long_small_scale_iql_chaotic_lstm_multiseed-v0 | tlab Workspace

Howuhh's group workspace

Group: long_small_scale_iql_chaotic_lstm_multiseed-v0

1-1

of 1

Tags

Notes

Author

State

Failed

Start time

June 9th, 2023 5:48:40 PM

Sweep

yxrjm35b

Runtime

4d 7h 18m 41s

Tracked hours

4d 7h 15m 30s

Run path

tlab/NetHack/5fbf84oj

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

Python version

3.8.10

Git repository

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

Git state

git checkout -b "iql-mon-hum-neu-80bb81ee" c6d28bed00e5a35d8e55bacde8bf1e3d6a7c7f21

Command

algorithms/small_scale/iql_chaotic_lstm.py --character=mon-hum-neu --data_mode=memmap --group=long_small_scale_iql_chaotic_lstm_multiseed --train_seed=0 --update_steps=6600000 --version=0

System Hardware

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

W&B CLI Version

0.12.21

Group

long_small_scale_iql_chaotic_lstm_multiseed-v0

Config parameters are your model's inputs. Learn more

▶
Config parameters:{} 27 keys
- 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
- expectile_tau:
  0.8
- gamma:
  0.999
- group:
  "long_small_scale_iql_chaotic_lstm_multiseed"
- learning_rate:
  0.0003
- name:
  "iql-mon-hum-neu-80bb81ee"
- project:
  "NetHack"
- rnn_dropout:
  0
- rnn_hidden_dim:
  2,048
- rnn_layers:
  2
- seq_len:
  16
- tau:
  0.005
- temperature:
  1
- train_seed:
  0
- update_steps:
  6,600,000
- use_prev_action:
  true
- version:
  0
- weight_decay:
  0

Summary metrics are your model's outputs. Learn more

▶
Summary metrics:{} 23 keys
- actor_loss:
  1,093.4251708984375
- depth_max:
  1
- depth_mean:
  0.1
- depth_median:
  0
- depth_min:
  0
- depth_std:
  0.3
- loss:
  1,136.6102294921875
- next_v:
  368.25
- q_target:
  367.895751953125
- reward_max:
  24
- reward_mean:
  0.8
- reward_median:
  0
- reward_min:
  0
- reward_std:
  4
- td_loss:
  14.08319091796875
- times/backward_pass:
  0.014198240280151368
- times/batch_loading_cpu:
  0.05915331840515137
- times/batch_loading_gpu:
  0.059116798400878905
- times/evaluation_cpu:
  17.403823614120483
- times/evaluation_gpu:
  17.4036796875
- times/forward_pass:
  0.013088383674621585
- transitions:
  3,901,740,032
- value_loss:
  29.10191535949707

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

wandb-history

run-5fbf84oj-history:v4