sam_dfki

Arne's group workspace

Group: <null>

1-1

of 1

Tags

Notes

https://wandb.ai/sam_dfki/uncased_best_adu/groups/unknown

Author

bverma

State

Finished

Start time

May 6th, 2022 4:58:45 PM

Runtime

5h 59m 49s

Tracked hours

5h 59m 45s

Run path

sam_dfki/best_adu_uncased/32e4gdy8

Linux-5.4.0-109-generic-x86_64-with-glibc2.10

Python version

3.8.10

Git repository

git clone git@github.com:ArneBinder/SAM.git

Git state

git checkout -b "faithful-glitter-1" b761d672e4cc2773e6cb2223c6e2e12bc8b43370

Command

training_scripts/cross_validation/train-cross-validation.py train -f allennlp_configs/adu_best_uncased.jsonnet

System Hardware

CPU count	96
GPU count	1
GPU type	NVIDIA RTX A6000

W&B CLI Version

0.12.0

Config parameters are your model's inputs. Learn more

No config parameters were saved for this run.

Check the configuration documentation for more information.

Summary metrics are your model's outputs. Learn more

▶
Summary metrics:{} 39 keys
- best_epoch_mean:
  19.6
- best_epoch_median:
  21
- best_epoch_std:
  4.979959839195493
- best_validation_loss_mean:
  1,028.3072421482632
- best_validation_loss_median:
  923.9118957519532
- best_validation_loss_std:
  210.55941178761657
- best_validation_span/overall/f1_mean:
  0.5437481113406147
- best_validation_span/overall/f1_median:
  0.5533543448896397
- best_validation_span/overall/f1_std:
  0.028676950611058735
- best_validation_span/overall/precision_mean:
  0.5175176566359864
- best_validation_span/overall/precision_median:
  0.52
- best_validation_span/overall/precision_std:
  0.016104521799069103
- best_validation_span/overall/recall_mean:
  0.5737997750994366
- best_validation_span/overall/recall_median:
  0.5990196078431372
- best_validation_span/overall/recall_std:
  0.046977097594261094
- best_validation_token/accuracy_mean:
  0.7827581681373791
- best_validation_token/accuracy_median:
  0.7835732185311315
- best_validation_token/accuracy_std:
  0.014160418989535168
- best_validation_token/accuracy3_mean:
  0.7880269872421503
- best_validation_token/accuracy3_median:
  0.7886332969221872
- best_validation_token/accuracy3_std:
  0.0147012437172554
- best_validation_token/overall-macro/fscore_mean:
  0.535315990447998
- best_validation_token/overall-macro/fscore_median:
  0.5325292944908142
- best_validation_token/overall-macro/fscore_std:
  0.00963758396909164
- best_validation_token/overall-macro/precision_mean:
  0.5395843744277954
- best_validation_token/overall-macro/precision_median:
  0.5503997206687927
- best_validation_token/overall-macro/precision_std:
  0.02902108861219871
- best_validation_token/overall-macro/recall_mean:
  0.5605273127555848
- best_validation_token/overall-macro/recall_median:
  0.5567867755889893
- best_validation_token/overall-macro/recall_std:
  0.0271935971240914
- best_validation_token/overall-micro/fscore_mean:
  0.6548072457313537
- best_validation_token/overall-micro/fscore_median:
  0.6608368158340454
- best_validation_token/overall-micro/fscore_std:
  0.029730200048482803
- best_validation_token/overall-micro/precision_mean:
  0.6206274032592773
- best_validation_token/overall-micro/precision_median:
  0.6336597800254822
- best_validation_token/overall-micro/precision_std:
  0.04434223864507581
- best_validation_token/overall-micro/recall_mean:
  0.6943212151527405
- best_validation_token/overall-micro/recall_median:
  0.6997272968292236
- best_validation_token/overall-micro/recall_std:
  0.02164145419986779

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

wandb-history

run-32e4gdy8-history:v0