abstractor

Awni00's group workspace

Group: Transformer (Pre-Trained; reshuffled attr)

1-20

of 300

Tags

Notes

Author

awni00

State

Finished

Start time

April 30th, 2023 2:56:40 AM

Runtime

5m 1s

Tracked hours

4m 52s

Run path

abstractor/object_argsort_autoregressive/9vssnkw5

Linux-3.10.0-1160.80.1.el7.x86_64-x86_64-with-glibc2.10

Python version

3.8.16

Git repository

git clone https://github.com/jdlafferty/relational

Git state

git checkout -b "train-size-=-3000;-trial-=-9" 753e3703eaa4d9005dad1d175c5d58791276f3b4

Command

evaluate_argsort_model_learning_curves.py --model transformer --pretraining_mode pretraining --init_trainable True --pretraining_task_type "reshuffled attr" --pretraining_task_data_path object_sorting_datasets/product_structure_reshuffled_object_sort_dataset.npy --eval_task_data_path object_sorting_datasets/product_structure_object_sort_dataset.npy --n_epochs 200 --early_stopping True --min_train_size 100 --max_train_size 3000 --train_size_step 100 --num_trials 10 --start_trial 0 --pretraining_train_size 1000 --wandb_project_name object_argsort_autoregressive

System Hardware

CPU count	36
Logical CPU count	36
GPU count	1
GPU type	NVIDIA GeForce RTX 3090

W&B CLI Version

0.13.9

Group

Transformer (Pre-Trained; reshuffled attr)

Config parameters are your model's inputs. Learn more

▶
Config parameters:{} 3 keys
- group:
  "Transformer (Pre-Trained; reshuffled attr)"
- train size:
  3,000
- trial:
  9

Summary metrics are your model's outputs. Learn more

▶
Summary metrics:{} 10 keys
- acc_by_position_table:
  "table-file"
- elementwise_accuracy:
  0.99974
- epoch/epoch:
  129
- epoch/learning_rate:
  0.0010000000474974513
- epoch/loss:
  0.02696329541504383
- epoch/teacher_forcing_accuracy:
  0.9919333457946776
- epoch/val_loss:
  0.0005985797033645213
- epoch/val_teacher_forcing_accuracy:
  0.9998800158500672
- full_sequence_accuracy:
  0.99905
- teacher_forcing_accuracy:
  0.9998966455459596

This run consumed these artifacts as inputs. Learn more

job

job-https___github.com_jdlafferty_relational_experiments_object_argsort_autoregressive_evaluate_argsort_model_learning_curves.py:v8

297

This run produced these artifacts as outputs. Total: 2. Learn more

run_table

run-9vssnkw5-acc_by_position_table:v0

wandb-history

run-9vssnkw5-history:v0

Awni00's group workspace

Transformer (Pre-Trained; reshuffled attr)

train size = 3000; trial = 9