snli-distilbert-base-uncased-alum-3e-05 | vat Workspace – Weights & Biases

Skip to main content

Arampacha's group workspace

Group: snli-distilbert-base-uncased-alum-3e-05

eval/accuracy

-

-

-

-

1-4

of 4

Tags

Notes

Simple finetuning distilbert-base-uncased with RAdam lr=3e-05

Tags

alum

distilbert-base-uncased

radam

snli

spec-tok

Author

State

Finished

Start time

April 20th, 2021 5:39:49 PM

Runtime

48m 14s

Tracked hours

47m 33s

Run path

fastai_community/vat/onmeit4o

OS

Linux-5.4.0-66-generic-x86_64-with-glibc2.10

Python version

3.8.5

Git repository

git clone https://github.com/aikindergarten/vat

Git state

git checkout -b "snli-distilbert-base-uncased-alum" 0fcb29ba2615a8ed9454453029fc0575f83cf719

Command

vat/nbs/_alum_lm_finetuning_fastai_blurr_nli.ipynb

System Hardware

CPU count	64
GPU count	1
GPU type	Quadro RTX 5000

W&B CLI Version

0.10.27

Group

snli-distilbert-base-uncased-alum-3e-05

Config parameters are your model's inputs. Learn more

▶
Config parameters:{} 20 keys
- ▶
  ALUMCallback:{} 5 keys
- batch per epoch:
  8,583
- batch size:
  64
- dataset.tfms:
  "[Pipeline: get_x, Pipeline: ItemGetter -> Categorize -- {'vocab': [0, 1, 2], 'sort': True, 'add_na': False}]"
- device:
  "cuda"
- dls.after_batch:
  "Pipeline: HF_AfterBatchTransform"
- dls.after_item:
  "Pipeline: ToTensor"
- dls.before_batch:
  "Pipeline: HF_BeforeBatchTransform"
- frozen:
  false
- frozen idx:
  0
- HF_BaseModelCallback:
  true
- ▶
  Learner:{} 12 keys
- MixedPrecision:
  true
- model parameters:
  66,955,779
- n_inp:
  1
- ParamScheduler:
  true
- ProgressCallback:
  true
- ▶
  Recorder:{} 3 keys
  - add_time:
    true
  - train_metrics:
    false
  - valid_metrics:
    true
- TrainEvalCallback:
  true
- ▶
  WandbCallback:{} 9 keys

Summary metrics are your model's outputs. Learn more

▶
Summary metrics:{} 29 keys
- accuracy:
  0.8972769975662231
- beta_0:
  0
- beta_1:
  0
- beta_2:
  0
- beta_3:
  0
- epoch:
  5
- eps_0:
  0.00001
- eps_1:
  0.00001
- eps_2:
  0.00001
- eps_3:
  0.00001
- lr_0:
  0.00000000030007138259
- lr_1:
  0.00000000030007138259
- lr_2:
  0.00000000030007138259
- lr_3:
  0.00000000030007138259
- mom_0:
  0.9499999997620556
- mom_1:
  0.9499999997620556
- mom_2:
  0.9499999997620556
- mom_3:
  0.9499999997620556
- raw_loss:
  0.12275370955467224
- sqr_mom_0:
  0.99
- sqr_mom_1:
  0.99
- sqr_mom_2:
  0.99
- sqr_mom_3:
  0.99
- train_loss:
  0.15957936644554138
- valid_loss:
  0.3332129418849945
- wd_0:
  0
- wd_1:
  0
- wd_2:
  0
- wd_3:
  0

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

run-onmeit4o-history:v0

Loading...