state-machine

State-machine's group workspace

Group: xland-multi-task-test-v0

1-79

of 79

Tags

Notes

Author

state-machine

State

Finished

Job

job-git_github.com_Howuhh_xland-minigrid-datasets.git_src_xminigrid_datasets_collection_train.py:v127

Start time

April 25th, 2024 8:07:31 AM

Runtime

5m 44s

Tracked hours

5m 39s

Run path

state-machine/xminigrid/6544651

Linux-5.4.0-176-generic-x86_64-with-glibc2.35

Python version

3.10.12

Git repository

git clone git@github.com:Howuhh/xland-minigrid-datasets.git

Git state

git checkout -b "ppo-rnn-multi-task-trivial" 5f9678e60b6bbf227b76ab940de3b6f771c03ad6

Command

/workspace/xminigrid-datasets/src/xminigrid_datasets/collection/train.py --group=xland-multi-task-test-v0 --name=ppo-rnn-multi-task-trivial --env_id=XLand-MiniGrid-R1-9x9 --benchmark_id=trivial-1m --pretrain_multitask=False --ruleset_id=0 --total_timesteps=500_000_000 --seed=0 --num_envs=8192 --num_steps=512 --num_minibatches=8 --gae_lambda=0.999 --gamma=0.999 --context_hidden_dim=256 --context_dropout=0.0 --head_hidden_dim=256 --rnn_hidden_dim=256 --lr=0.0001 --ent_coef=0.001 --use_bf16=True

System Hardware

CPU count	64
Logical CPU count	128
GPU count	1
GPU type	NVIDIA A100-PCIE-40GB

W&B CLI Version

0.16.6

Group

xland-multi-task-test-v0

Config parameters are your model's inputs. Learn more

▶
Config parameters:{} 38 keys
- action_emb_dim:
  16
- benchmark_id:
  "trivial-1m"
- checkpoint_path:
  null
- clip_eps:
  0.2
- context_dropout:
  0
- context_emb_dim:
  8
- context_hidden_dim:
  256
- dataset_name:
  null
- dataset_num_histories:
  1
- dataset_path:
  null
- ent_coef:
  0.001
- env_id:
  "XLand-MiniGrid-R1-9x9"
- eval_episodes:
  256
- eval_seed:
  42
- gae_lambda:
  0.999
- gamma:
  0.999
- group:
  "xland-multi-task-test-v0"
- head_hidden_dim:
  256
- lr:
  0.0001
- max_grad_norm:
  0.5
- name:
  "ppo-rnn-multi-task-trivial"
- num_envs:
  8,192
- num_minibatches:
  8
- num_steps:
  512
- obs_emb_dim:
  16
- pretrain_multitask:
  false
- pretrained_checkpoint_path:
  null
- project:
  "xminigrid"
- rnn_hidden_dim:
  256
- rnn_num_layers:
  1
- ruleset_id:
  0
- seed:
  0
- total_timesteps:
  500,000,000
- update_epochs:
  1
- upload_to_hf_repo:
  null
- use_bf16:
  true
- vf_coef:
  0.5
- wandb_logging:
  true

Summary metrics are your model's outputs. Learn more

▶
Summary metrics:{} 10 keys
- actor_loss:
  -0.00000050492235459387
- entropy:
  1.500483155250549
- eval/lengths:
  217.96484375
- eval/returns:
  0.11459781229496002
- lr:
  0.00000084033013081353
- steps_per_second:
  1,651,300.840711287
- total_loss:
  0.008420394733548164
- training_time:
  302.79158568382263
- transitions:
  494,927,872
- value_loss:
  0.019842766225337986

This run consumed these artifacts as inputs. Learn more

job

job-git_github.com_Howuhh_xland-minigrid-datasets.git_src_xminigrid_datasets_collection_train.py:v127

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

wandb-history

run-6544651-history:v0