highest-precision | gpt Overview – Weights & Biases

Skip to main content

Clashluke's group workspace

Group: highest-precision

1-4

of 4

Tags

Notes

Author

State

Crashed

Start time

October 29th, 2022 12:43:53 PM

Runtime

46m 37s

Tracked hours

44m 38s

Run path

homebrewnlp/gpt/xribrpxw6q6342pnj576uv9cnqklnmkl

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 "highest-precision-2" 0638a43b2a022fbd3b6cad5ada9c358166ce0bb0

Command

main.py

System Hardware

CPU count

48

W&B CLI Version

0.13.4

Group

highest-precision

Config parameters are your model's inputs. Learn more

▶
Config parameters:{} 13 keys
- add_depth:
  false
- ▶
  data:{} 8 keys
- depth:
  0
- ▶
  dims:{} 13 keys
- fail_on_missing_parameter:
  true
- global_prefix:
  ""
- ▶
  model:{} 10 keys
- name_cache_offsets:{} 0 keys
- ▶
  optimizer:{} 15 keys
- parameter_usages:{} 0 keys
- seed:
  0
- ▶
  training:{} 10 keys
- ▶
  wandb:{} 7 keys

Summary metrics are your model's outputs. Learn more

▶
Summary metrics:{} 15 keys
- Accuracy/Current:
  0.7597784996032715
- Accuracy/Median64:
  0.7594457864761353
- Accuracy/Median256:
  0.7591880559921265
- Accuracy/Median1024:
  0.759235143661499
- Loss/Current:
  0.7872974276542664
- Loss/Median64:
  0.7852031588554382
- Loss/Median256:
  0.7863572835922241
- Loss/Median1024:
  0.7861653566360474
- Optimizer/Beta1:
  0.1
- Optimizer/Beta2:
  0.01
- Optimizer/Learning Rate:
  0.008983365260064602
- Speed/Batches per Second:
  0.1004367480989338
- Speed/Parameters * Tokens per Day:
  3,685,315,759,425,335,808
- Speed/Tokens per Day:
  9,099,264,692.84437
- Speed/Tokens Seen:
  16,119,758,848

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

run-xribrpxw6q6342pnj576uv9cnqklnmkl-history:v0

Loading...