AI Dungeon 2 crash

> load
What is the ID of the saved game?d2caf1e4-1a2b-11ea-8aac-0242ac1c0002
Copying gs://aidungeonstories/storyd2caf1e4-1a2b-11ea-8aac-0242ac1c0002.json...
- [1 files][  3.1 KiB/  3.1 KiB]
Operation completed over 1 objects/3.1 KiB.

Loading Game...

You are Thomas, a adventurer living in the kingdom of Larion, which has recently
 entered an alliance with the Monster Lord. This has resulted in thousands of
 monster girls immigrating to Larion. You have a sword and a shield. You make
 your living doing quests for whoever has the most gold. Lately, business hasn't
 been very good, because monsters no longer need to be driven off. You sigh and
 return home in defeat, unable to find a job yet again. When you enter your home,
 you are much surprised to find that it is now decorated with trophies from your
 recent adventures

> You go outside and fly to the moon.


You take flight, and float through the air towards the moon. The moonlight shines
 upon your face, illuminating your features as you soar through the sky. As you
 reach the edge of the horizon, you see a bright light, like sunlight, but much
 brighter

> You embrace the light.


As you touch the surface of the moon, you feel the warmth of its rays on your
 skin. It feels so nice, and you want more. You close your eyes, and let yourself
 drift into blissful oblivion

> You seek the castle of the moon.


The next day, you find the castle of the moon. You fly up to it, and land gently.
 You look around at the castle, and wonder what kind of people live there. There
 is no sign of anyone else here

> You find the moon queen.


You walk through the halls of the castle, looking for the moon queen. You hear
 her laughter from somewhere inside the castle, and then she appears before you.
 She smiles at you, and speaks softly


> You greet her.


"Hello, my name is..".
She looks at you, smiling brightly
"I'm glad you could make it".

You smile back, and begin to speak...

> You tell her that you are her's to command.


"Yes, I am your servant, and you can command me".
She nods happily, and begins to lead you to the throne room. You follow her,
 and soon arrive at the throne room

> You kneel before the queen.


You kneel down before the queen, who stands proudly in front of you. She holds
 a staff in one hand, and a spear in the other. Her hair is white, and her eyes
 are blue. She smiles at you, and beckons you forward

> You crawl toward the queen.


You crawl forward, until you are right in front of the queen. She stares at you,
 and raises her spear, ready to strike

> You wait.


You wait patiently, and eventually, the queen notices you. She smiles, and beckons
 you forward again

> You crawl toward the queen.


You crawl forward, and stand behind the queen. She slowly turns, and sees you

> You remove clothes.


You remove your clothing, and stand naked before the queen. She smiles at you,
 and begins to stroke your head
> You nuzzle into her hand.
Traceback (most recent call last):
  File "/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/client/session.py", line 1365, in _do_call
    return fn(*args)
  File "/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/client/session.py", line 1350, in _run_fn
    target_list, run_metadata)
  File "/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/client/session.py", line 1443, in _call_tf_sessionrun
    run_metadata)
tensorflow.python.framework.errors_impl.ResourceExhaustedError: 2 root error(s) found.
  (0) Resource exhausted: OOM when allocating tensor with shape[1,48,2,25,615,64] and type float on /job:localhost/replica:0/task:0/device:GPU:0 by allocator GPU_0_bfc
	 [[{{node sample_sequence/while/concat}}]]
Hint: If you want to see a list of allocated tensors when OOM happens, add report_tensor_allocations_upon_oom to RunOptions for current allocation info.

	 [[sample_sequence/while/Exit_3/_1387]]
Hint: If you want to see a list of allocated tensors when OOM happens, add report_tensor_allocations_upon_oom to RunOptions for current allocation info.

  (1) Resource exhausted: OOM when allocating tensor with shape[1,48,2,25,615,64] and type float on /job:localhost/replica:0/task:0/device:GPU:0 by allocator GPU_0_bfc
	 [[{{node sample_sequence/while/concat}}]]
Hint: If you want to see a list of allocated tensors when OOM happens, add report_tensor_allocations_upon_oom to RunOptions for current allocation info.

0 successful operations.
0 derived errors ignored.

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "play.py", line 211, in <module>
    play_aidungeon_2()
  File "play.py", line 180, in play_aidungeon_2
    result = "\n" + story_manager.act(action)
  File "/content/AIDungeon/story/story_manager.py", line 181, in act
    result = self.generate_result(action_choice)
  File "/content/AIDungeon/story/story_manager.py", line 186, in generate_result
    block = self.generator.generate(self.story_context() + action)
  File "/content/AIDungeon/generator/gpt2/gpt2_generator.py", line 109, in generate
    text = self.generate_raw(prompt)
  File "/content/AIDungeon/generator/gpt2/gpt2_generator.py", line 92, in generate_raw
    self.context: [context_tokens for _ in range(self.batch_size)]
  File "/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/client/session.py", line 956, in run
    run_metadata_ptr)
  File "/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/client/session.py", line 1180, in _run
    feed_dict_tensor, options, run_metadata)
  File "/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/client/session.py", line 1359, in _do_run
    run_metadata)
  File "/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/client/session.py", line 1384, in _do_call
    raise type(e)(node_def, op, message)
tensorflow.python.framework.errors_impl.ResourceExhaustedError: 2 root error(s) found.
  (0) Resource exhausted: OOM when allocating tensor with shape[1,48,2,25,615,64] and type float on /job:localhost/replica:0/task:0/device:GPU:0 by allocator GPU_0_bfc
	 [[node sample_sequence/while/concat (defined at /usr/local/lib/python3.6/dist-packages/tensorflow_core/python/framework/ops.py:1748) ]]
Hint: If you want to see a list of allocated tensors when OOM happens, add report_tensor_allocations_upon_oom to RunOptions for current allocation info.

	 [[sample_sequence/while/Exit_3/_1387]]
Hint: If you want to see a list of allocated tensors when OOM happens, add report_tensor_allocations_upon_oom to RunOptions for current allocation info.

  (1) Resource exhausted: OOM when allocating tensor with shape[1,48,2,25,615,64] and type float on /job:localhost/replica:0/task:0/device:GPU:0 by allocator GPU_0_bfc
	 [[node sample_sequence/while/concat (defined at /usr/local/lib/python3.6/dist-packages/tensorflow_core/python/framework/ops.py:1748) ]]
Hint: If you want to see a list of allocated tensors when OOM happens, add report_tensor_allocations_upon_oom to RunOptions for current allocation info.

0 successful operations.
0 derived errors ignored.

Original stack trace for 'sample_sequence/while/concat':
  File "play.py", line 211, in <module>
    play_aidungeon_2()
  File "play.py", line 74, in play_aidungeon_2
    generator = GPT2Generator()
  File "/content/AIDungeon/generator/gpt2/gpt2_generator.py", line 44, in __init__
    temperature=temperature, top_k=top_k, top_p=top_p
  File "/content/AIDungeon/generator/gpt2/src/sample.py", line 112, in sample_sequence
    back_prop=False,
  File "/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/ops/control_flow_ops.py", line 2753, in while_loop
    return_same_structure)
  File "/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/ops/control_flow_ops.py", line 2245, in BuildLoop
    pred, body, original_loop_vars, loop_vars, shape_invariants)
  File "/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/ops/control_flow_ops.py", line 2170, in _BuildLoop
    body_result = body(*packed_vars_for_body)
  File "/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/ops/control_flow_ops.py", line 2705, in <lambda>
    body = lambda i, lv: (i + 1, orig_body(*lv))
  File "/content/AIDungeon/generator/gpt2/src/sample.py", line 89, in body
    next_outputs['presents'] if past is None else tf.concat([past, next_outputs['presents']], axis=-2),
  File "/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/util/dispatch.py", line 180, in wrapper
    return target(*args, **kwargs)
  File "/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/ops/array_ops.py", line 1420, in concat
    return gen_array_ops.concat_v2(values=values, axis=axis, name=name)
  File "/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/ops/gen_array_ops.py", line 1257, in concat_v2
    "ConcatV2", values=values, axis=axis, name=name)
  File "/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/framework/op_def_library.py", line 794, in _apply_op_helper
    op_def=op_def)
  File "/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/util/deprecation.py", line 507, in new_func
    return func(*args, **kwargs)
  File "/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/framework/ops.py", line 3357, in create_op
    attrs, op_def, compute_device)
  File "/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/framework/ops.py", line 3426, in _create_op_internal
    op_def=op_def)
  File "/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/framework/ops.py", line 1748, in __init__
    self._traceback = tf_stack.extract_stack()