Awni00's group workspace
Simple Abstractor (Pre-Trained; reshuffled objects)
What makes this group special?
Tags
train size = 3000; trial = 9
Notes
Author
awni00State
Finished
Start time
May 6th, 2023 9:18:55 PM
Runtime
1m
Tracked hours
53s
Run path
abstractor/object_argsort_autoregressive/xtijkge0
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 "train-size-=-3000;-trial-=-9" 5391abcf0d8b3c1b099038f043e26ee8e0139829
Command
evaluate_argsort_model_learning_curves.py --model simple-abstractor --pretraining_mode pretraining --init_trainable True --pretraining_task_type "reshuffled objects" --pretraining_task_data_path object_sorting_datasets/task2_reshuffled_object_sort_dataset.npy --eval_task_data_path object_sorting_datasets/task1_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 count | 36 |
| Logical CPU count | 36 |
| GPU count | 1 |
| GPU type | NVIDIA GeForce RTX 3090 |
W&B CLI Version
0.13.9
Config
Config parameters are your model's inputs. Learn more
- {} 3 keys▶
- "Simple Abstractor (Pre-Trained; reshuffled objects)"
- 3,000
- 9
Summary
Summary metrics are your model's outputs. Learn more
- {} 10 keys▶
- "table-file"
- 0.28097
- 167
- 0.0010000000474974513
- 1.00712788105011
- 0.6218666434288025
- 1.1770672798156738
- 0.5464299917221069
- 0.00075
- 0.5452366471290588
Artifact Inputs
This run consumed these artifacts as inputs. Learn more
Artifact Outputs
This run produced these artifacts as outputs. Total: 2. Learn more
Type
Name
Consumer count
Loading...