collingray

Collingray's group workspace

Group: multilayer_pythia_32x_v5

1-4

of 4

Tags

Notes

Author

collingray

State

Failed

Start time

May 10th, 2024 5:34:15 AM

Runtime

5m 6s

Tracked hours

5m 3s

Run path

collingray/multilayer_sae/ya6wfpfg

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-6a90d68f-59e7-431c-b0b3-cba086160eb0.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_v5

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:
  0.0003
- lr_decay_pct:
  0.2
- lr_warmup_pct:
  0
- β1:
  0.9
- β2:
  0.999
- λ:
  1
- λ_warmup_pct:
  null

Summary metrics are your model's outputs. Learn more

▶
Summary metrics:{} 50 keys
- layer_0.avg_fvu:
  0.27132704854011536
- layer_0.avg_l0:
  375.0765686035156
- ▶
  layer_0.feature_density.bins:[] 65 items
- ▶
  layer_0.feature_density.values:[] 64 items
- layer_0.l1:
  0.26953125
- layer_0.loss:
  0.59765625
- layer_0.mse:
  0.328125
- layer_1.avg_fvu:
  0.5491142868995667
- layer_1.avg_l0:
  438.034912109375
- ▶
  layer_1.feature_density.bins:[] 65 items
- ▶
  layer_1.feature_density.values:[] 64 items
- layer_1.l1:
  0.1650390625
- layer_1.loss:
  0.828125
- layer_1.mse:
  0.6640625
- layer_2.avg_fvu:
  11.73166561126709
- layer_2.avg_l0:
  315.7430419921875
- ▶
  layer_2.feature_density.bins:[] 65 items
- ▶
  layer_2.feature_density.values:[] 64 items
- layer_2.l1:
  0.12451171875
- layer_2.loss:
  14.3125
- layer_2.mse:
  14.1875
- layer_3.avg_fvu:
  0.3779198229312897
- layer_3.avg_l0:
  431.5701904296875
- ▶
  layer_3.feature_density.bins:[] 65 items
- ▶
  layer_3.feature_density.values:[] 64 items
- layer_3.l1:
  0.267578125
- layer_3.loss:
  0.7265625
- layer_3.mse:
  0.45703125
- layer_4.avg_fvu:
  5.762470245361328
- layer_4.avg_l0:
  220.39356994628903
- ▶
  layer_4.feature_density.bins:[] 65 items
- ▶
  layer_4.feature_density.values:[] 64 items
- layer_4.l1:
  0.08935546875
- layer_4.loss:
  7.0625
- layer_4.mse:
  6.96875
- layer_5.avg_fvu:
  15.71112823486328
- layer_5.avg_l0:
  10.759926795959473
- ▶
  layer_5.feature_density.bins:[] 65 items
- ▶
  layer_5.feature_density.values:[] 64 items
- layer_5.l1:
  0.0013885498046875
- layer_5.loss:
  19
- layer_5.mse:
  19
- lr:
  0.00003
- total.avg_fvu:
  5.733937740325928
- total.avg_l0:
  298.59637451171875
- ▶
  total.feature_density.bins:[] 65 items
- ▶
  total.feature_density.values:[] 64 items
- total.l1:
  0.1533203125
- total.loss:
  7.09375
- total.mse:
  6.9375

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

wandb-history

run-ya6wfpfg-history:v0

Collingray's group workspace

multilayer_pythia_32x_v5

4: λ1.0e+00_LR3.0e-04_β₁0.9_β₂0.999