small_scale_awac_chaotic_lstm_multiseed-v0 | tlab Overview

Howuhh's group workspace

Group: small_scale_awac_chaotic_lstm_multiseed-v0

114

1-1

of 1

Tags

Notes

Author

howuhh

State

Finished

Start time

June 4th, 2023 3:29:55 PM

Sweep

ssvzsurc

Runtime

16h 39m 48s

Tracked hours

16h 39m 10s

Run path

tlab/NetHack/5fxaj9n3

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 "awac-kni-hum-law-8b7dca62" 16ccfc3af2d42d7b145cb94feeaacb039d3a669b

Command

algorithms/small_scale/awac_chaotic_lstm.py --character=kni-hum-law --data_mode=memmap --group=small_scale_awac_chaotic_lstm_multiseed --train_seed=1 --version=0

System Hardware

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

W&B CLI Version

0.12.21

Group

small_scale_awac_chaotic_lstm_multiseed-v0

Config parameters are your model's inputs. Learn more

▶
Config parameters:{} 26 keys
- batch_size:
  64
- character:
  "kni-hum-law"
- 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_awac_chaotic_lstm_multiseed"
- learning_rate:
  0.0003
- name:
  "awac-kni-hum-law-8b7dca62"
- project:
  "NetHack"
- rnn_dropout:
  0
- rnn_hidden_dim:
  2,048
- rnn_layers:
  2
- seq_len:
  16
- tau:
  0.005
- temperature:
  1
- train_seed:
  1
- update_steps:
  500,000
- use_prev_action:
  true
- version:
  0
- weight_decay:
  0

Summary metrics are your model's outputs. Learn more

▶
Summary metrics:{} 21 keys
- actor_loss:
  0.30627840757369995
- depth_max:
  0
- depth_mean:
  0
- depth_median:
  0
- depth_min:
  0
- depth_std:
  0
- loss:
  0.30727338790893555
- q_target:
  0.370849609375
- reward_max:
  1,719
- reward_mean:
  487.52
- reward_median:
  359
- reward_min:
  28
- reward_std:
  371.3345790523688
- td_loss:
  0.000994967296719551
- times/backward_pass:
  0.017688480377197266
- times/batch_loading_cpu:
  0.10955500602722168
- times/batch_loading_gpu:
  0.10952124786376952
- times/evaluation_cpu:
  79.45491361618042
- times/evaluation_gpu:
  79.4546796875
- times/forward_pass:
  0.013456000328063964
- transitions:
  512,000,000

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

wandb-history

run-5fxaj9n3-history:v0