Skip to main content
abstractor
Projects
object_argsort_autoregressive
Run groups
Pre-training Task (reshuffled attr); Relational Abstractor
Overview
Group
Workspace
Runs
Logs
Files
Artifacts

Awni00's group workspace

Pre-training Task (reshuffled attr); Relational Abstractor

What makes this group special?
Tags

pretraining_mode=pretraining

Notes
Author
awni00
State
Finished
Start time
May 3rd, 2023 7:32:15 AM
Runtime
40s
Tracked hours
31s
Run path
abstractor/object_argsort_autoregressive/lfqywkw8
OS
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 "pretraining_mode=pretraining" f397b06952b125c267dcbb3ea837aa1fcf1d84fd
Command
evaluate_argsort_model_learning_curves.py --model simple-abstractor --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 400 --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 count36
Logical CPU count 36
GPU count1
GPU typeNVIDIA GeForce RTX 2080 Ti
W&B CLI Version
0.13.9
Group
Pre-training Task (reshuffled attr); Relational Abstractor
Config

Config parameters are your model's inputs. Learn more

  • ▶
    {} 3 keys
    • "Pre-training Task (reshuffled attr); Simple Abstractor"
    • "pretraining"
    • 1,000
Summary

Summary metrics are your model's outputs. Learn more

  • ▶
    {} 10 keys
    • "table-file"
    • 0.997935
    • 251
    • 0.0010000000474974513
    • 0.05360994860529899
    • 0.9818999767303468
    • 0.0016461961204186082
    • 0.9998000264167786
    • 0.9964
    • 0.999642848968506
Artifact Inputs

This run consumed these artifacts as inputs. Learn more

1-1
of 1
Type
Name
Consumer count
job
job-https___github.com_jdlafferty_relational_experiments_object_argsort_autoregressive_evaluate_argsort_model_learning_curves.py:v10
1
Loading...
Artifact Outputs

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

1-2
of 2
Type
Name
Consumer count
run_table
run-lfqywkw8-acc_by_position_table:v0
0
wandb-history
run-lfqywkw8-history:v0
0
Loading...