Skip to content

Commit

Permalink
exp: update wa-capable nodes
Browse files Browse the repository at this point in the history
  • Loading branch information
zhudotexe committed Dec 11, 2024
1 parent 4e8c4c4 commit eb2d581
Show file tree
Hide file tree
Showing 47 changed files with 47 additions and 46 deletions.
1 change: 1 addition & 0 deletions README.md
Original file line number Diff line number Diff line change
Expand Up @@ -223,6 +223,7 @@ See https://github.com/web-arena-x/webarena/blob/main/environment_docker/README.

> [!NOTE]
> https://github.com/gasse/webarena-setup/tree/main/webarena is a helpful unofficial setup script.
> The containers are loaded on NLPGPU 04, 05, and 08.
Next, run the following to setup the webarena configuration:

Expand Down
2 changes: 1 addition & 1 deletion slurm/claude/webarena-1-full.sh
Original file line number Diff line number Diff line change
Expand Up @@ -11,7 +11,7 @@
#SBATCH --gpus=0
#SBATCH [email protected]
#SBATCH --mail-type=END,FAIL
#SBATCH --nodelist=nlpgpu05
#SBATCH --nodelist=nlpgpu04,nlpgpu05,nlpgpu08


source slurm/env.sh
Expand Down
2 changes: 1 addition & 1 deletion slurm/claude/webarena-2-root-fc.sh
Original file line number Diff line number Diff line change
Expand Up @@ -11,7 +11,7 @@
#SBATCH --gpus=0
#SBATCH [email protected]
#SBATCH --mail-type=END,FAIL
#SBATCH --nodelist=nlpgpu05
#SBATCH --nodelist=nlpgpu04,nlpgpu05,nlpgpu08


source slurm/env.sh
Expand Down
2 changes: 1 addition & 1 deletion slurm/claude/webarena-3-baseline.sh
Original file line number Diff line number Diff line change
Expand Up @@ -11,7 +11,7 @@
#SBATCH --gpus=0
#SBATCH [email protected]
#SBATCH --mail-type=END,FAIL
#SBATCH --nodelist=nlpgpu05
#SBATCH --nodelist=nlpgpu04,nlpgpu05,nlpgpu08


source slurm/env.sh
Expand Down
2 changes: 1 addition & 1 deletion slurm/claude/webarena-4-small-leaf.sh
Original file line number Diff line number Diff line change
Expand Up @@ -11,7 +11,7 @@
#SBATCH --gpus=0
#SBATCH [email protected]
#SBATCH --mail-type=END,FAIL
#SBATCH --nodelist=nlpgpu05
#SBATCH --nodelist=nlpgpu04,nlpgpu05,nlpgpu08


source slurm/env.sh
Expand Down
2 changes: 1 addition & 1 deletion slurm/claude/webarena-5-small-all.sh
Original file line number Diff line number Diff line change
Expand Up @@ -11,7 +11,7 @@
#SBATCH --gpus=0
#SBATCH [email protected]
#SBATCH --mail-type=END,FAIL
#SBATCH --nodelist=nlpgpu05
#SBATCH --nodelist=nlpgpu04,nlpgpu05,nlpgpu08


source slurm/env.sh
Expand Down
2 changes: 1 addition & 1 deletion slurm/claude/webarena-6-small-baseline.sh
Original file line number Diff line number Diff line change
Expand Up @@ -11,7 +11,7 @@
#SBATCH --gpus=0
#SBATCH [email protected]
#SBATCH --mail-type=END,FAIL
#SBATCH --nodelist=nlpgpu05
#SBATCH --nodelist=nlpgpu04,nlpgpu05,nlpgpu08


source slurm/env.sh
Expand Down
2 changes: 1 addition & 1 deletion slurm/claude/webarena-7-short-context.sh
Original file line number Diff line number Diff line change
Expand Up @@ -11,7 +11,7 @@
#SBATCH --gpus=0
#SBATCH [email protected]
#SBATCH --mail-type=END,FAIL
#SBATCH --nodelist=nlpgpu05
#SBATCH --nodelist=nlpgpu04,nlpgpu05,nlpgpu08


source slurm/env.sh
Expand Down
2 changes: 1 addition & 1 deletion slurm/claude/webarena-8-short-baseline.sh
Original file line number Diff line number Diff line change
Expand Up @@ -11,7 +11,7 @@
#SBATCH --gpus=0
#SBATCH [email protected]
#SBATCH --mail-type=END,FAIL
#SBATCH --nodelist=nlpgpu05
#SBATCH --nodelist=nlpgpu04,nlpgpu05,nlpgpu08


source slurm/env.sh
Expand Down
2 changes: 1 addition & 1 deletion slurm/claude/webarena-all.sh
Original file line number Diff line number Diff line change
Expand Up @@ -11,7 +11,7 @@
#SBATCH --gpus=0
#SBATCH [email protected]
#SBATCH --mail-type=END,FAIL
#SBATCH --nodelist=nlpgpu05
#SBATCH --nodelist=nlpgpu04,nlpgpu05,nlpgpu08


source slurm/env.sh
Expand Down
2 changes: 1 addition & 1 deletion slurm/cohere-hf/webarena-1-full.sh
Original file line number Diff line number Diff line change
Expand Up @@ -11,7 +11,7 @@
#SBATCH --gpus=8
#SBATCH [email protected]
#SBATCH --mail-type=END,FAIL
#SBATCH --nodelist=nlpgpu05
#SBATCH --nodelist=nlpgpu04,nlpgpu05,nlpgpu08
#SBATCH --constraint=48GBgpu

source slurm/env.sh
Expand Down
2 changes: 1 addition & 1 deletion slurm/cohere-hf/webarena-2-root-fc.sh
Original file line number Diff line number Diff line change
Expand Up @@ -11,7 +11,7 @@
#SBATCH --gpus=8
#SBATCH [email protected]
#SBATCH --mail-type=END,FAIL
#SBATCH --nodelist=nlpgpu05
#SBATCH --nodelist=nlpgpu04,nlpgpu05,nlpgpu08
#SBATCH --constraint=48GBgpu

source slurm/env.sh
Expand Down
2 changes: 1 addition & 1 deletion slurm/cohere-hf/webarena-3-baseline.sh
Original file line number Diff line number Diff line change
Expand Up @@ -11,7 +11,7 @@
#SBATCH --gpus=8
#SBATCH [email protected]
#SBATCH --mail-type=END,FAIL
#SBATCH --nodelist=nlpgpu05
#SBATCH --nodelist=nlpgpu04,nlpgpu05,nlpgpu08
#SBATCH --constraint=48GBgpu

source slurm/env.sh
Expand Down
2 changes: 1 addition & 1 deletion slurm/cohere-hf/webarena-4-small-leaf.sh
Original file line number Diff line number Diff line change
Expand Up @@ -11,7 +11,7 @@
#SBATCH --gpus=8
#SBATCH [email protected]
#SBATCH --mail-type=END,FAIL
#SBATCH --nodelist=nlpgpu05
#SBATCH --nodelist=nlpgpu04,nlpgpu05,nlpgpu08
#SBATCH --constraint=48GBgpu

source slurm/env.sh
Expand Down
2 changes: 1 addition & 1 deletion slurm/cohere-hf/webarena-5-small-all.sh
Original file line number Diff line number Diff line change
Expand Up @@ -11,7 +11,7 @@
#SBATCH --gpus=8
#SBATCH [email protected]
#SBATCH --mail-type=END,FAIL
#SBATCH --nodelist=nlpgpu05
#SBATCH --nodelist=nlpgpu04,nlpgpu05,nlpgpu08
#SBATCH --constraint=48GBgpu

source slurm/env.sh
Expand Down
2 changes: 1 addition & 1 deletion slurm/cohere-hf/webarena-6-small-baseline.sh
Original file line number Diff line number Diff line change
Expand Up @@ -11,7 +11,7 @@
#SBATCH --gpus=8
#SBATCH [email protected]
#SBATCH --mail-type=END,FAIL
#SBATCH --nodelist=nlpgpu05
#SBATCH --nodelist=nlpgpu04,nlpgpu05,nlpgpu08
#SBATCH --constraint=48GBgpu

source slurm/env.sh
Expand Down
2 changes: 1 addition & 1 deletion slurm/cohere-hf/webarena-7-short-context.sh
Original file line number Diff line number Diff line change
Expand Up @@ -11,7 +11,7 @@
#SBATCH --gpus=8
#SBATCH [email protected]
#SBATCH --mail-type=END,FAIL
#SBATCH --nodelist=nlpgpu05
#SBATCH --nodelist=nlpgpu04,nlpgpu05,nlpgpu08
#SBATCH --constraint=48GBgpu

source slurm/env.sh
Expand Down
2 changes: 1 addition & 1 deletion slurm/cohere-hf/webarena-8-short-baseline.sh
Original file line number Diff line number Diff line change
Expand Up @@ -11,7 +11,7 @@
#SBATCH --gpus=8
#SBATCH [email protected]
#SBATCH --mail-type=END,FAIL
#SBATCH --nodelist=nlpgpu05
#SBATCH --nodelist=nlpgpu04,nlpgpu05,nlpgpu08
#SBATCH --constraint=48GBgpu

source slurm/env.sh
Expand Down
2 changes: 1 addition & 1 deletion slurm/cohere-hf/webarena-all.sh
Original file line number Diff line number Diff line change
Expand Up @@ -11,7 +11,7 @@
#SBATCH --gpus=8
#SBATCH [email protected]
#SBATCH --mail-type=END,FAIL
#SBATCH --nodelist=nlpgpu05
#SBATCH --nodelist=nlpgpu04,nlpgpu05,nlpgpu08
#SBATCH --constraint=48GBgpu

source slurm/env.sh
Expand Down
2 changes: 1 addition & 1 deletion slurm/gen_slurm.py
Original file line number Diff line number Diff line change
Expand Up @@ -85,7 +85,7 @@ def main():
for bench in BENCHES:
# WA needs extra env vars
if bench == "webarena":
gpuconstraint = f"#SBATCH --nodelist=nlpgpu05\n{gpuconstraint}"
gpuconstraint = f"#SBATCH --nodelist=nlpgpu04,nlpgpu05,nlpgpu08\n{gpuconstraint}"
bench_extras = "curl -X GET ${RESTART_URL}\nsleep 600"
bench_startup = (
"dockerd-rootless.sh &\n"
Expand Down
2 changes: 1 addition & 1 deletion slurm/mistral/webarena-1-full.sh
Original file line number Diff line number Diff line change
Expand Up @@ -11,7 +11,7 @@
#SBATCH --gpus=8
#SBATCH [email protected]
#SBATCH --mail-type=END,FAIL
#SBATCH --nodelist=nlpgpu05
#SBATCH --nodelist=nlpgpu04,nlpgpu05,nlpgpu08
#SBATCH --constraint=48GBgpu

source slurm/env.sh
Expand Down
2 changes: 1 addition & 1 deletion slurm/mistral/webarena-2-root-fc.sh
Original file line number Diff line number Diff line change
Expand Up @@ -11,7 +11,7 @@
#SBATCH --gpus=8
#SBATCH [email protected]
#SBATCH --mail-type=END,FAIL
#SBATCH --nodelist=nlpgpu05
#SBATCH --nodelist=nlpgpu04,nlpgpu05,nlpgpu08
#SBATCH --constraint=48GBgpu

source slurm/env.sh
Expand Down
2 changes: 1 addition & 1 deletion slurm/mistral/webarena-3-baseline.sh
Original file line number Diff line number Diff line change
Expand Up @@ -11,7 +11,7 @@
#SBATCH --gpus=8
#SBATCH [email protected]
#SBATCH --mail-type=END,FAIL
#SBATCH --nodelist=nlpgpu05
#SBATCH --nodelist=nlpgpu04,nlpgpu05,nlpgpu08
#SBATCH --constraint=48GBgpu

source slurm/env.sh
Expand Down
2 changes: 1 addition & 1 deletion slurm/mistral/webarena-4-small-leaf.sh
Original file line number Diff line number Diff line change
Expand Up @@ -11,7 +11,7 @@
#SBATCH --gpus=8
#SBATCH [email protected]
#SBATCH --mail-type=END,FAIL
#SBATCH --nodelist=nlpgpu05
#SBATCH --nodelist=nlpgpu04,nlpgpu05,nlpgpu08
#SBATCH --constraint=48GBgpu

source slurm/env.sh
Expand Down
2 changes: 1 addition & 1 deletion slurm/mistral/webarena-5-small-all.sh
Original file line number Diff line number Diff line change
Expand Up @@ -11,7 +11,7 @@
#SBATCH --gpus=8
#SBATCH [email protected]
#SBATCH --mail-type=END,FAIL
#SBATCH --nodelist=nlpgpu05
#SBATCH --nodelist=nlpgpu04,nlpgpu05,nlpgpu08
#SBATCH --constraint=48GBgpu

source slurm/env.sh
Expand Down
2 changes: 1 addition & 1 deletion slurm/mistral/webarena-6-small-baseline.sh
Original file line number Diff line number Diff line change
Expand Up @@ -11,7 +11,7 @@
#SBATCH --gpus=8
#SBATCH [email protected]
#SBATCH --mail-type=END,FAIL
#SBATCH --nodelist=nlpgpu05
#SBATCH --nodelist=nlpgpu04,nlpgpu05,nlpgpu08
#SBATCH --constraint=48GBgpu

source slurm/env.sh
Expand Down
2 changes: 1 addition & 1 deletion slurm/mistral/webarena-7-short-context.sh
Original file line number Diff line number Diff line change
Expand Up @@ -11,7 +11,7 @@
#SBATCH --gpus=8
#SBATCH [email protected]
#SBATCH --mail-type=END,FAIL
#SBATCH --nodelist=nlpgpu05
#SBATCH --nodelist=nlpgpu04,nlpgpu05,nlpgpu08
#SBATCH --constraint=48GBgpu

source slurm/env.sh
Expand Down
2 changes: 1 addition & 1 deletion slurm/mistral/webarena-8-short-baseline.sh
Original file line number Diff line number Diff line change
Expand Up @@ -11,7 +11,7 @@
#SBATCH --gpus=8
#SBATCH [email protected]
#SBATCH --mail-type=END,FAIL
#SBATCH --nodelist=nlpgpu05
#SBATCH --nodelist=nlpgpu04,nlpgpu05,nlpgpu08
#SBATCH --constraint=48GBgpu

source slurm/env.sh
Expand Down
2 changes: 1 addition & 1 deletion slurm/mistral/webarena-all.sh
Original file line number Diff line number Diff line change
Expand Up @@ -11,7 +11,7 @@
#SBATCH --gpus=8
#SBATCH [email protected]
#SBATCH --mail-type=END,FAIL
#SBATCH --nodelist=nlpgpu05
#SBATCH --nodelist=nlpgpu04,nlpgpu05,nlpgpu08
#SBATCH --constraint=48GBgpu

source slurm/env.sh
Expand Down
2 changes: 1 addition & 1 deletion slurm/openai/webarena-1-full.sh
Original file line number Diff line number Diff line change
Expand Up @@ -11,7 +11,7 @@
#SBATCH --gpus=0
#SBATCH [email protected]
#SBATCH --mail-type=END,FAIL
#SBATCH --nodelist=nlpgpu05
#SBATCH --nodelist=nlpgpu04,nlpgpu05,nlpgpu08


source slurm/env.sh
Expand Down
2 changes: 1 addition & 1 deletion slurm/openai/webarena-2-root-fc.sh
Original file line number Diff line number Diff line change
Expand Up @@ -11,7 +11,7 @@
#SBATCH --gpus=0
#SBATCH [email protected]
#SBATCH --mail-type=END,FAIL
#SBATCH --nodelist=nlpgpu05
#SBATCH --nodelist=nlpgpu04,nlpgpu05,nlpgpu08


source slurm/env.sh
Expand Down
2 changes: 1 addition & 1 deletion slurm/openai/webarena-3-baseline.sh
Original file line number Diff line number Diff line change
Expand Up @@ -11,7 +11,7 @@
#SBATCH --gpus=0
#SBATCH [email protected]
#SBATCH --mail-type=END,FAIL
#SBATCH --nodelist=nlpgpu05
#SBATCH --nodelist=nlpgpu04,nlpgpu05,nlpgpu08


source slurm/env.sh
Expand Down
2 changes: 1 addition & 1 deletion slurm/openai/webarena-4-small-leaf.sh
Original file line number Diff line number Diff line change
Expand Up @@ -11,7 +11,7 @@
#SBATCH --gpus=0
#SBATCH [email protected]
#SBATCH --mail-type=END,FAIL
#SBATCH --nodelist=nlpgpu05
#SBATCH --nodelist=nlpgpu04,nlpgpu05,nlpgpu08


source slurm/env.sh
Expand Down
2 changes: 1 addition & 1 deletion slurm/openai/webarena-5-small-all.sh
Original file line number Diff line number Diff line change
Expand Up @@ -11,7 +11,7 @@
#SBATCH --gpus=0
#SBATCH [email protected]
#SBATCH --mail-type=END,FAIL
#SBATCH --nodelist=nlpgpu05
#SBATCH --nodelist=nlpgpu04,nlpgpu05,nlpgpu08


source slurm/env.sh
Expand Down
2 changes: 1 addition & 1 deletion slurm/openai/webarena-6-small-baseline.sh
Original file line number Diff line number Diff line change
Expand Up @@ -11,7 +11,7 @@
#SBATCH --gpus=0
#SBATCH [email protected]
#SBATCH --mail-type=END,FAIL
#SBATCH --nodelist=nlpgpu05
#SBATCH --nodelist=nlpgpu04,nlpgpu05,nlpgpu08


source slurm/env.sh
Expand Down
2 changes: 1 addition & 1 deletion slurm/openai/webarena-7-short-context.sh
Original file line number Diff line number Diff line change
Expand Up @@ -11,7 +11,7 @@
#SBATCH --gpus=0
#SBATCH [email protected]
#SBATCH --mail-type=END,FAIL
#SBATCH --nodelist=nlpgpu05
#SBATCH --nodelist=nlpgpu04,nlpgpu05,nlpgpu08


source slurm/env.sh
Expand Down
2 changes: 1 addition & 1 deletion slurm/openai/webarena-8-short-baseline.sh
Original file line number Diff line number Diff line change
Expand Up @@ -11,7 +11,7 @@
#SBATCH --gpus=0
#SBATCH [email protected]
#SBATCH --mail-type=END,FAIL
#SBATCH --nodelist=nlpgpu05
#SBATCH --nodelist=nlpgpu04,nlpgpu05,nlpgpu08


source slurm/env.sh
Expand Down
2 changes: 1 addition & 1 deletion slurm/openai/webarena-all.sh
Original file line number Diff line number Diff line change
Expand Up @@ -11,7 +11,7 @@
#SBATCH --gpus=0
#SBATCH [email protected]
#SBATCH --mail-type=END,FAIL
#SBATCH --nodelist=nlpgpu05
#SBATCH --nodelist=nlpgpu04,nlpgpu05,nlpgpu08


source slurm/env.sh
Expand Down
2 changes: 1 addition & 1 deletion slurm/qwen/webarena-1-full.sh
Original file line number Diff line number Diff line change
Expand Up @@ -11,7 +11,7 @@
#SBATCH --gpus=8
#SBATCH [email protected]
#SBATCH --mail-type=END,FAIL
#SBATCH --nodelist=nlpgpu05
#SBATCH --nodelist=nlpgpu04,nlpgpu05,nlpgpu08
#SBATCH --constraint=48GBgpu

source slurm/env.sh
Expand Down
2 changes: 1 addition & 1 deletion slurm/qwen/webarena-2-root-fc.sh
Original file line number Diff line number Diff line change
Expand Up @@ -11,7 +11,7 @@
#SBATCH --gpus=8
#SBATCH [email protected]
#SBATCH --mail-type=END,FAIL
#SBATCH --nodelist=nlpgpu05
#SBATCH --nodelist=nlpgpu04,nlpgpu05,nlpgpu08
#SBATCH --constraint=48GBgpu

source slurm/env.sh
Expand Down
2 changes: 1 addition & 1 deletion slurm/qwen/webarena-3-baseline.sh
Original file line number Diff line number Diff line change
Expand Up @@ -11,7 +11,7 @@
#SBATCH --gpus=8
#SBATCH [email protected]
#SBATCH --mail-type=END,FAIL
#SBATCH --nodelist=nlpgpu05
#SBATCH --nodelist=nlpgpu04,nlpgpu05,nlpgpu08
#SBATCH --constraint=48GBgpu

source slurm/env.sh
Expand Down
2 changes: 1 addition & 1 deletion slurm/qwen/webarena-4-small-leaf.sh
Original file line number Diff line number Diff line change
Expand Up @@ -11,7 +11,7 @@
#SBATCH --gpus=8
#SBATCH [email protected]
#SBATCH --mail-type=END,FAIL
#SBATCH --nodelist=nlpgpu05
#SBATCH --nodelist=nlpgpu04,nlpgpu05,nlpgpu08
#SBATCH --constraint=48GBgpu

source slurm/env.sh
Expand Down
2 changes: 1 addition & 1 deletion slurm/qwen/webarena-5-small-all.sh
Original file line number Diff line number Diff line change
Expand Up @@ -11,7 +11,7 @@
#SBATCH --gpus=8
#SBATCH [email protected]
#SBATCH --mail-type=END,FAIL
#SBATCH --nodelist=nlpgpu05
#SBATCH --nodelist=nlpgpu04,nlpgpu05,nlpgpu08
#SBATCH --constraint=48GBgpu

source slurm/env.sh
Expand Down
2 changes: 1 addition & 1 deletion slurm/qwen/webarena-6-small-baseline.sh
Original file line number Diff line number Diff line change
Expand Up @@ -11,7 +11,7 @@
#SBATCH --gpus=8
#SBATCH [email protected]
#SBATCH --mail-type=END,FAIL
#SBATCH --nodelist=nlpgpu05
#SBATCH --nodelist=nlpgpu04,nlpgpu05,nlpgpu08
#SBATCH --constraint=48GBgpu

source slurm/env.sh
Expand Down
Loading

0 comments on commit eb2d581

Please sign in to comment.