Jump_Fixed

Batu's group workspace

Group: Jump_Fixed

1-20

of 261

Tags

Notes

Author

batu

State

Finished

Start time

December 4th, 2021 6:33:03 AM

Runtime

3m 36s

Tracked hours

3m 34s

Run path

batu/BehaviorCloning/ncxmjmog

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_layers2_learning_rate0.0001_h_feats16_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

Jump_Fixed

Config parameters are your model's inputs. Learn more

▶
Config parameters:{} 8 keys
- activation:
  "torch.nn.functional.relu"
- batch_size:
  128
- h_feats:
  16
- input_dim:
  505
- learning_rate:
  0.0001
- loss:
  "torch.nn.functional.mse_loss"
- num_layers:
  2
- seed:
  2,727

Summary metrics are your model's outputs. Learn more

▶
Summary metrics:{} 8 keys
- epoch:
  99
- Mean of Gradients:
  0.0005261005135253072
- Success Rate:
  0
- train_loss_epoch:
  0.006377874873578548
- train_loss_step:
  0.005414433777332306
- trainer/global_step:
  17,599
- val_loss_epoch:
  0.005914035253226757
- val_loss_step:
  0.004710125736892223

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

wandb-history

run-ncxmjmog-history:v0

Batu's group workspace

num_layers:2_learning_rate:0.0001_h_feats:16_activation:<function relu at 0x000001C71913B678>_loss:<function mse_loss at 0x000001C7191491F8>