small_scale_cql_chaotic_lstm_sweep-v1 | tlab Workspace

Howuhh's group workspace

Group: small_scale_cql_chaotic_lstm_sweep-v1

1-8

of 8

Tags

Notes

Author

howuhh

State

Finished

Start time

May 27th, 2023 3:52:51 AM

Sweep

xbu4m2bb

Runtime

6h 56m 8s

Tracked hours

6h 55m 58s

Run path

tlab/NetHack/pfbzoo55

Linux-5.4.0-146-generic-x86_64-with-glibc2.29

Python version

3.8.10

Git repository

git clone git@github.com:tinkoff-ai/katakomba.git

Git state

git checkout -b "cql-mon-hum-neu-504c65d4" 2bac99f941f8ffcbb7d2b4d878d22cacff02aca5

Command

algorithms/small_scale/cql_chaotic_lstm.py --alpha=1 --character=mon-hum-neu --data_mode=memmap --group=small_scale_cql_chaotic_lstm_sweep --train_seed=2 --update_steps=250000 --version=1

System Hardware

CPU count	128
GPU count	1
GPU type	NVIDIA A100-PCIE-40GB

W&B CLI Version

0.12.21

Group

small_scale_cql_chaotic_lstm_sweep-v1

Config parameters are your model's inputs. Learn more

▶
Config parameters:{} 26 keys
- alpha:
  1
- batch_size:
  64
- character:
  "mon-hum-neu"
- checkpoints_path:
  null
- clip_grad_norm:
  null
- clip_range:
  10
- data_mode:
  "memmap"
- eval_episodes:
  50
- eval_every:
  10,000
- eval_processes:
  14
- eval_seed:
  50
- gamma:
  0.999
- group:
  "small_scale_cql_chaotic_lstm_sweep"
- learning_rate:
  0.0003
- name:
  "cql-mon-hum-neu-504c65d4"
- project:
  "NetHack"
- rnn_dropout:
  0
- rnn_hidden_dim:
  2,048
- rnn_layers:
  2
- seq_len:
  16
- tau:
  0.005
- train_seed:
  2
- update_steps:
  250,000
- use_prev_action:
  true
- version:
  1
- weight_decay:
  0

Summary metrics are your model's outputs. Learn more

▶
Summary metrics:{} 21 keys
- cql_loss:
  2.2503175735473633
- depth_max:
  0
- depth_mean:
  0
- depth_median:
  0
- depth_min:
  0
- depth_std:
  0
- loss:
  16.566600799560547
- q_target:
  937.635009765625
- reward_max:
  24
- reward_mean:
  1.18
- reward_median:
  0
- reward_min:
  0
- reward_std:
  4.731553656041532
- td_loss:
  14.316282272338867
- times/backward_pass:
  0.01636265563964844
- times/batch_loading_cpu:
  0.07824206352233887
- times/batch_loading_gpu:
  0.07819363403320312
- times/evaluation_cpu:
  17.300806522369385
- times/evaluation_gpu:
  17.30063671875
- times/forward_pass:
  0.011005375862121582
- transitions:
  256,000,000

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

wandb-history

run-pfbzoo55-history:v0