more-norm | homebrewnlp Overview – Weights & Biases

Skip to main content

Clashluke's group workspace

Group: more-norm

1-3

of 3

Tags

Notes

Author

State

Crashed

Start time

October 16th, 2022 6:59:42 PM

Runtime

12h 26m 49s

Tracked hours

12h 25m 30s

Run path

homebrewnlp/gpt/m96hu7bv0520ookdaulmhjhw6s1i9p94

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 "more-norm-1" ba7ce319ce724c8384d6c77ca8c6997b53a34e21

Command

main.py

System Hardware

CPU count

48

W&B CLI Version

0.13.4

Group

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:
  0.7438337802886963
- Accuracy/Median64:
  0.7440400123596191
- Accuracy/Median256:
  0.7443052530288696
- Accuracy/Median1024:
  0.7431126832962036
- Loss/Current:
  0.8397631645202637
- Loss/Median64:
  0.8389042615890503
- Loss/Median256:
  0.8381509780883789
- Loss/Median1024:
  0.842053234577179
- Optimizer/Beta1:
  0.1
- Optimizer/Beta2:
  0.01
- Optimizer/Learning Rate:
  0.009214837104082108
- Speed/Batches per Second:
  0.09051756139120136
- Speed/Parameters * Tokens per Day:
  3,322,712,397,085,444,608
- Speed/Tokens per Day:
  8,200,616,467.968608
- Speed/Tokens Seen:
  12,294,553,600

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

run-m96hu7bv0520ookdaulmhjhw6s1i9p94-history:v0

Loading...