r2s-cur-rl-lr5-s2-834abf2-f7b39568-47646604
cancelled —
Hypothesis
Render-reward fine-tuning of the final model for 800 steps at lr 5e-5 on the d02 recipe's online stream. Declared in state/CURRENT.md (2026-10-31 18:45): the RL arm's greedy float32 pixel error on the 339 validation renders beats the control's, seed-matched over seeds 7001-7004 with a bootstrap interval excluding zero, and the best RL run is more often recognisable than the final model on the same blind visual review.
State transitions
- running2026-10-31T18:01:57Z
- cancelled2026-10-31T18:59:47Zstopped_by_operator_at_step_250_of_800_before_its_time_cap; last_64_icon_eval_0.0648; no_final_evaluation_or_checkpoint_copied
Run record
Verbatim from runs/r2s-cur-rl-lr5-s2-834abf2-f7b39568-47646604/run.yaml, the record committed before launch.
schema_version
2
run_id
r2s-cur-rl-lr5-s2-834abf2-f7b39568-47646604
state
cancelled
planned_at
2026-10-31T18:01:57Z
hypothesis
Render-reward fine-tuning of the final model for 800 steps at lr 5e-5 on the d02 recipe's online stream. Declared in state/CURRENT.md (2026-10-31 18:45): the RL arm's greedy float32 pixel error on the 339 validation renders beats the control's, seed-matched over seeds 7001-7004 with a bootstrap interval excluding zero, and the best RL run is more often recognisable than the final model on the same blind visual review.
parent_run
r2s-cur-d02-s120k-seed2-53b3108-46294452-47646604
git_commit
834abf2b31b7a835a1e0e931363d5707e65526d6
dirty_patch_sha256
config
configs/render2svg/cur-rl-lr5-s2.yaml
config_sha256
f7b395687cca0b7c…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
800
batch_size
16
learning_rate
5e-05
weight_decay
0.01
warmup_steps
50
seed
7002
eval_every
50
eval_icons
64
train_icons
None
evaluate_on_train
false
augment_variants
0
augment_seed
9002
augment_mirror
0.5
augment_max_shift
48
augment_colour
0.1
augment_online
true
compose_probability
0.5
compose_parts
4
augment_original
0.1
loader_workers
16
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
6000
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
evaluation_inputs
clean renders
init
run
r2s-cur-d02-s120k-seed2-53b3108-46294452-47646604
checkpoint
/home/eai-jdkxz/eai-team11/mojidiff/cache/runs/r2s-cur-d02-s120k-seed2-53b3108-46294452-47646604/best.pt
sha256
38daeca4dd27fb4c…step
64000
seed
7002
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-lr5-s2.yaml
outputs
run_dir
runs/r2s-cur-rl-lr5-s2-834abf2-f7b39568-47646604
checkpoints
/home/eai-jdkxz/eai-team11/mojidiff/cache/runs/r2s-cur-rl-lr5-s2-834abf2-f7b39568-47646604
notes
cancelled_at
2026-10-31T18:59:47Z
cancel_reason
stopped_by_operator_at_step_250_of_800_before_its_time_cap; last_64_icon_eval_0.0648; no_final_evaluation_or_checkpoint_copied
slurm_job
14181