Job instance 270580

Stderr output

<core_client_version>7.24.1</core_client_version>
<![CDATA[
<stderr_txt>
14:40:01 (13972): wrapper (7.7.26016): starting
14:40:01 (13972): wrapper: running ../../projects/axiom.heliex.net/axiom_worker_2.17_windows_x86_64.exe (wu.json result.json)
[CPU] Using NumPy
[Worker] Saved 5 gradient files to contribute folder (gradient sharing)
INFO: Downloading model: https://axiom.heliex.net/pyhelix/model/expert_184_v2.0.bin
INFO: Downloaded and cached model: expert_184_v2.0.bin (42580994 params)
[Worker] FATAL ERROR: MemoryError: Unable to allocate 2.25 MiB for an array with shape (768, 768) and data type float32
Traceback (most recent call last):
  File "worker_boinc_app.py", line 1678, in main
  File "worker_boinc_app.py", line 1182, in __init__
  File "simple_ml.py", line 1153, in __init__
    self.expert = SimpleTransformer(
                  ^^^^^^^^^^^^^^^^^^
  File "simple_ml.py", line 372, in __init__
    self._init_weights()
  File "simple_ml.py", line 397, in _init_weights
    'Wq': np.random.randn(d, d).astype(np.float32) * scale_proj,
          ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
numpy._core._exceptions._ArrayMemoryError: Unable to allocate 2.25 MiB for an array with shape (768, 768) and data type float32

14:40:28 (13972): axiom_worker_2.17_windows_x86_64.exe exited; CPU time 8.406250
14:40:28 (13972): called boinc_finish(0)

</stderr_txt>
]]>