GraphNNSweep3 | BehaviorCloning Workspace

Batu's group workspace

Group: GraphNNSweep3

1-20

of 269

Tags

Notes

Author

batu

State

Finished

Start time

November 30th, 2021 4:56:15 PM

Runtime

2m 31s

Tracked hours

2m 28s

Run path

batu/BehaviorCloning/21fz2mpr

Windows-10-10.0.19041-SP0

Python version

3.7.10

Git repository

git clone https://github.com/batu/RLAgency.git

Git state

git checkout -b "learning_rate0.001_batch_size128_residualTrue_add_node_idTrue_activation<function-tanh-at-0x000001D45957E798>_hidden_dim16_activation_first_layerFalse" 6e4e3bb5250b23f7cc217320753f7a5bca39a6ab

Command

BehaviorCloning.ipynb

System Hardware

CPU count	16
GPU count	1
GPU type	NVIDIA GeForce RTX 3070 Laptop GPU

W&B CLI Version

0.12.6

Group

GraphNNSweep3

Config parameters are your model's inputs. Learn more

▶
Config parameters:{} 15 keys
- activation:
  "torch.nn.functional.tanh"
- activation_first_layer:
  false
- add_node_id:
  true
- aggregation_method:
  "node"
- batch_size:
  128
- edge_type:
  "goal_to_agent"
- hidden_dim:
  16
- input_dim:
  3
- learning_rate:
  0.001
- linear_input:
  true
- linear_output:
  true
- model_type:
  "__main__.GCNLayer"
- num_layers:
  3
- residual:
  true
- self_loop:
  true

Summary metrics are your model's outputs. Learn more

▶
Summary metrics:{} 7 keys
- epoch:
  2
- Mean of Gradients:
  0.004342876374721527
- train_loss_epoch:
  0.2033285051584244
- train_loss_step:
  0.16505186259746552
- trainer/global_step:
  499
- val_loss_epoch:
  0.17092102766036987
- val_loss_step:
  0.14663498103618622

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

code

source-21fz2mpr:v0

wandb-history

run-21fz2mpr-history:v0