tied-moe-modulo | gpt Overview – Weights & Biases

Skip to main content

Clashluke's group workspace

Group: tied-moe-modulo

1-13

of 13

Tags

Notes

Author

State

Crashed

Start time

October 14th, 2022 8:24:19 PM

Runtime

1d 1h 11m 15s

Tracked hours

22h 27m

Run path

homebrewnlp/gpt/4qmbn7d8rcvggn0n49p6nekeecvy0qeo

OS

Linux-5.4.0-1043-gcp-x86_64-with-glibc2.29

Python version

3.8.5

Git repository

git clone https://github.com/HomebrewNLP/HomebrewNLP-Jax

Git state

git checkout -b "tied-moe-modulo-11" 1ffcf5132b7f202b9977ceb4c0e001d86ca15f5f

Command

main.py

System Hardware

CPU count

48

W&B CLI Version

0.13.4

Group

tied-moe-modulo

Config parameters are your model's inputs. Learn more

▶
Config parameters:{} 9 keys
- add_depth:
  false
- ▶
  data:{} 8 keys
- ▶
  dims:{} 12 keys
- global_prefix:
  ""
- ▶
  model:{} 9 keys
- ▶
  optimizer:{} 15 keys
- seed:
  0
- ▶
  training:{} 10 keys
- ▶
  wandb:{} 7 keys

Summary metrics are your model's outputs. Learn more

▶
Summary metrics:{} 15 keys
- Accuracy/Current:
  0.7860369682312012
- Accuracy/Median64:
  0.7892330884933472
- Accuracy/Median256:
  0.7888813018798828
- Accuracy/Median1024:
  0.7889246940612793
- Loss/Current:
  0.6941242218017578
- Loss/Median64:
  0.6836007833480835
- Loss/Median256:
  0.6838908195495605
- Loss/Median1024:
  0.6832436919212341
- Optimizer/Beta1:
  0.1
- Optimizer/Beta2:
  0.01
- Optimizer/Learning Rate:
  0.005122804082930088
- Speed/Batches per Second:
  0.09657169028425924
- Speed/Parameters * Tokens per Day:
  3,543,513,489,805,536,768
- Speed/Tokens per Day:
  8,749,102,179.87424
- Speed/Tokens Seen:
  100,572,069,888

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

run-4qmbn7d8rcvggn0n49p6nekeecvy0qeo-history:v0

Loading...