rnn-shortctx-nonoise | gpt Overview – Weights & Biases

Skip to main content

Clashluke's group workspace

Group: rnn-shortctx-nonoise

1-1

of 1

Tags

Notes

Author

State

Crashed

Start time

May 7th, 2023 9:42:48 AM

Runtime

1h 2m 31s

Tracked hours

-

Run path

homebrewnlp/gpt/2uqb8eexmw5rpq59800iih9rven514os

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 "rnn-shortctx-nonoise-0" 9d35b446169f88be8ba3142b1f0d19d2e997a800

Command

main.py

System Hardware

CPU count	48
Logical CPU count	96

W&B CLI Version

0.15.2

Group

rnn-shortctx-nonoise

Config parameters are your model's inputs. Learn more

▶
Config parameters:{} 11 keys
- ▶
  data:{} 8 keys
- ▶
  dims:{} 9 keys
- fail_on_missing_parameter:
  true
- global_prefix:
  ""
- ▶
  model:{} 4 keys
  - autoregressive:
    true
  - computation_dtype:
    "bfloat16"
  - ▶
    norm:{} 1 key
    - eps:
      0.0000000000000001
  - storage_dtype:
    "float32"
- name_cache_offsets:{} 0 keys
- ▶
  optimizer:{} 11 keys
- parameter_usages:{} 0 keys
- seed:
  0
- ▶
  training:{} 10 keys
- ▶
  wandb:{} 6 keys

Summary metrics are your model's outputs. Learn more

▶
Summary metrics:{} 13 keys
- Accuracy/Current:
  0.1673583984375
- Accuracy/Median64:
  0.166107177734375
- Accuracy/Median256:
  0.0631103515625
- Accuracy/Median1024:
  0.04998779296875
- Loss/Current:
  3.5386788436797794
- Loss/Median64:
  3.5070617875524643
- Loss/Median256:
  3.6815127108729033
- Loss/Median1024:
  4.170044458160284
- Optimizer/Learning Rate:
  0.0004400118486955762
- Speed/Batches per Second:
  0.12751059714411556
- Speed/Parameters * Tokens per Day:
  141,636,181,468,688,512
- Speed/Tokens per Day:
  361,002,290.1596679
- Speed/Tokens Seen:
  14,811,136

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

run-2uqb8eexmw5rpq59800iih9rven514os-history:v0

Loading...