MojiDiff

← experiments

r2s-cur-d02-sh64-s7-d35d12b-1c5212d2-47646604

failed —

Hypothesis

With exact translations of up to 16 view units instead of 12 and everything else as dropout 0.2 at 60k steps, the model transcribes the 339 validation renders better than the dropout-0.2 run of the same seed. Judged over seeds 7001-7008: the mean seed-matched difference with a bootstrap interval over seeds excluding zero.

State transitions

  1. running2026-10-31T09:56:34Z
  2. failed2026-10-31T10:20:07ZRuntimeError('Caught RuntimeError in DataLoader worker process 10.\nOriginal Traceback (most recent call last):\n File "/home/eai-jdkxz/eai-team11/mojidiff/repo-d35d12b/.venv/lib/python3.12/site-packages/torch/utils/data/_utils/worker.py", line 375, in _worker_loop\n data = fetcher.fetch(index) # type: ignore[possibly-undefined]\n ^^^^^^^^^^^^^^^^^^^^\n File "/home/eai-jdkxz/eai-team11/mojidiff/repo-d35d12b/.venv/lib/python3.12/site-packages/torch/utils/data/_utils/fetch.py", line 45, in fetch\n return self.collate_fn(data)\n ^^^^^^^^^^^^^^^^^^^^^\n File "/home/eai-jdkxz/eai-team11/mojidiff/repo-d35d12b/.venv/lib/python3.12/site-packages/torch/utils/data/_utils/collate.py", line 401, in default_collate\n return collate(batch, collate_fn_map=default_collate_fn_map)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/home/eai-jdkxz/eai-team11/mojidiff/repo-d35d12b/.venv/lib/python3.12/site-packages/torch/utils/data/_utils/collate.py", line 215, in collate\n collate(samples, collate_fn_map=collate_fn_map)\n File "/home/eai-jdkxz/eai-team11/mojidiff/repo-d35d12b/.venv/lib/python3.12/site-packages/torch/utils/data/_utils/collate.py", line 155, in collate\n return collate_fn_map[elem_type](batch, collate_fn_map=collate_fn_map)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/home/eai-jdkxz/eai-team11/mojidiff/repo-d35d12b/.venv/lib/python3.12/site-packages/torch/utils/data/_utils/collate.py", line 273, in collate_tensor_fn\n storage = elem._typed_storage()._new_shared(numel, device=elem.device)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/home/eai-jdkxz/eai-team11/mojidiff/repo-d35d12b/.venv/lib/python3.12/site-packages/torch/storage.py", line 1220, in _new_shared\n untyped_storage = torch.UntypedStorage._new_shared(\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/home/eai-jdkxz/eai-team11/mojidiff/repo-d35d12b/.venv/lib/python3.12/site-packages/torch/storage.py", line 423, in _new_shared\n return cls._new_using_fd_cpu(size)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^\nRuntimeError: could not unlink the shared memory file /torch_262778_660356566_9855 : No such file or directory (2)\n')

Run record

Verbatim from runs/r2s-cur-d02-sh64-s7-d35d12b-1c5212d2-47646604/run.yaml, the record committed before launch.

schema_version
2
run_id
r2s-cur-d02-sh64-s7-d35d12b-1c5212d2-47646604
state
failed
planned_at
2026-10-31T09:56:34Z
hypothesis
With exact translations of up to 16 view units instead of 12 and everything else as dropout 0.2 at 60k steps, the model transcribes the 339 validation renders better than the dropout-0.2 run of the same seed. Judged over seeds 7001-7008: the mean seed-matched difference with a bootstrap interval over seeds excluding zero.
parent_run
r2s-cur-dropout02
git_commit
d35d12b35ce8019342e1cad4a9b543bffd86c1f5
dirty_patch_sha256
config
configs/render2svg/cur-d02-sh64-s7.yaml
config_sha256
1c5212d20f3e8295…
config_resolved
model
image_size
144
d_model
256
heads
8
encoder_layers
2
decoder_layers
6
feedforward
1024
dropout
0.2
metric
true
fourier
10
order
path
sources
0
training
steps
60000
batch_size
32
learning_rate
0.0005
weight_decay
0.01
warmup_steps
1000
seed
7007
eval_every
2000
eval_icons
64
train_icons
None
evaluate_on_train
false
augment_variants
0
augment_seed
9007
augment_mirror
0.5
augment_max_shift
64
augment_colour
0.1
augment_online
true
compose_probability
0.5
compose_parts
4
augment_original
0.1
loader_workers
16
extra_training
bf16
true
final_eval_icons
339
clip_icons
32
dataset
pilot_config
configs/learning/openmoji-g1-geometric-gate-v16.yaml
cache_sha256
476466042da98d72…
train_icons
2681
augmented_variants
0
extra_training
None
augmented_sha256
None
evaluated_on
primary/validation
seed
7007
determinism
seeded; cuDNN and SDPA kernels not forced deterministic
model_parameters
9025826
command
.venv/bin/python -m mojidiff.learning.render2svg --config configs/render2svg/cur-d02-sh64-s7.yaml
outputs
run_dir
runs/r2s-cur-d02-sh64-s7-d35d12b-1c5212d2-47646604
checkpoints
/home/eai-jdkxz/eai-team11/mojidiff/cache/runs/r2s-cur-d02-sh64-s7-d35d12b-1c5212d2-47646604
notes
failed_at
2026-10-31T10:20:07Z
failure_reason
RuntimeError('Caught RuntimeError in DataLoader worker process 10.\nOriginal Traceback (most recent call last):\n File "/home/eai-jdkxz/eai-team11/mojidiff/repo-d35d12b/.venv/lib/python3.12/site-packages/torch/utils/data/_utils/worker.py", line 375, in _worker_loop\n data = fetcher.fetch(index) # type: ignore[possibly-undefined]\n ^^^^^^^^^^^^^^^^^^^^\n File "/home/eai-jdkxz/eai-team11/mojidiff/repo-d35d12b/.venv/lib/python3.12/site-packages/torch/utils/data/_utils/fetch.py", line 45, in fetch\n return self.collate_fn(data)\n ^^^^^^^^^^^^^^^^^^^^^\n File "/home/eai-jdkxz/eai-team11/mojidiff/repo-d35d12b/.venv/lib/python3.12/site-packages/torch/utils/data/_utils/collate.py", line 401, in default_collate\n return collate(batch, collate_fn_map=default_collate_fn_map)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/home/eai-jdkxz/eai-team11/mojidiff/repo-d35d12b/.venv/lib/python3.12/site-packages/torch/utils/data/_utils/collate.py", line 215, in collate\n collate(samples, collate_fn_map=collate_fn_map)\n File "/home/eai-jdkxz/eai-team11/mojidiff/repo-d35d12b/.venv/lib/python3.12/site-packages/torch/utils/data/_utils/collate.py", line 155, in collate\n return collate_fn_map[elem_type](batch, collate_fn_map=collate_fn_map)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/home/eai-jdkxz/eai-team11/mojidiff/repo-d35d12b/.venv/lib/python3.12/site-packages/torch/utils/data/_utils/collate.py", line 273, in collate_tensor_fn\n storage = elem._typed_storage()._new_shared(numel, device=elem.device)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/home/eai-jdkxz/eai-team11/mojidiff/repo-d35d12b/.venv/lib/python3.12/site-packages/torch/storage.py", line 1220, in _new_shared\n untyped_storage = torch.UntypedStorage._new_shared(\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/home/eai-jdkxz/eai-team11/mojidiff/repo-d35d12b/.venv/lib/python3.12/site-packages/torch/storage.py", line 423, in _new_shared\n return cls._new_using_fd_cpu(size)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^\nRuntimeError: could not unlink the shared memory file /torch_262778_660356566_9855 : No such file or directory (2)\n')