:seq_encoder:block_1:MLPDecoder:num_layers": 0, "network_backbone:seq_encoder:block_1:MLPDecoder:has_local_layer": true, "network_backbone:seq_encoder:block_1:MLPDecoder:units_local_layer": 30 }, "4": { "data_loader:backcast": false, "data_loader:batch_size": 32, "data_loader:num_batches_per_epoch": 50, "data_loader:sample_strategy": "SeqUniform", "data_loader:transform_time_features": false, "loss:__choice__": "DistributionLoss", "lr_scheduler:__choice__": "ReduceLROnPlateau", "network_backbone:__choice__": "seq_encoder", "network_embedding:__choice__": "NoEmbedding", "network_init:__choice__": "XavierInit", "optimizer:__choice__": "AdamOptimizer", "target_scaler:scaling_mode": "mean_abs", "trainer:__choice__": "ForecastingStandardTrainer", "data_loader:window_size": 2, "loss:DistributionLoss:dist_cls": "studentT", "loss:DistributionLoss:forecast_strategy": "sample", "lr_scheduler:ReduceLROnPlateau:factor": 0.5, "lr_scheduler:ReduceLROnPlateau:mode": "max", "lr_scheduler:ReduceLROnPlateau:patience": 10, "network_backbone:seq_encoder:block_1:__choice__": "TCNEncoder", "network_backbone:seq_encoder:decoder_auto_regressive": false, "network_backbone:seq_encoder:num_blocks": 1, "network_backbone:seq_encoder:skip_connection": false, "network_backbone:seq_encoder:use_temporal_fusion": false, "network_backbone:seq_encoder:variable_selection": false, "network_init:XavierInit:bias_strategy": "Normal", "optimizer:AdamOptimizer:beta1": 0.9, "optimizer:AdamOptimizer:beta2": 0.999, "optimizer:AdamOptimizer:lr": 0.001, "optimizer:AdamOptimizer:weight_decay": 1e-08, "loss:DistributionLoss:aggregation": "median", "loss:DistributionLoss:num_samples": 100, "network_backbone:seq_encoder:block_1:TCNEncoder:kernel_size_1": 7, "network_backbone:seq_encoder:block_1:TCNEncoder:num_blocks": 3, "network_backbone:seq_encoder:block_1:TCNEncoder:num_filters_1": 30, "network_backbone:seq_encoder:block_1:TCNEncoder:use_dropout": false, "network_backbone:seq_encoder:block_1:MLPDecoder:auto_regressive": false, "network_backbone:seq_encoder:block_1:MLPDecoder:num_layers": 0, "network_backbone:seq_encoder:block_1:TCNEncoder:kernel_size_2": 3, "network_backbone:seq_encoder:block_1:TCNEncoder:kernel_size_3": 3, "network_backbone:seq_encoder:block_1:TCNEncoder:num_filters_2": 30, "network_backbone:seq_encoder:block_1:TCNEncoder:num_filters_3": 30, "network_backbone:seq_encoder:block_1:MLPDecoder:has_local_layer": false }, "5": { "data_loader:backcast": false, "data_loader:batch_size": 32, "data_loader:num_batches_per_epoch": 50, "data_loader:sample_strategy": "SeqUniform", "data_loader:transform_time_features": false, "loss:__choice__": "DistributionLoss", "lr_scheduler:__choice__": "ReduceLROnPlateau", "network_backbone:__choice__": "seq_encoder", "network_embedding:__choice__": "NoEmbedding", "network_init:__choice__": "XavierInit", "optimizer:__choice__": "AdamOptimizer", "target_scaler:scaling_mode": "mean_abs", "trainer:__choice__": "ForecastingStandardTrainer", "data_loader:window_size": 2, "loss:DistributionLoss:dist_cls": "studentT", "loss:DistributionLoss:forecast_strategy": "mean", "lr_scheduler:ReduceLROnPlateau:factor": 0.5, "lr_scheduler:ReduceLROnPlateau:mode": "max", "lr_scheduler:ReduceLROnPlateau:patience": 10, "network_backbone:seq_encoder:block_1:__choice__": "RNNEncoder", "network_backbone:seq_encoder:decoder_auto_regressive": true, "network_backbone:seq_encoder:num_blocks": 1, "network_backbone:seq_encoder:skip_connection": false, "network_backbone:seq_encoder:use_temporal_fusion": false, "network_backbone:seq_encoder:variable_selection": false, "network_init:XavierInit:bias_strategy": "Normal", "optimizer:AdamOptimizer:beta1": 0.9, "optimizer:AdamOptimizer:beta2": 0.999, "optimizer:AdamOptimizer:lr": 0.001, "optimizer:AdamOptimizer:weight_decay": 1e-08, "network_backbone:seq_encoder:block_1:RNNEncoder:bidirectional": false, "network_backbone:seq_encoder:block_1:RNNEncoder:cell_type": "gru", "network_backbone:seq_encoder:block_1:RNNEncoder:decoder_type": "RNNDecoder", "network_backbone:seq_encoder:block_1:RNNEncoder:hidden_size": 32, "network_backbone:seq_encoder:block_1:RNNEncoder:num_layers": 3, "network_backbone:seq_encoder:block_1:RNNEncoder:use_dropout": false, "network_backbone:seq_encoder:block_1:RNNDecoder:decoder_type": "RNNDecoder" }, "6": { "data_loader:backcast": false, "data_loader:batch_size": 32, "data_loader:num_batches_per_epoch": 50, "data_loader:sample_strategy": "SeqUniform", "data_loader:transform_time_features": true, "loss:__choice__": "DistributionLoss", "lr_scheduler:__choice__": "ReduceLROnPlateau", "network_backbone:__choice__": "seq_encoder", "network_embedding:__choice__": "NoEmbedding", "network_init:__choice__": "XavierInit", "optimizer:__choice__": "AdamOptimizer", "target_scaler:scaling_mode": "mean_abs", "trainer:__choice__": "ForecastingStandardTrainer", "data_loader:window_size": 2, "loss:DistributionLoss:dist_cls": "studentT", "loss:DistributionLoss:forecast_strategy": "sample", "lr_scheduler:ReduceLROnPlateau:factor": 0.5, "lr_scheduler:ReduceLROnPlateau:mode": "max", "lr_scheduler:ReduceLROnPlateau:patience": 10, "network_backbone:seq_encoder:block_1:__choice__": "TransformerEncoder", "network_backbone:seq_encoder:decoder_auto_regressive": true, "network_backbone:seq_encoder:num_blocks": 1, "network_backbone:seq_encoder:skip_connection": false, "network_backbone:seq_encoder:use_temporal_fusion": false, "network_backbone:seq_encoder:variable_selection": false, "network_init:XavierInit:bias_strategy": "Normal", "optimizer:AdamOptimizer:beta1": 0.9, "optimizer:AdamOptimizer:beta2": 0.999, "optimizer:AdamOptimizer:lr": 0.001, "optimizer:AdamOptimizer:weight_decay": 1e-08, "loss:DistributionLoss:aggregation": "median", "loss:DistributionLoss:num_samples": 100, "network_backbone:seq_encoder:block_1:TransformerEncoder:activation": "gelu", "network_backbone:seq_encoder:block_1:TransformerEncoder:d_feed_forward_log": 7, "network_backbone:seq_encoder:block_1:TransformerEncoder:d_model_log": 5, "network_backbone:seq_encoder:block_1:TransformerEncoder:decoder_type": "TransformerDecoder", "network_backbone:seq_encoder:block_1:TransformerEncoder:layer_norm_eps": 1e-05, "network_backbone:seq_encoder:block_1:TransformerEncoder:n_head_log": 3, "network_backbone:seq_encoder:block_1:TransformerEncoder:norm_first": true, "network_backbone:seq_encoder:block_1:TransformerEncoder:num_layers": 1, "network_backbone:seq_encoder:block_1:TransformerEncoder:use_dropout": true, "network_backbone:seq_encoder:block_1:TransformerEncoder:use_layer_norm_output": true, "network_backbone:seq_encoder:block_1:TransformerEncoder:use_positional_encoder": true, "network_backbone:seq_encoder:block_1:TransformerDecoder:activation": "gelu", "network_backbone:seq_encoder:block_1:TransformerDecoder:d_feed_forward_log": 7, "network_backbone:seq_encoder:block_1:TransformerDecoder:layer_norm_eps": 1e-05, "network_backbone:seq_encoder:block_1:TransformerDecoder:n_head_log": 3, "network_backbone:seq_encoder:block_1:TransformerDecoder:norm_first": true, "network_backbone:seq_encoder:block_1:TransformerDecoder:num_layers": 1, "network_backbone:seq_encoder:block_1:TransformerDecoder:use_dropout": true, "network_backbone:seq_encoder:block_1:TransformerDecoder:use_layer_norm_output": true, "network_backbone:seq_encoder:block_1:TransformerDecoder:use_positional_decoder": true, "network_backbone:seq_encoder:block_1:TransformerEncoder:dropout": 0.1, "network_backbone:seq_encoder:block_1:TransformerEncoder:dropout_positional_encoder": 0.1, "network_backbone:seq_encoder:block_1:TransformerEncoder:layer_norm_eps_output": 1e-05, "network_backbone:seq_encoder:block_1:TransformerDecoder:dropout": 0.1, "network_backbone:seq_encoder:block_1:TransformerDecoder:dropout_positional_decoder": 0.1, "network_backbone:seq_encoder:block_1:TransformerDecoder:layer_norm_eps_output": 1e-05 }, "7": { "data_loader:backcast": true, "data_loader:batch_size": 32, "data_loader:num_batches_per_epoch": 50, "data_loader:sample_strategy": "SeqUniform", "data_loader:transform_time_features": false, "loss:__choice__": "RegressionLoss", "lr_scheduler:__choice__": "ReduceLROnPlateau", "network_backbone:__choice__": "flat_encoder", "network_embedding:__choice__": "NoEmbedding", "network_init:__choice__": "XavierInit", "optimizer:__choice__": "AdamOptimizer", "target_scaler:scaling_mode": "none", "trainer:__choice__": "ForecastingStandardTrainer", "data_loader:backcast_period": 2, "loss:RegressionLoss:loss_name": "mase", "lr_scheduler:ReduceLROnPlateau:factor": 0.5, "lr_scheduler:ReduceLROnPlateau:mode": "max", "lr_scheduler:ReduceLROnPlateau:patience": 10, "network_backbone:flat_encoder:__choice__": "NBEATSEncoder", "network_init:XavierInit:bias_strategy": "Normal", "optimizer:AdamOptimizer:beta1": 0.9, "optimizer:AdamOptimizer:beta2": 0.999, "optimizer:AdamOptimizer:lr": 0.001, "optimizer:AdamOptimizer:weight_decay": 1e-08, "network_backbone:flat_encoder:NBEATSDecoder:activation": "relu", "network_backbone:flat_encoder:NBEATSDecoder:backcast_loss_ration": 0.0, "network_backbone:flat_encoder:NBEATSDecoder:n_beats_type": "I", "network_backbone:flat_encoder:NBEATSDecoder:normalization": "NoNorm", "network_backbone:flat_encoder:NBEATSDecoder:num_blocks_i_1": 3, "network_backbone:flat_encoder:NBEATSDecoder:num_layers_i_1": 2, "network_backbone:flat_encoder:NBEATSDecoder:num_stacks_i": 2, "network_backbone:flat_encoder:NBEATSDecoder:stack_type_i_1": "trend", "network_backbone:flat_encoder:NBEATSDecoder:use_dropout_i": true, "network_backbone:flat_encoder:NBEATSDecoder:weight_sharing_i_1": true, "network_backbone:flat_encoder:NBEATSDecoder:width_i_1": 256, "network_backbone:flat_encoder:NBEATSDecoder:dropout_i_1": 0.1, "network_backbone:flat_encoder:NBEATSDecoder:dropout_i_2": 0.1, "network_backbone:flat_encoder:NBEATSDecoder:expansion_coefficient_length_i_trend_1": 3, "network_backbone:flat_encoder:NBEATSDecoder:num_blocks_i_2": 3, "network_backbone:flat_encoder:NBEATSDecoder:num_layers_i_2": 2, "network_backbone:flat_encoder:NBEATSDecoder:stack_type_i_2": "seasonality", "network_backbone:flat_encoder:NBEATSDecoder:weight_sharing_i_2": true, "network_backbone:flat_encoder:NBEATSDecoder:width_i_2": 512, "network_backbone:flat_encoder:NBEATSDecoder:expansion_coefficient_length_i_seasonality_2": 7 }, "8": { "data_loader:backcast": false, "data_loader:batch_size": 32, "data_loader:num_batches_per_epoch": 50, "data_loader:sample_strategy": "SeqUniform", "data_loader:transform_time_features": false, "loss:__choice__": "RegressionLoss", "lr_scheduler:__choice__": "ReduceLROnPlateau", "network_backbone:__choice__": "flat_encoder", "network_embedding:__choice__": "NoEmbedding", "network_init:__choice__": "XavierInit", "optimizer:__choice__": "AdamOptimizer", "target_scaler:scaling_mode": "mean_abs", "trainer:__choice__": "ForecastingStandardTrainer", "data_loader:window_size": 2, "loss:RegressionLoss:loss_name": "mape", "lr_scheduler:ReduceLROnPlateau:factor": 0.5, "lr_scheduler:ReduceLROnPlateau:mode": "max", "lr_scheduler:ReduceLROnPlateau:patience": 10, "network_backbone:flat_encoder:__choice__": "NBEATSEncoder", "network_init:XavierInit:bias_strategy": "Normal", "optimizer:AdamOptimizer:beta1": 0.9, "optimizer:AdamOptimizer:beta2": 0.999, "optimizer:AdamOptimizer:lr": 0.001, "optimizer:AdamOptimizer:weight_decay": 1e-08, "network_backbone:flat_encoder:NBEATSDecoder:activation": "relu", "network_backbone:flat_encoder:NBEATSDecoder:backcast_loss_ration": 0.0, "network_backbone:flat_encoder:NBEATSDecoder:n_beats_type": "G", "network_backbone:flat_encoder:NBEATSDecoder:normalization": "NoNorm", "network_backbone:flat_encoder:NBEATSDecoder:expansion_coefficient_length_g": 32, "network_backbone:flat_encoder:NBEATSDecoder:num_blocks_g": 1, "network_backbone:flat_encoder:NBEATSDecoder:num_layers_g": 4, "network_backbone:flat_encoder:NBEATSDecoder:num_stacks_g": 30, "network_backbone:flat_encoder:NBEATSDecoder:use_dropout_g": true, "network_backbone:flat_encoder:NBEATSDecoder:weight_sharing_g": false, "network_backbone:flat_encoder:NBEATSDecoder:width_g": 512, "network_backbone:flat_encoder:NBEATSDecoder:dropout_g": 0.1 }, "9": { "data_loader:backcast": false, "data_loader:batch_size": 32, "data_loader:num_batches_per_epoch": 50, "data_loader:sample_strategy": "SeqUniform", "data_loader:transform_time_features": true, "loss:__choice__": "QuantileLoss", "lr_scheduler:__choice__": "ReduceLROnPlateau", "network_backbone:__choice__": "seq_encoder", "network_embedding:__choice__": "NoEmbedding", "network_init:__choice__": "XavierInit", "optimizer:__choice__": "AdamOptimizer", "target_scaler:scaling_mode": "standard", "trainer:__choice__": "ForecastingStandardTrainer", "data_loader:window_size": 2, "loss:QuantileLoss:lower_quantile": 0.1, "loss:QuantileLoss:upper_quantile": 0.9, "lr_scheduler:ReduceLROnPlateau:factor": 0.5, "lr_scheduler:ReduceLROnPlateau:mode": "max", "lr_scheduler:ReduceLROnPlateau:patience": 10, "network_backbone:seq_encoder:block_1:__choice__": "RNNEncoder", "network_backbone:seq_encoder:decoder_auto_regressive": false, "network_backbone:seq_encoder:num_blocks": 1, "network_backbone:seq_encoder:skip_connection": true, "network_backbone:seq_encoder:use_temporal_fusion": true, "network_backbone:seq_encoder:variable_selection": true, "network_init:XavierInit:bias_strategy": "Normal", "optimizer:AdamOptimizer:beta1": 0.9, "optimizer:AdamOptimizer:beta2": 0.999, "optimizer:AdamOptimizer:lr": 0.001, "optimizer:AdamOptimizer:weight_decay": 1e-08, "network_backbone:seq_encoder:block_1:RNNEncoder:bidirectional": false, "network_backbone:seq_encoder:block_1:RNNEncoder:cell_type": "lstm", "network_backbone:seq_encoder:block_1:RNNEncoder:decoder_type": "RNNDecoder", "network_backbone:seq_encoder:block_1:RNNEncoder:hidden_size": 32, "network_backbone:seq_encoder:block_1:RNNEncoder:num_layers": 1, "network_backbone:seq_encoder:block_1:RNNEncoder:use_dropout": false, "network_backbone:seq_encoder:share_single_variable_networks": true, "network_backbone:seq_encoder:skip_connection_type": "gate_add_norm", "network_backbone:seq_encoder:temporal_fusion:attention_d_model_log": 5, "network_backbone:seq_encoder:temporal_fusion:attention_n_head_log": 2, "network_backbone:seq_encoder:temporal_fusion:use_dropout": true, "network_backbone:seq_encoder:variable_selection_use_dropout": true, "network_backbone:seq_encoder:block_1:RNNDecoder:decoder_type": "RNNDecoder", "network_backbone:seq_encoder:grn_use_dropout": true, "network_backbone:seq_encoder:temporal_fusion:dropout_rate": 0.1, "network_backbone:seq_encoder:variable_selection_dropout_rate": 0.1, "network_backbone:seq_encoder:grn_dropout_rate": 0.1 } } }