r2s-cur-rl-smoke-532c2d4-c2adce86-47646604
failed —
Hypothesis
Smoke test: render-reward fine-tuning from the final model runs end to end (6 steps, 16 icons x 8 samples).
State transitions
- running2026-10-31T17:39:08Z
- failed2026-10-31T17:39:17ZOutOfMemoryError('CUDA out of memory. Tried to allocate 86.00 MiB. GPU 0 has a total capacity of 15.57 GiB of which 21.94 MiB is free. Including non-PyTorch memory, this process has 15.51 GiB memory in use. Of the allocated memory 14.95 GiB is allocated by PyTorch, and 282.79 MiB is reserved by PyTorch but unallocated. If reserved but unallocated memory is large try setting PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True to avoid fragmentation. See documentation for Memory Management (https://docs.pytorch.org/docs/stable/notes/cuda.html#optimizing-memory-usage-with-pytorch-cuda-alloc-conf)')
Run record
Verbatim from runs/r2s-cur-rl-smoke-532c2d4-c2adce86-47646604/run.yaml, the record committed before launch.
schema_version
2
run_id
r2s-cur-rl-smoke-532c2d4-c2adce86-47646604
state
failed
planned_at
2026-10-31T17:39:08Z
hypothesis
Smoke test: render-reward fine-tuning from the final model runs end to end (6 steps, 16 icons x 8 samples).
parent_run
r2s-cur-d02-s120k-seed2-53b3108-46294452-47646604
git_commit
532c2d4782562261abb60738a7997ab3d4bbcc86
dirty_patch_sha256
f883399197ca9882…config
configs/render2svg/cur-rl-smoke.yaml
config_sha256
c2adce86c7b51cdd…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
6
batch_size
16
learning_rate
2e-05
weight_decay
0.01
warmup_steps
2
seed
7001
eval_every
3
eval_icons
16
train_icons
None
evaluate_on_train
false
augment_variants
0
augment_seed
9001
augment_mirror
0.5
augment_max_shift
48
augment_colour
0.5
augment_online
false
compose_probability
0.0
compose_parts
4
augment_original
0.1
loader_workers
10
extra_training
degrade_probability
0.0
degrade_kinds
lineart, sloppy, flat
degrade_eval_seed
0
init_run
r2s-cur-d02-s120k-seed2-53b3108-46294452-47646604
init_sha256
38daeca4dd27fb4c…rl_samples
8
rl_temperature
1.0
rl_anchor
0.5
max_seconds
None
bf16
true
final_eval_icons
16
clip_icons
4
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
evaluation_inputs
clean renders
init
run
r2s-cur-d02-s120k-seed2-53b3108-46294452-47646604
checkpoint
/home/dev/.cache/mojidiff/runs/r2s-cur-d02-s120k-seed2-53b3108-46294452-47646604/best.pt
sha256
38daeca4dd27fb4c…step
64000
seed
7001
determinism
seeded; cuDNN and SDPA kernels not forced deterministic
model_parameters
9025826
command
.venv/bin/python -m mojidiff.learning.render2svg --config configs/render2svg/cur-rl-smoke.yaml
outputs
run_dir
runs/r2s-cur-rl-smoke-532c2d4-c2adce86-47646604
checkpoints
/home/dev/.cache/mojidiff/runs/r2s-cur-rl-smoke-532c2d4-c2adce86-47646604
notes
failed_at
2026-10-31T17:39:17Z
failure_reason
OutOfMemoryError('CUDA out of memory. Tried to allocate 86.00 MiB. GPU 0 has a total capacity of 15.57 GiB of which 21.94 MiB is free. Including non-PyTorch memory, this process has 15.51 GiB memory in use. Of the allocated memory 14.95 GiB is allocated by PyTorch, and 282.79 MiB is reserved by PyTorch but unallocated. If reserved but unallocated memory is large try setting PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True to avoid fragmentation. See documentation for Memory Management (https://docs.pytorch.org/docs/stable/notes/cuda.html#optimizing-memory-usage-with-pytorch-cuda-alloc-conf)')