state-machine

State-machine's group workspace

Group: trivial-faster-trials

1-4

of 4

Tags

Notes

Author

state-machine

State

Finished

Job

job-git_github.com_corl-team_xland-minigrid.git_training_train_meta_task.py:v22

Start time

October 10th, 2024 11:54:07 AM

Runtime

1h 4m 44s

Tracked hours

1h 4m 38s

Run path

state-machine/xminigrid/a7qi74qf

Linux-5.15.0-1044-nvidia-x86_64-with-glibc2.31

Python version

3.10.13

Git repository

git clone git@github.com:corl-team/xland-minigrid.git

Git state

git checkout -b "meta-task-ppo" 6a775f35dd4366f167ab7ddf6941c9f8bcf7f87a

Command

/home/jovyan/tmp/c53f11f8/training/train_meta_task.py --config_path=configs/wip/config_best.yaml --group=trivial-faster-trials --env_id=XLand-MiniGrid-R1-9x9 --benchmark_id=trivial-1m --num_steps_per_env=768 --eval_num_episodes=3 --total_timesteps=5_000_000_000 --train_seed=1 --enable_bf16=True

System Hardware

CPU count	112
Logical CPU count	224
GPU count	1
GPU type	NVIDIA H100 80GB HBM3

W&B CLI Version

0.17.0

Group

trivial-faster-trials

Config parameters are your model's inputs. Learn more

▶
Config parameters:{} 30 keys
- action_emb_dim:
  16
- benchmark_id:
  "trivial-1m"
- checkpoint_path:
  null
- clip_eps:
  0.2
- enable_bf16:
  true
- ent_coef:
  0.01
- env_id:
  "XLand-MiniGrid-R1-9x9"
- eval_num_envs:
  16,384
- eval_num_episodes:
  3
- eval_seed:
  42
- gae_lambda:
  0.95
- gamma:
  0.99
- group:
  "trivial-faster-trials"
- head_hidden_dim:
  256
- img_obs:
  false
- lr:
  0.001
- max_grad_norm:
  0.5
- name:
  "meta-task-ppo"
- num_envs:
  16,384
- num_minibatches:
  16
- num_steps_per_env:
  768
- num_steps_per_update:
  256
- obs_emb_dim:
  16
- project:
  "xminigrid"
- rnn_hidden_dim:
  1,024
- rnn_num_layers:
  1
- total_timesteps:
  5,000,000,000
- train_seed:
  1
- update_epochs:
  1
- vf_coef:
  0.5

Summary metrics are your model's outputs. Learn more

▶
Summary metrics:{} 13 keys
- actor_loss:
  -0.00004479156632442027
- entropy:
  0.2930731177330017
- eval/lengths:
  183.04229736328125
- eval/lengths_20percentile:
  50
- eval/returns_20percentile:
  1.7259259223937988
- eval/returns_mean:
  2.2938060760498047
- eval/returns_median:
  2.6148147583007812
- lr:
  0.00000251895198744023
- steps_per_second:
  1,310,045.098662586
- total_loss:
  0.06517531722784042
- training_time:
  3,816.6624989509583
- transitions:
  4,995,416,064
- value_loss:
  0.13671875

This run consumed these artifacts as inputs. Learn more

job

job-git_github.com_corl-team_xland-minigrid.git_training_train_meta_task.py:v22

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

wandb-history

run-a7qi74qf-history:v0