table1_contrastive | issl Workspace

Yanndubs's group workspace

Group: table1_contrastive

1-5

of 5

Tags

Notes

Goal: compares contrastive methods (table 1 contrastive column).

Author

yanndubs

State

Finished

Start time

August 21st, 2022 9:29:36 PM

Runtime

14h 10m 30s

Tracked hours

14h 10m 25s

Run path

issl/issl_opensource/0_3930943

Linux-5.4.0-107-generic-x86_64-with-glibc2.31

Python version

3.10.4

Command

-m submitit.core._submit /juice/scr/yanndubs/Invariant-Self-Supervised-Learning/outputs/2022-08-21_14-28-02/.submitit/%j

System Hardware

CPU count	96
GPU count	1
GPU type	NVIDIA GeForce RTX 3090

W&B CLI Version

0.13.1

Group

table1_contrastive

Config parameters are your model's inputs. Learn more

▶
Config parameters:{} 267 keys
- callbacks/LearningRateMonitor/is_use:
  true
- callbacks/LearningRateMonitor/kwargs/logging_interval:
  "epoch"
- callbacks/RichModelSummary/is_use:
  true
- callbacks/RichModelSummary/kwargs/max_depth:
  4
- callbacks/RichProgressBar/is_use:
  false
- callbacks/RichProgressBar/kwargs/refresh_rate:
  50
- checkpoint_pred/is_load_last:
  true
- checkpoint_pred/kwargs/dirpath:
  "/juice/scr/yanndubs/Invariant-Self-Supervised-Learning/checkpoints/exp_table1_contrastive/datarepr_tinyimagenet/augrepr_data-standard/repr_cissl/dec_cissl/enc_resnet18/optrepr_Adam_lr2.0e-03_w1.0e-06/schedrepr_cosine/zdim_2048/bs_512/ep_1000/beta_1.0e-01/seed_1/addrepr_None/datapred_data_repr/pred_torch_logisticw1.0e-06/optpred_SGD_lr3.0e-01_w1.0e-06/schedpred_cosine_nowarm/eppred_100/bspred_512/addpred_None/jid_0_3930943"
- checkpoint_pred/kwargs/every_n_epochs:
  1
- checkpoint_pred/kwargs/mode:
  "min"
- checkpoint_pred/kwargs/monitor:
  "None"
- checkpoint_pred/kwargs/save_last:
  true
- checkpoint_pred/kwargs/save_top_k:
  1
- checkpoint_pred/kwargs/save_weights_only:
  false
- checkpoint_pred/kwargs/verbose:
  true
- checkpoint_pred/name:
  "last"
- checkpoint_repr/is_load_last:
  true
- checkpoint_repr/kwargs/dirpath:
  "/juice/scr/yanndubs/Invariant-Self-Supervised-Learning/checkpoints/exp_table1_contrastive/datarepr_tinyimagenet/augrepr_data-standard/repr_cissl/dec_cissl/enc_resnet18/optrepr_Adam_lr2.0e-03_w1.0e-06/schedrepr_cosine/zdim_2048/bs_512/ep_1000/beta_1.0e-01/seed_1/addrepr_None/datapred_data_repr/pred_torch_logisticw1.0e-06/optpred_SGD_lr3.0e-01_w1.0e-06/schedpred_cosine_nowarm/eppred_100/bspred_512/addpred_None/jid_0_3930943"
- checkpoint_repr/kwargs/every_n_epochs:
  1
- checkpoint_repr/kwargs/mode:
  "min"
- checkpoint_repr/kwargs/monitor:
  "None"
- checkpoint_repr/kwargs/save_last:
  true
- checkpoint_repr/kwargs/save_top_k:
  1
- checkpoint_repr/kwargs/save_weights_only:
  false
- checkpoint_repr/kwargs/verbose:
  true
- checkpoint_repr/name:
  "last"
- checkpoint/is_load_last:
  true
- checkpoint/kwargs/dirpath:
  "/juice/scr/yanndubs/Invariant-Self-Supervised-Learning/checkpoints/exp_table1_contrastive/datarepr_tinyimagenet/augrepr_data-standard/repr_cissl/dec_cissl/enc_resnet18/optrepr_Adam_lr2.0e-03_w1.0e-06/schedrepr_cosine/zdim_2048/bs_512/ep_1000/beta_1.0e-01/seed_1/addrepr_None/datapred_data_repr/pred_torch_logisticw1.0e-06/optpred_SGD_lr3.0e-01_w1.0e-06/schedpred_cosine_nowarm/eppred_100/bspred_512/addpred_None/jid_0_3930943"
- checkpoint/kwargs/every_n_epochs:
  1
- checkpoint/kwargs/mode:
  "min"
- checkpoint/kwargs/monitor:
  "None"
- checkpoint/kwargs/save_last:
  true
- checkpoint/kwargs/save_top_k:
  1
- checkpoint/kwargs/save_weights_only:
  false
- checkpoint/kwargs/verbose:
  true
- checkpoint/name:
  "last"
- data_pred/aux_shape:
  "???"
- data_pred/aux_target:
  "???"
- data_pred/dataset:
  "tinyimagenet"
- data_pred/is_copy_repr:
  true
- data_pred/kwargs/batch_size:
  512
- data_pred/kwargs/data_dir:
  "/juice/scr/yanndubs/Invariant-Self-Supervised-Learning/data"
- ▶
  data_pred/kwargs/dataset_kwargs/a_augmentations:[] 1 item
  - 0:
    "data-standard"
- data_pred/kwargs/dataset_kwargs/aux_target:
  "None"
- data_pred/kwargs/dataset_kwargs/is_normalize:
  true
- data_pred/kwargs/dataset_kwargs/seed:
  1
- update_trainer_pred/max_epochs:
  100
- update_trainer_repr/max_epochs:
  1,000
- user:
  "yanndubs"
- wandb_entity:
  "issl"

Summary metrics are your model's outputs. Learn more

▶
Summary metrics:{} 65 keys
- epoch:
  99
- lr_evaluator:
  0.000003
- lr_issl:
  0.00000001006998889785
- lr_predictor:
  0.00014803189028051998
- test/pred/torchlogisticw1e-4_datarepr/acc:
  0.4478999972343445
- test/pred/torchlogisticw1e-4_datarepr/err:
  0.5521000027656555
- test/pred/torchlogisticw1e-4_datarepr/loss:
  2.3899106979370117
- test/pred/torchlogisticw1e-5_datarepr/acc:
  0.4860999882221222
- test/pred/torchlogisticw1e-5_datarepr/err:
  0.5138999819755554
- test/pred/torchlogisticw1e-5_datarepr/loss:
  2.131173610687256
- test/pred/torchlogisticw1e-6_datarepr/acc:
  0.4869000017642975
- test/pred/torchlogisticw1e-6_datarepr/err:
  0.5131000280380249
- test/pred/torchlogisticw1e-6_datarepr/loss:
  2.113882303237915
- test/repr/tinyimagenet/cosine_neg:
  0.0006173462024889886
- test/repr/tinyimagenet/cosine_pos:
  0.7869250178337097
- test/repr/tinyimagenet/dist_to_etf:
  0.2137218713760376
- test/repr/tinyimagenet/eval_acc:
  0.43369999527931213
- test/repr/tinyimagenet/eval_err:
  0.5662999749183655
- test/repr/tinyimagenet/eval_loss:
  2.4042751789093018
- test/repr/tinyimagenet/hat_H_m:
  6.914267063140869
- test/repr/tinyimagenet/I_q_zm:
  6.105527877807617
- test/repr/tinyimagenet/loss:
  0.8087393045425415
- test/repr/tinyimagenet/n_negatives:
  1,010.9439697265624
- test/repr/tinyimagenet/temperature:
  0.07000000774860382
- train/pred/torchlogisticw1e-4_datarepr/acc:
  0.4312500059604645
- train/pred/torchlogisticw1e-4_datarepr/err:
  0.5687500238418579
- train/pred/torchlogisticw1e-4_datarepr/loss:
  2.288386821746826
- train/pred/torchlogisticw1e-5_datarepr/acc:
  0.59375
- train/pred/torchlogisticw1e-5_datarepr/err:
  0.40625
- train/pred/torchlogisticw1e-5_datarepr/loss:
  1.6436372995376587
- train/pred/torchlogisticw1e-6_datarepr/acc:
  0.625
- train/pred/torchlogisticw1e-6_datarepr/err:
  0.375
- train/pred/torchlogisticw1e-6_datarepr/loss:
  1.567849040031433
- train/repr/tinyimagenet/cosine_neg:
  -0.00444793701171875
- train/repr/tinyimagenet/cosine_pos:
  0.7197265625
- train/repr/tinyimagenet/dist_to_etf:
  0.276123046875
- train/repr/tinyimagenet/eval_acc:
  0.3812499940395355
- train/repr/tinyimagenet/eval_err:
  0.6187499761581421
- train/repr/tinyimagenet/eval_loss:
  2.643411636352539
- train/repr/tinyimagenet/hat_H_m:
  5.7683210372924805
- train/repr/tinyimagenet/I_q_zm:
  5.00069522857666
- train/repr/tinyimagenet/loss:
  0.7676257491111755
- train/repr/tinyimagenet/n_negatives:
  320
- train/repr/tinyimagenet/temperature:
  0.07000000029802322
- trainer/global_step:
  19,600
- val/pred/torchlogisticw1e-4_datarepr/acc:
  0.4478999972343445
- val/repr/tinyimagenet/I_q_zm:
  6.104569911956787
- val/repr/tinyimagenet/loss:
  0.8096976280212402
- val/repr/tinyimagenet/n_negatives:
  1,010.9439697265624
- val/repr/tinyimagenet/temperature:
  0.07000000774860382

This run produced these artifacts as outputs. Total: 3. Learn more

code

source-issl_opensource-None:v10

code

source-issl_opensource-None:v11

wandb-history

run-0_3930943-history:v0