collingray

Collingray's group workspace

Group: multilayer_pythia_32x_v7

1-3

of 3

Tags

Notes

Author

collingray

State

Finished

Start time

May 10th, 2024 7:18:20 AM

Runtime

26m 35s

Tracked hours

26m 28s

Run path

collingray/multilayer_sae/wab12cya

Linux-6.7.8-arch1-1-x86_64-with-glibc2.39

Python version

3.11.4

Command

<python with no main file> -f /home/collin/.local/share/jupyter/runtime/kernel-765cd774-2848-45c7-9760-7a09bdd1a6af.json

System Hardware

CPU count	6
Logical CPU count	12
GPU count	1
GPU type	NVIDIA GeForce RTX 4090

W&B CLI Version

0.16.1

Group

multilayer_pythia_32x_v7

Config parameters are your model's inputs. Learn more

▶
Config parameters:{} 12 keys
- act_renorm_scale:
  1
- act_renorm_type:
  "none"
- decoder_scale:
  true
- input_scale:
  false
- latent_p:
  1
- lr:
  0.0004
- lr_decay_pct:
  0.3
- lr_warmup_pct:
  0.1
- β1:
  0.9
- β2:
  0.999
- λ:
  0.01
- λ_warmup_pct:
  null

Summary metrics are your model's outputs. Learn more

▶
Summary metrics:{} 47 keys
- layer_0.avg_fvu:
  0.024912260472774506
- layer_0.avg_l0:
  395.6185607910156
- ▶
  layer_0.feature_density.bins:[] 65 items
- ▶
  layer_0.feature_density.values:[] 64 items
- layer_0.l1:
  9.0625
- layer_0.loss:
  0.12109375
- layer_0.mse:
  0.030029296875
- layer_1.avg_fvu:
  0.01630585640668869
- layer_1.avg_l0:
  306.1298828125
- ▶
  layer_1.feature_density.bins:[] 65 items
- ▶
  layer_1.feature_density.values:[] 64 items
- layer_1.l1:
  14.125
- layer_1.loss:
  0.1611328125
- layer_1.mse:
  0.0196533203125
- layer_2.avg_fvu:
  0.01711357571184635
- layer_2.avg_l0:
  1,040.7322998046875
- ▶
  layer_2.feature_density.bins:[] 65 items
- ▶
  layer_2.feature_density.values:[] 64 items
- layer_2.l1:
  72
- layer_2.loss:
  0.73828125
- layer_2.mse:
  0.0206298828125
- layer_3.avg_fvu:
  0.03036865033209324
- layer_3.avg_l0:
  472.8605041503906
- ▶
  layer_3.feature_density.bins:[] 65 items
- ▶
  layer_3.feature_density.values:[] 64 items
- layer_3.l1:
  11.5
- layer_3.loss:
  0.15234375
- layer_3.mse:
  0.03662109375
- layer_4.avg_fvu:
  0.03724897280335426
- layer_4.avg_l0:
  617.4312133789062
- ▶
  layer_4.feature_density.bins:[] 65 items
- ▶
  layer_4.feature_density.values:[] 64 items
- layer_4.l1:
  51.75
- layer_4.loss:
  0.5625
- layer_4.mse:
  0.044921875
- layer_5.avg_fvu:
  0.04817138984799385
- layer_5.avg_l0:
  348.14892578125
- ▶
  layer_5.feature_density.bins:[] 65 items
- ▶
  layer_5.feature_density.values:[] 64 items
- layer_5.l1:
  93
- layer_5.loss:
  0.98828125
- layer_5.mse:
  0.05810546875
- lr:
  0.00000476031999999903
- total.avg_fvu:
  0.02013052999973297
- total.avg_l0:
  530.1619262695312
- ▶
  total.feature_density.bins:[] 65 items
- ▶
  total.feature_density.values:[] 64 items

This run produced these artifacts as outputs. Total: 1. Learn more

wandb-history

run-wab12cya-history:v0

Collingray's group workspace

multilayer_pythia_32x_v7

1: λ1.0e-02_LR4.0e-04_β₁0.9_β₂0.999