collingray

Collingray's group workspace

Group: multilayer_pythia_32x_v6

1-9

of 9

Tags

Notes

Author

collingray

State

Finished

Start time

May 10th, 2024 5:49:28 AM

Runtime

56m

Tracked hours

55m 57s

Run path

collingray/multilayer_sae/uf2hkn11

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_v6

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:
  0.0002
- lr_decay_pct:
  0.2
- lr_warmup_pct:
  0
- β1:
  0.9
- β2:
  0.999
- λ:
  0.05
- λ_warmup_pct:
  null

Summary metrics are your model's outputs. Learn more

▶
Summary metrics:{} 47 keys
- layer_0.avg_fvu:
  0.2771596312522888
- layer_0.avg_l0:
  362.51708984375
- ▶
  layer_0.feature_density.bins:[] 65 items
- ▶
  layer_0.feature_density.values:[] 64 items
- layer_0.l1:
  0.0771484375
- layer_0.loss:
  0.337890625
- layer_0.mse:
  0.333984375
- layer_1.avg_fvu:
  0.5769772529602051
- layer_1.avg_l0:
  323.64373779296875
- ▶
  layer_1.feature_density.bins:[] 65 items
- ▶
  layer_1.feature_density.values:[] 64 items
- layer_1.l1:
  0.1044921875
- layer_1.loss:
  0.69921875
- layer_1.mse:
  0.6953125
- layer_2.avg_fvu:
  0.2528323233127594
- layer_2.avg_l0:
  622.2101440429688
- ▶
  layer_2.feature_density.bins:[] 65 items
- ▶
  layer_2.feature_density.values:[] 64 items
- layer_2.l1:
  71.5
- layer_2.loss:
  3.875
- layer_2.mse:
  0.3046875
- layer_3.avg_fvu:
  0.39224448800086975
- layer_3.avg_l0:
  257.4353332519531
- ▶
  layer_3.feature_density.bins:[] 65 items
- ▶
  layer_3.feature_density.values:[] 64 items
- layer_3.l1:
  0.0556640625
- layer_3.loss:
  0.474609375
- layer_3.mse:
  0.47265625
- layer_4.avg_fvu:
  0.6677919030189514
- layer_4.avg_l0:
  151.2168426513672
- ▶
  layer_4.feature_density.bins:[] 65 items
- ▶
  layer_4.feature_density.values:[] 64 items
- layer_4.l1:
  42.75
- layer_4.loss:
  2.9375
- layer_4.mse:
  0.8046875
- layer_5.avg_fvu:
  0.47357064485549927
- layer_5.avg_l0:
  120.18358612060548
- ▶
  layer_5.feature_density.bins:[] 65 items
- ▶
  layer_5.feature_density.values:[] 64 items
- layer_5.l1:
  86
- layer_5.loss:
  4.875
- layer_5.mse:
  0.5703125
- lr:
  0.00000257024000000076
- total.avg_fvu:
  0.4715379476547241
- total.avg_l0:
  306.065673828125
- ▶
  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-uf2hkn11-history:v0

Collingray's group workspace

multilayer_pythia_32x_v6

3: λ5.0e-02_LR2.0e-04_β₁0.9_β₂0.999