When running with quick_start.yaml with own dataset getting the following error

[Shraban123]

multiprocessing.pool.RemoteTraceback: """ Traceback (most recent call last): File "/opt/conda/lib/python3.7/multiprocessing/pool.py", line 121, in worker result = (True, func(*args, *kwds)) File "/opt/conda/lib/python3.7/multiprocessing/pool.py", line 44, in mapstar return list(map(args)) File "/opt/conda/lib/python3.7/site-packages/graphvite-0.1.0-py3.7.egg/graphvite/application/application.py", line 411, in linear_classification loss.backward() File "/opt/conda/lib/python3.7/site-packages/torch/tensor.py", line 118, in backward torch.autograd.backward(self, gradient, retain_graph, create_graph) File "/opt/conda/lib/python3.7/site-packages/torch/autograd/init.py", line 93, in backward allow_unreachable=True) # allow_unreachable flag RuntimeError: CUDA error: CUBLAS_STATUS_EXECUTION_FAILED when calling cublasSgemm( handle, opa, opb, m, n, k, &alpha, a, lda, b, ldb, &beta, c, ldc) """

The above exception was the direct cause of the following exception:

Traceback (most recent call last): File "/opt/conda/bin/graphvite", line 11, in load_entry_point('graphvite==0.1.0', 'console_scripts', 'graphvite')() File "/opt/conda/lib/python3.7/site-packages/graphvite-0.1.0-py3.7.egg/graphvite/cmd.py", line 212, in main commandargs.command File "/opt/conda/lib/python3.7/site-packages/graphvite-0.1.0-py3.7.egg/graphvite/cmd.py", line 110, in run_main app.evaluate(*cfg.evaluate) File "/opt/conda/lib/python3.7/site-packages/graphvite-0.1.0-py3.7.egg/graphvite/util.py", line 95, in wrapper result = function(args, kwargs) File "/opt/conda/lib/python3.7/site-packages/graphvite-0.1.0-py3.7.egg/graphvite/application/application.py", line 101, in evaluate result = getattr(self, func_name)(kwargs) File "/opt/conda/lib/python3.7/site-packages/graphvite-0.1.0-py3.7.egg/graphvite/application/application.py", line 261, in node_classification results = self.gpu_map(linear_classification, settings) File "/opt/conda/lib/python3.7/site-packages/graphvite-0.1.0-py3.7.egg/graphvite/application/application.py", line 159, in gpu_map results = pool.map(func, settings, chunksize=1) File "/opt/conda/lib/python3.7/multiprocessing/pool.py", line 268, in map return self._map_async(func, iterable, mapstar, chunksize).get() File "/opt/conda/lib/python3.7/multiprocessing/pool.py", line 657, in get raise self._value RuntimeError: CUDA error: CUBLAS_STATUS_EXECUTION_FAILED when calling cublasSgemm( handle, opa, opb, m, n, k, &alpha, a, lda, b, ldb, &beta, c, ldc)

[Shraban123]

application: graph

resource: gpus: [] cpu_per_gpu: 2 dim: 128

format: delimiters: " " comment: "#"

graph:

file_name: '/home/shraban/Paper2/LINE/cora_edge_list.txt'

file_name: '/home/shraban/Paper2/LINE/demo_list.txt' as_undirected: true

build: optimizer: type: SGD lr: 0.025 weight_decay: 0.005 num_partition: auto num_negative: 1 batch_size: 7 # must be greater than numbe of nodes episode_size: 2

train: model: LINE num_epoch: 10 negative_weight: 2 augmentation_step: 2 random_walk_length: 2 random_walk_batch_size: 2 log_frequency: 10

evaluate: task: node classification

file_name: '/home/shraban/Paper2/LINE/cora_labels.txt'

file_name: '/home/shraban/Paper2/LINE/demo_labels.txt'
portions: [1]
times: 1

save: file_name: line_cora.pkl