JumpMLP_Observations

Batu's group workspace

Group: JumpMLP_Observations

1-20

of 21

Tags

Notes

Author

batu

State

Finished

Start time

December 16th, 2021 11:38:56 AM

Runtime

2m 48s

Tracked hours

2m 42s

Run path

batu/BehaviorCloning/kppa124o

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 "observation_specification{'vector'-slice(0,-19,-None)}" 6e4e3bb5250b23f7cc217320753f7a5bca39a6ab

Command

<python with no main file> --ip=127.0.0.1 --stdin=9008 --control=9006 --hb=9005 --Session.signature_scheme="hmac-sha256" --Session.key=b"3788daf4-3215-4e59-b4dd-8c9489ac9561" --shell=9007 --transport="tcp" --iopub=9009 --f=C:\Users\batua\AppData\Local\Temp\tmp-16980dcSENUV03Q17.json

System Hardware

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

W&B CLI Version

0.12.6

Group

JumpMLP_Observations

Config parameters are your model's inputs. Learn more

▶
Config parameters:{} 16 keys
- activation:
  "torch.nn.functional.relu"
- architecture:
  "BaselineNoGraph( (dropout): Dropout(p=0, inplace=False) (layers): ModuleList( (0): Linear(in_features=19, out_features=512, bias=True) (1): Linear(in_features=512, out_features=512, bias=True) (2): Linear(in_features=512, out_features=3, bias=True) ) (input_layer): Linear(in_features=19, out_features=512, bias=True) (hidden_layers): ModuleList( (0): Linear(in_features=512, out_features=512, bias=True) ) (output_layer): Linear(in_features=512, out_features=3, bias=True) )"
- batch_size:
  128
- dropout_percentage:
  0
- env_name:
  "Jump"
- h_feats:
  512
- input_dim:
  19
- l2_regularization:
  0
- learning_rate:
  0.001
- loss:
  "torch.nn.functional.mse_loss"
- max_epochs:
  50
- num_layers:
  3
- observation:
  "pos"
- ▶
  observation_specification:{} 1 key
  - ▶
    vector:{} 3 keys
    - slice_start:
      0
    - slice_step:
      null
    - slice_stop:
      19
- seed:
  2,106
- sweep:
  "InputSweep"

Summary metrics are your model's outputs. Learn more

▶
Summary metrics:{} 20 keys
- epoch:
  49
- ▶
  Fail Ending Position:{} 7 keys
- Mean of Gradients:
  0.00010685406596167012
- ▶
  Succes-Fail Starting Position:{} 7 keys
- Success Rate:
  0.62
- train_abs_error:
  0.17514070868492126
- train_loss_epoch:
  0.07913825660943985
- train_loss_step:
  0.07183842360973358
- trainer/global_step:
  8,799
- val_abs_error:
  0.33316442370414734
- val_loss_epoch:
  0.24756859242916107
- val_loss_step:
  0.23375990986824036
- val_mape_epoch:
  0.33011963963508606
- val_mape_jump_epoch:
  0.4207627177238464
- val_mape_jump_step:
  0.3651314973831177
- val_mape_step:
  0.2905857563018799
- val_mape_x_epoch:
  0.2992700934410095
- val_mape_x_step:
  0.2915428876876831
- val_mape_z_epoch:
  0.27032607793807983
- val_mape_z_step:
  0.21508283913135529

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

wandb-history

run-kppa124o-history:v0

Batu's group workspace

observation_specification:{'vector': slice(0, 19, None)}