dal-nlp

Assenmacher-mat's group workspace

Group: distilbert_fulltraining_fnc1

1-5

of 5

Tags

Notes

Author

mwirth

State

Finished

Start time

February 19th, 2023 9:27:39 PM

Runtime

58m 28s

Tracked hours

58m 21s

Run path

dal-nlp/active-glae_old/kknv4l1d

Linux-4.15.0-202-generic-x86_64-with-glibc2.27

Python version

3.9.13

Command

/mnt/stud/home/mwirth/projekts/dal-toolbox/experiments/active_learning/al_txt.py model=distilbert dataset=fnc1 output_dir=/mnt/work/glae/glae-results/fnc1/distilbert/fulltraining/seed5 random_seed=5 al_strategy=fulltraining al_cycle.n_init=0 al_cycle.acq_size=0 al_cycle.n_acq=0 wandb.group=distilbert_fulltraining_fnc1

System Hardware

CPU count	48
Logical CPU count	96
GPU count	1
GPU type	Tesla V100-SXM2-32GB

W&B CLI Version

0.13.9

Group

distilbert_fulltraining_fnc1

Config parameters are your model's inputs. Learn more

▶
Config parameters:{} 13 keys
- ▶
  al_cycle:{} 4 keys
  - acq_size:
    0
  - cold_start:
    false
  - n_acq:
    0
  - n_init:
    0
- ▶
  al_strategy:{} 1 key
  - name:
    "fulltraining"
- check_freq_model:
  15
- ▶
  dataset:{} 5 keys
- dataset_path:
  "$HOME/.cache/huggingface/datasets"
- device:
  "cuda"
- ▶
  model:{} 5 keys
- output_dir:
  "/mnt/work/glae/glae-results/fnc1/distilbert/fulltraining/seed5"
- print_freq_eval:
  25
- print_freq_train:
  25
- random_seed:
  5
- val_batch_size:
  128
- ▶
  wandb:{} 5 keys

Summary metrics are your model's outputs. Learn more

▶
Summary metrics:{} 7 keys
- final_auc_acc:
  97.276
- final_auc_acc_blc:
  0.862
- final_auc_f1:
  0.836
- test_batch_acc_balanced_epoch:
  0.9223406078050428
- test_batch_acc_epoch:
  98.43937572892926
- test_batch_f1_epoch:
  0.8951558234774314
- test_loss_epoch:
  0.06260685175994507

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

wandb-history

run-kknv4l1d-history:v0