JumpOverfit_Vector

Batu's group workspace

Group: JumpOverfit_Vector

1-8

of 8

Tags

Notes

Author

batu

State

Finished

Start time

December 3rd, 2021 3:18:10 PM

Runtime

46s

Tracked hours

43s

Run path

batu/BehaviorCloning/27id2ts7

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 "num_layers3_learning_rate0.001_h_feats512_activation<function-relu-at-0x000001C71913B678>_loss<function-mse_loss-at-0x000001C7191491F8>" 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

JumpOverfit_Vector

Config parameters are your model's inputs. Learn more

▶
Config parameters:{} 8 keys
- activation:
  "torch.nn.functional.relu"
- batch_size:
  128
- h_feats:
  512
- input_dim:
  505
- learning_rate:
  0.001
- loss:
  "torch.nn.functional.mse_loss"
- num_layers:
  3
- seed:
  140

Summary metrics are your model's outputs. Learn more

▶
Summary metrics:{} 7 keys
- epoch:
  11
- Mean of Gradients:
  0.00003676945925690234
- train_loss_epoch:
  0.00390692288056016
- train_loss_step:
  0.003472220851108432
- trainer/global_step:
  1,999
- val_loss_epoch:
  0.004001745022833347
- val_loss_step:
  0.003116063540801406

This run produced these artifacts as outputs. Total: 1. Learn more

wandb-history

run-27id2ts7-history:v0

Batu's group workspace

num_layers:3_learning_rate:0.001_h_feats:512_activation:<function relu at 0x000001C71913B678>_loss:<function mse_loss at 0x000001C7191491F8>