Awni00's group workspace
Pre-training Task (reshuffled objects); Abstractor
What makes this group special?
Tags
pretraining_mode=pretraining
Notes
Author
awni00State
Finished
Start time
May 27th, 2023 2:00:11 AM
Runtime
47s
Tracked hours
41s
Run path
abstractor/object_argsort_autoregressive/vj41paca
OS
Linux-4.18.0-425.13.1.el8_7.x86_64-x86_64-with-glibc2.28
Python version
3.10.8
Git repository
git clone https://github.com/jdlafferty/relational
Git state
git checkout -b "pretraining_mode=pretraining" b98437cbc7c2f1a78bfd13943d733bfd7fea87c5
Command
/diskarray/home/awni/projects/relational/experiments/object_argsort_autoregressive/evaluate_argsort_model_learning_curves.py --model abstractor --pretraining_mode pretraining --init_trainable True --pretraining_task_type "reshuffled objects" --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 500 --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 | 20 |
| Logical CPU count | 20 |
| GPU count | 1 |
| GPU type | NVIDIA GeForce RTX 4090 |
W&B CLI Version
0.15.3
Config
Config parameters are your model's inputs. Learn more
- {} 3 keys▶
- "Pre-training Task (reshuffled objects); Abstractor"
- "pretraining"
- 1,000
Summary
Summary metrics are your model's outputs. Learn more
- {} 10 keys▶
- "table-file"
- 0.99732
- 499
- 0.0010000000474974513
- 0.06894054263830185
- 0.977299988269806
- 0.009467425756156445
- 0.9987999796867372
- 0.98795
- 0.9987149834632874
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...