Upload folder using huggingface_hub
Browse files- .gitignore +2 -0
- arguments.json +93 -0
- arguments.pkl +3 -0
- environ.txt +236 -0
- stderr.log +0 -0
- stdout.log +0 -0
.gitignore
ADDED
|
@@ -0,0 +1,2 @@
|
|
|
|
|
|
|
|
|
|
| 1 |
+
wandb/
|
| 2 |
+
script.sh
|
arguments.json
ADDED
|
@@ -0,0 +1,93 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"actor_model_name_or_path": "AlisonWen/safe-rlhf-sft",
|
| 3 |
+
"reward_model_name_or_path": "AlisonWen/rm-seed-42-targeted-flipped-0.5",
|
| 4 |
+
"reward_critic_model_name_or_path": "AlisonWen/rm-seed-42-targeted-flipped-0.5",
|
| 5 |
+
"max_length": 512,
|
| 6 |
+
"trust_remote_code": true,
|
| 7 |
+
"train_datasets": [
|
| 8 |
+
[
|
| 9 |
+
"PKU-SafeRLHF/train",
|
| 10 |
+
{
|
| 11 |
+
"proportion": 1.0
|
| 12 |
+
}
|
| 13 |
+
]
|
| 14 |
+
],
|
| 15 |
+
"ptx_datasets": [
|
| 16 |
+
[
|
| 17 |
+
"alpaca",
|
| 18 |
+
{
|
| 19 |
+
"proportion": 1.0
|
| 20 |
+
}
|
| 21 |
+
]
|
| 22 |
+
],
|
| 23 |
+
"eval_datasets": null,
|
| 24 |
+
"kl_coeff": 0.02,
|
| 25 |
+
"clip_range_ratio": 0.2,
|
| 26 |
+
"clip_range_score": 50.0,
|
| 27 |
+
"clip_range_value": 5.0,
|
| 28 |
+
"ptx_coeff": 16.0,
|
| 29 |
+
"epochs": 1,
|
| 30 |
+
"update_iters": 2,
|
| 31 |
+
"per_device_prompt_batch_size": 16,
|
| 32 |
+
"per_device_train_batch_size": 16,
|
| 33 |
+
"per_device_eval_batch_size": 16,
|
| 34 |
+
"gradient_accumulation_steps": 2,
|
| 35 |
+
"actor_lr": 1e-05,
|
| 36 |
+
"actor_weight_decay": 0.01,
|
| 37 |
+
"actor_lr_scheduler_type": "cosine",
|
| 38 |
+
"actor_lr_warmup_ratio": 0.03,
|
| 39 |
+
"actor_gradient_checkpointing": true,
|
| 40 |
+
"critic_lr": 5e-06,
|
| 41 |
+
"critic_weight_decay": 0.0,
|
| 42 |
+
"critic_lr_scheduler_type": "constant",
|
| 43 |
+
"critic_lr_warmup_ratio": 0.03,
|
| 44 |
+
"critic_gradient_checkpointing": true,
|
| 45 |
+
"normalize_reward": false,
|
| 46 |
+
"seed": 100,
|
| 47 |
+
"fp16": false,
|
| 48 |
+
"bf16": true,
|
| 49 |
+
"tf32": true,
|
| 50 |
+
"pth": 0.5,
|
| 51 |
+
"pth_dynamic_adjust": null,
|
| 52 |
+
"pth_meta_lr": 0.0,
|
| 53 |
+
"meta_pth_scale": 10.0,
|
| 54 |
+
"meta_pth_update_interval": 10,
|
| 55 |
+
"linear_pth": null,
|
| 56 |
+
"linear_pth_init": 0.3,
|
| 57 |
+
"linear_pth_end": 1.0,
|
| 58 |
+
"random_reward_poisoning": null,
|
| 59 |
+
"attack_prob": null,
|
| 60 |
+
"attack_strength": null,
|
| 61 |
+
"uniform_random_poisoning": null,
|
| 62 |
+
"malicious_babble_attack": null,
|
| 63 |
+
"dynamic_pth_rate": 0.0,
|
| 64 |
+
"pth_batch_size": 8,
|
| 65 |
+
"temperature": 1.0,
|
| 66 |
+
"top_p": 1.0,
|
| 67 |
+
"num_return_sequences": 1,
|
| 68 |
+
"repetition_penalty": 1.0,
|
| 69 |
+
"eval_strategy": "epoch",
|
| 70 |
+
"eval_interval": 1000000,
|
| 71 |
+
"need_eval": false,
|
| 72 |
+
"eval_split_ratio": null,
|
| 73 |
+
"output_dir": "/mnt/home/alison.cs13/RobustRLHF/output/ppo-robust-0.5-resample-large-batch-random-select-voted-flipped",
|
| 74 |
+
"log_type": "wandb",
|
| 75 |
+
"log_dir": "/mnt/home/alison.cs13/RobustRLHF/output/ppo-robust-0.5-resample-large-batch-random-select-voted-flipped",
|
| 76 |
+
"log_project": "Safe-RLHF-PPO",
|
| 77 |
+
"log_run_name": "ppo-robust-0.5-resample-large-batch-voted-flipped-step-604",
|
| 78 |
+
"save_16bit": false,
|
| 79 |
+
"save_interval": 1000000,
|
| 80 |
+
"local_rank": 0,
|
| 81 |
+
"zero_stage": 3,
|
| 82 |
+
"offload": "none",
|
| 83 |
+
"deepspeed": false,
|
| 84 |
+
"deepspeed_config": null,
|
| 85 |
+
"deepscale": false,
|
| 86 |
+
"deepscale_config": null,
|
| 87 |
+
"global_rank": 0,
|
| 88 |
+
"device": {
|
| 89 |
+
"type": "torch.device",
|
| 90 |
+
"repr": "device(type='cuda', index=0)"
|
| 91 |
+
},
|
| 92 |
+
"total_training_steps": 1208
|
| 93 |
+
}
|
arguments.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e617aa8ecb05af101b8b2ec74dc4ce12b8df3fadee5127f4f2f1d9f899a0188e
|
| 3 |
+
size 2117
|
environ.txt
ADDED
|
@@ -0,0 +1,236 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
BASH_FUNC_ml%%=() { module ml "$@"
|
| 2 |
+
}
|
| 3 |
+
BASH_FUNC_module%%=() { unset _mlshdbg;
|
| 4 |
+
if [ "${MODULES_SILENT_SHELL_DEBUG:-0}" = '1' ]; then
|
| 5 |
+
case "$-" in
|
| 6 |
+
*v*x*)
|
| 7 |
+
set +vx;
|
| 8 |
+
_mlshdbg='vx'
|
| 9 |
+
;;
|
| 10 |
+
*v*)
|
| 11 |
+
set +v;
|
| 12 |
+
_mlshdbg='v'
|
| 13 |
+
;;
|
| 14 |
+
*x*)
|
| 15 |
+
set +x;
|
| 16 |
+
_mlshdbg='x'
|
| 17 |
+
;;
|
| 18 |
+
*)
|
| 19 |
+
_mlshdbg=''
|
| 20 |
+
;;
|
| 21 |
+
esac;
|
| 22 |
+
fi;
|
| 23 |
+
unset _mlre _mlIFS;
|
| 24 |
+
if [ -n "${IFS+x}" ]; then
|
| 25 |
+
_mlIFS=$IFS;
|
| 26 |
+
fi;
|
| 27 |
+
IFS=' ';
|
| 28 |
+
for _mlv in ${MODULES_RUN_QUARANTINE:-};
|
| 29 |
+
do
|
| 30 |
+
if [ "${_mlv}" = "${_mlv##*[!A-Za-z0-9_]}" -a "${_mlv}" = "${_mlv#[0-9]}" ]; then
|
| 31 |
+
if [ -n "`eval 'echo ${'$_mlv'+x}'`" ]; then
|
| 32 |
+
_mlre="${_mlre:-}${_mlv}_modquar='`eval 'echo ${'$_mlv'}'`' ";
|
| 33 |
+
fi;
|
| 34 |
+
_mlrv="MODULES_RUNENV_${_mlv}";
|
| 35 |
+
_mlre="${_mlre:-}${_mlv}='`eval 'echo ${'$_mlrv':-}'`' ";
|
| 36 |
+
fi;
|
| 37 |
+
done;
|
| 38 |
+
if [ -n "${_mlre:-}" ]; then
|
| 39 |
+
eval `eval ${_mlre} /usr/bin/tclsh /cm/local/apps/environment-modules/4.5.3/libexec/modulecmd.tcl bash '"$@"'`;
|
| 40 |
+
else
|
| 41 |
+
eval `/usr/bin/tclsh /cm/local/apps/environment-modules/4.5.3/libexec/modulecmd.tcl bash "$@"`;
|
| 42 |
+
fi;
|
| 43 |
+
_mlstatus=$?;
|
| 44 |
+
if [ -n "${_mlIFS+x}" ]; then
|
| 45 |
+
IFS=$_mlIFS;
|
| 46 |
+
else
|
| 47 |
+
unset IFS;
|
| 48 |
+
fi;
|
| 49 |
+
unset _mlre _mlv _mlrv _mlIFS;
|
| 50 |
+
if [ -n "${_mlshdbg:-}" ]; then
|
| 51 |
+
set -$_mlshdbg;
|
| 52 |
+
fi;
|
| 53 |
+
unset _mlshdbg;
|
| 54 |
+
return $_mlstatus
|
| 55 |
+
}
|
| 56 |
+
BASH_FUNC_switchml%%=() { typeset swfound=1;
|
| 57 |
+
if [ "${MODULES_USE_COMPAT_VERSION:-0}" = '1' ]; then
|
| 58 |
+
typeset swname='main';
|
| 59 |
+
if [ -e /cm/local/apps/environment-modules/4.5.3/libexec/modulecmd.tcl ]; then
|
| 60 |
+
typeset swfound=0;
|
| 61 |
+
unset MODULES_USE_COMPAT_VERSION;
|
| 62 |
+
fi;
|
| 63 |
+
else
|
| 64 |
+
typeset swname='compatibility';
|
| 65 |
+
if [ -e /cm/local/apps/environment-modules/4.5.3/libexec/modulecmd-compat ]; then
|
| 66 |
+
typeset swfound=0;
|
| 67 |
+
MODULES_USE_COMPAT_VERSION=1;
|
| 68 |
+
export MODULES_USE_COMPAT_VERSION;
|
| 69 |
+
fi;
|
| 70 |
+
fi;
|
| 71 |
+
if [ $swfound -eq 0 ]; then
|
| 72 |
+
echo "Switching to Modules $swname version";
|
| 73 |
+
source /cm/local/apps/environment-modules/4.5.3/init/bash;
|
| 74 |
+
else
|
| 75 |
+
echo "Cannot switch to Modules $swname version, command not found";
|
| 76 |
+
return 1;
|
| 77 |
+
fi
|
| 78 |
+
}
|
| 79 |
+
BROWSER=/home/alison.cs13/.vscode-server/cli/servers/Stable-4437686ffebaf200fa4a6e6e67f735f3edf24ada/server/bin/helpers/browser.sh
|
| 80 |
+
CC=/usr/bin/gcc
|
| 81 |
+
CMD_WLM_CLUSTER_NAME=slurm
|
| 82 |
+
COLORTERM=truecolor
|
| 83 |
+
CONDA_DEFAULT_ENV=safe-rlhf-12.4
|
| 84 |
+
CONDA_EXE=/mnt/home/alison.cs13/anaconda3/bin/conda
|
| 85 |
+
CONDA_PREFIX=/mnt/home/alison.cs13/anaconda3/envs/safe-rlhf-12.4
|
| 86 |
+
CONDA_PREFIX_1=/mnt/home/alison.cs13/anaconda3
|
| 87 |
+
CONDA_PROMPT_MODIFIER=(safe-rlhf-12.4)
|
| 88 |
+
CONDA_PYTHON_EXE=/mnt/home/alison.cs13/anaconda3/bin/python
|
| 89 |
+
CONDA_SHLVL=2
|
| 90 |
+
CPATH=/cm/shared/apps/slurm/current/include
|
| 91 |
+
CPATH_modshare=/cm/shared/apps/slurm/current/include:1
|
| 92 |
+
CROSS_RANK=0
|
| 93 |
+
CROSS_SIZE=1
|
| 94 |
+
CUDA_MODULE_LOADING=LAZY
|
| 95 |
+
CUDA_VISIBLE_DEVICES=0,1,2,3
|
| 96 |
+
CXX=/usr/bin/g++
|
| 97 |
+
DBUS_SESSION_BUS_ADDRESS=unix:path=/run/user/1109/bus
|
| 98 |
+
ENABLE_LMOD=0
|
| 99 |
+
ENVIRONMENT=BATCH
|
| 100 |
+
GIT_ASKPASS=/home/alison.cs13/.vscode-server/cli/servers/Stable-4437686ffebaf200fa4a6e6e67f735f3edf24ada/server/extensions/git/dist/askpass.sh
|
| 101 |
+
GPU_DEVICE_ORDINAL=0,1,2,3
|
| 102 |
+
HOME=/home/alison.cs13
|
| 103 |
+
HOSTNAME=cnode4-002
|
| 104 |
+
LANG=en_US.UTF-8
|
| 105 |
+
LD_LIBRARY_PATH=/cm/shared/apps/slurm/current/lib64/slurm:/cm/shared/apps/slurm/current/lib64:/cm/local/apps/gcc/13.1.0/lib:/cm/local/apps/gcc/13.1.0/lib64:/cm/local/apps/gcc/13.1.0/lib32
|
| 106 |
+
LD_LIBRARY_PATH_modshare=/cm/shared/apps/slurm/current/lib64:1:/cm/local/apps/gcc/13.1.0/lib64:1:/cm/shared/apps/slurm/current/lib64/slurm:1:/cm/local/apps/gcc/13.1.0/lib:1:/cm/local/apps/gcc/13.1.0/lib32:1
|
| 107 |
+
LESSCLOSE=/usr/bin/lesspipe %s %s
|
| 108 |
+
LESSOPEN=| /usr/bin/lesspipe %s
|
| 109 |
+
LIBRARY_PATH=/cm/shared/apps/slurm/current/lib64/slurm:/cm/shared/apps/slurm/current/lib64
|
| 110 |
+
LIBRARY_PATH_modshare=/cm/shared/apps/slurm/current/lib64:1:/cm/shared/apps/slurm/current/lib64/slurm:1
|
| 111 |
+
LOADEDMODULES=gcc/13.1.0:slurm/slurm/23.02.8
|
| 112 |
+
LOADEDMODULES_modshare=gcc/13.1.0:1:slurm/slurm/23.02.8:1
|
| 113 |
+
LOCAL_RANK=0
|
| 114 |
+
LOCAL_SIZE=4
|
| 115 |
+
LOGLEVEL=WARNING
|
| 116 |
+
LOGNAME=alison.cs13
|
| 117 |
+
LS_COLORS=rs=0:di=01;34:ln=01;36:mh=00:pi=40;33:so=01;35:do=01;35:bd=40;33;01:cd=40;33;01:or=40;31;01:mi=00:su=37;41:sg=30;43:ca=30;41:tw=30;42:ow=34;42:st=37;44:ex=01;32:*.tar=01;31:*.tgz=01;31:*.arc=01;31:*.arj=01;31:*.taz=01;31:*.lha=01;31:*.lz4=01;31:*.lzh=01;31:*.lzma=01;31:*.tlz=01;31:*.txz=01;31:*.tzo=01;31:*.t7z=01;31:*.zip=01;31:*.z=01;31:*.dz=01;31:*.gz=01;31:*.lrz=01;31:*.lz=01;31:*.lzo=01;31:*.xz=01;31:*.zst=01;31:*.tzst=01;31:*.bz2=01;31:*.bz=01;31:*.tbz=01;31:*.tbz2=01;31:*.tz=01;31:*.deb=01;31:*.rpm=01;31:*.jar=01;31:*.war=01;31:*.ear=01;31:*.sar=01;31:*.rar=01;31:*.alz=01;31:*.ace=01;31:*.zoo=01;31:*.cpio=01;31:*.7z=01;31:*.rz=01;31:*.cab=01;31:*.wim=01;31:*.swm=01;31:*.dwm=01;31:*.esd=01;31:*.jpg=01;35:*.jpeg=01;35:*.mjpg=01;35:*.mjpeg=01;35:*.gif=01;35:*.bmp=01;35:*.pbm=01;35:*.pgm=01;35:*.ppm=01;35:*.tga=01;35:*.xbm=01;35:*.xpm=01;35:*.tif=01;35:*.tiff=01;35:*.png=01;35:*.svg=01;35:*.svgz=01;35:*.mng=01;35:*.pcx=01;35:*.mov=01;35:*.mpg=01;35:*.mpeg=01;35:*.m2v=01;35:*.mkv=01;35:*.webm=01;35:*.webp=01;35:*.ogm=01;35:*.mp4=01;35:*.m4v=01;35:*.mp4v=01;35:*.vob=01;35:*.qt=01;35:*.nuv=01;35:*.wmv=01;35:*.asf=01;35:*.rm=01;35:*.rmvb=01;35:*.flc=01;35:*.avi=01;35:*.fli=01;35:*.flv=01;35:*.gl=01;35:*.dl=01;35:*.xcf=01;35:*.xwd=01;35:*.yuv=01;35:*.cgm=01;35:*.emf=01;35:*.ogv=01;35:*.ogx=01;35:*.aac=00;36:*.au=00;36:*.flac=00;36:*.m4a=00;36:*.mid=00;36:*.midi=00;36:*.mka=00;36:*.mp3=00;36:*.mpc=00;36:*.ogg=00;36:*.ra=00;36:*.wav=00;36:*.oga=00;36:*.opus=00;36:*.spx=00;36:*.xspf=00;36:
|
| 118 |
+
MANPATH=/cm/shared/apps/slurm/current/man:/cm/local/apps/environment-modules/4.5.3/share/man:/usr/local/man:/usr/local/share/man:/usr/share/man:/cm/local/apps/environment-modules/current/share/man
|
| 119 |
+
MANPATH_modshare=/usr/local/share/man:1:/cm/local/apps/environment-modules/current/share/man:1:/cm/local/apps/environment-modules/4.5.3/share/man:1:/usr/local/man:1:/usr/share/man:1:/cm/shared/apps/slurm/current/man:1
|
| 120 |
+
MASTER_ADDR=127.0.0.1
|
| 121 |
+
MASTER_PORT=26638
|
| 122 |
+
MODULEPATH=/cm/local/modulefiles:/cm/shared/modulefiles
|
| 123 |
+
MODULESHOME=/cm/local/apps/environment-modules/4.5.3
|
| 124 |
+
MODULES_CMD=/cm/local/apps/environment-modules/4.5.3/libexec/modulecmd.tcl
|
| 125 |
+
MODULES_SET_SHELL_STARTUP=0
|
| 126 |
+
MOTD_SHOWN=pam
|
| 127 |
+
NVCC_FLAGS=--ccbin=/usr/bin/g++
|
| 128 |
+
OLDPWD=/mnt/home/alison.cs13/RobustRLHF
|
| 129 |
+
PATH=/cm/shared/apps/slurm/current/sbin:/cm/shared/apps/slurm/current/bin:/mnt/home/alison.cs13/anaconda3/envs/safe-rlhf-12.4/bin:/mnt/home/alison.cs13/anaconda3/condabin:/cm/local/apps/gcc/13.1.0/bin:/home/alison.cs13/.vscode-server/cli/servers/Stable-4437686ffebaf200fa4a6e6e67f735f3edf24ada/server/bin/remote-cli:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin:/usr/games:/usr/local/games:/snap/bin:/sbin:/usr/sbin:/cm/local/apps/environment-modules/4.5.3/bin
|
| 130 |
+
PATH_modshare=/home/alison.cs13/.vscode-server/cli/servers/Stable-4437686ffebaf200fa4a6e6e67f735f3edf24ada/server/bin/remote-cli:1:/usr/bin:1:/usr/local/bin:1:/cm/shared/apps/slurm/current/bin:1:/cm/shared/apps/slurm/current/sbin:1:/mnt/home/alison.cs13/anaconda3/condabin:1:/cm/local/apps/gcc/13.1.0/bin:1:/bin:1:/snap/bin:1:/mnt/home/alison.cs13/anaconda3/bin:1:/sbin:1:/usr/sbin:1:/usr/games:1:/cm/local/apps/environment-modules/4.5.3/bin:1:/usr/local/sbin:1:/usr/local/games:1
|
| 131 |
+
PMIX_BFROP_BUFFER_TYPE=PMIX_BFROP_BUFFER_NON_DESC
|
| 132 |
+
PMIX_GDS_MODULE=hash
|
| 133 |
+
PMIX_HOSTNAME=cnode4-002
|
| 134 |
+
PMIX_NAMESPACE=slurm.pmix.1046.0
|
| 135 |
+
PMIX_RANK=0
|
| 136 |
+
PMIX_SECURITY_MODE=none
|
| 137 |
+
PMIX_SERVER_TMPDIR=/cm/local/apps/slurm/var/spool/pmix.1046.0/
|
| 138 |
+
PMIX_SERVER_URI2=pmix-server.3992859;tcp4://127.0.0.1:52873
|
| 139 |
+
PMIX_SERVER_URI21=pmix-server.3992859;tcp4://127.0.0.1:52873
|
| 140 |
+
PMIX_SERVER_URI3=pmix-server.3992859;tcp4://127.0.0.1:52873
|
| 141 |
+
PMIX_SERVER_URI4=pmix-server.3992859;tcp4://127.0.0.1:52873
|
| 142 |
+
PMIX_SERVER_URI41=pmix-server.3992859;tcp4://127.0.0.1:52873
|
| 143 |
+
PMIX_SYSTEM_TMPDIR=/var/empty
|
| 144 |
+
PMIX_VERSION=4.1.3
|
| 145 |
+
PWD=/mnt/home/alison.cs13/RobustRLHF/scripts
|
| 146 |
+
PYTHONHASHSEED=100
|
| 147 |
+
PYTHONPATH=/mnt/home/alison.cs13/RobustRLHF
|
| 148 |
+
RANK=0
|
| 149 |
+
ROCR_VISIBLE_DEVICES=0,1,2,3
|
| 150 |
+
SHELL=/bin/bash
|
| 151 |
+
SHLVL=5
|
| 152 |
+
SLURMD_DEBUG=2
|
| 153 |
+
SLURMD_NODENAME=cnode4-002
|
| 154 |
+
SLURM_CLUSTER_NAME=slurm
|
| 155 |
+
SLURM_CONF=/cm/shared/apps/slurm/var/etc/slurm/slurm.conf
|
| 156 |
+
SLURM_CPUS_ON_NODE=8
|
| 157 |
+
SLURM_CPUS_PER_TASK=8
|
| 158 |
+
SLURM_DISTRIBUTION=cyclic
|
| 159 |
+
SLURM_GPUS_ON_NODE=4
|
| 160 |
+
SLURM_GTIDS=0
|
| 161 |
+
SLURM_JOBID=1046
|
| 162 |
+
SLURM_JOB_CPUS_PER_NODE=8
|
| 163 |
+
SLURM_JOB_END_TIME=1748625845
|
| 164 |
+
SLURM_JOB_GID=1109
|
| 165 |
+
SLURM_JOB_GPUS=0,1,2,3
|
| 166 |
+
SLURM_JOB_ID=1046
|
| 167 |
+
SLURM_JOB_NAME=Train-PPO-robust-0.5-resample-large-batch-voted-flipped-voted-flipped
|
| 168 |
+
SLURM_JOB_NODELIST=cnode4-002
|
| 169 |
+
SLURM_JOB_NUM_NODES=1
|
| 170 |
+
SLURM_JOB_PARTITION=p1
|
| 171 |
+
SLURM_JOB_QOS=normal
|
| 172 |
+
SLURM_JOB_START_TIME=1748496245
|
| 173 |
+
SLURM_JOB_UID=1109
|
| 174 |
+
SLURM_JOB_USER=alison.cs13
|
| 175 |
+
SLURM_LAUNCH_NODE_IPADDR=10.225.1.228
|
| 176 |
+
SLURM_LOCALID=0
|
| 177 |
+
SLURM_MEM_PER_NODE=204800
|
| 178 |
+
SLURM_MPI_TYPE=pmix
|
| 179 |
+
SLURM_NNODES=1
|
| 180 |
+
SLURM_NODEID=0
|
| 181 |
+
SLURM_NODELIST=cnode4-002
|
| 182 |
+
SLURM_NPROCS=1
|
| 183 |
+
SLURM_NTASKS=1
|
| 184 |
+
SLURM_NTASKS_PER_NODE=1
|
| 185 |
+
SLURM_PMIXP_ABORT_AGENT_PORT=37393
|
| 186 |
+
SLURM_PMIX_MAPPING_SERV=(vector,(0,1,1))
|
| 187 |
+
SLURM_PRIO_PROCESS=0
|
| 188 |
+
SLURM_PROCID=0
|
| 189 |
+
SLURM_SRUN_COMM_HOST=10.225.1.228
|
| 190 |
+
SLURM_SRUN_COMM_PORT=37925
|
| 191 |
+
SLURM_STEPID=0
|
| 192 |
+
SLURM_STEP_GPUS=0,1,2,3
|
| 193 |
+
SLURM_STEP_ID=0
|
| 194 |
+
SLURM_STEP_LAUNCHER_PORT=37925
|
| 195 |
+
SLURM_STEP_NODELIST=cnode4-002
|
| 196 |
+
SLURM_STEP_NUM_NODES=1
|
| 197 |
+
SLURM_STEP_NUM_TASKS=1
|
| 198 |
+
SLURM_STEP_TASKS_PER_NODE=1
|
| 199 |
+
SLURM_SUBMIT_DIR=/mnt/home/alison.cs13/RobustRLHF/scripts
|
| 200 |
+
SLURM_SUBMIT_HOST=Tunnel4-TRDC-02
|
| 201 |
+
SLURM_TASKS_PER_NODE=1
|
| 202 |
+
SLURM_TASK_PID=3992869
|
| 203 |
+
SLURM_TOPOLOGY_ADDR=cnode4-002
|
| 204 |
+
SLURM_TOPOLOGY_ADDR_PATTERN=node
|
| 205 |
+
SLURM_UMASK=0002
|
| 206 |
+
SLURM_WORKING_CLUSTER=slurm:Tunnel4-TRDC-02:6817:9984:109
|
| 207 |
+
SRUN_DEBUG=3
|
| 208 |
+
SSH_CLIENT=127.0.0.1 58318 22
|
| 209 |
+
SSH_CONNECTION=127.0.0.1 58318 127.0.0.1 22
|
| 210 |
+
SSL_CERT_DIR=/usr/lib/ssl/certs
|
| 211 |
+
SSL_CERT_FILE=/usr/lib/ssl/certs/ca-certificates.crt
|
| 212 |
+
TERM=xterm-256color
|
| 213 |
+
TERM_PROGRAM=vscode
|
| 214 |
+
TERM_PROGRAM_VERSION=1.99.0
|
| 215 |
+
TMPDIR=/tmp
|
| 216 |
+
TORCH_CUDA_ARCH_LIST=9.0
|
| 217 |
+
USER=alison.cs13
|
| 218 |
+
VSCODE_GIT_ASKPASS_EXTRA_ARGS=
|
| 219 |
+
VSCODE_GIT_ASKPASS_MAIN=/home/alison.cs13/.vscode-server/cli/servers/Stable-4437686ffebaf200fa4a6e6e67f735f3edf24ada/server/extensions/git/dist/askpass-main.js
|
| 220 |
+
VSCODE_GIT_ASKPASS_NODE=/home/alison.cs13/.vscode-server/cli/servers/Stable-4437686ffebaf200fa4a6e6e67f735f3edf24ada/server/node
|
| 221 |
+
VSCODE_GIT_IPC_HANDLE=/run/user/1109/vscode-git-a784703e7c.sock
|
| 222 |
+
VSCODE_IPC_HOOK_CLI=/run/user/1109/vscode-ipc-f85ac3c8-43d6-4f74-9af5-5e756b3860de.sock
|
| 223 |
+
WANDB_MODE=online
|
| 224 |
+
WANDB_SERVICE=2-3993654-tcp-localhost-41861
|
| 225 |
+
WORLD_SIZE=4
|
| 226 |
+
XDG_DATA_DIRS=/usr/local/share:/usr/share:/var/lib/snapd/desktop
|
| 227 |
+
XDG_RUNTIME_DIR=/run/user/1109
|
| 228 |
+
XDG_SESSION_CLASS=user
|
| 229 |
+
XDG_SESSION_ID=28663
|
| 230 |
+
XDG_SESSION_TYPE=tty
|
| 231 |
+
ZE_AFFINITY_MASK=0,1,2,3
|
| 232 |
+
_=/mnt/home/alison.cs13/anaconda3/envs/safe-rlhf-12.4/bin/deepspeed
|
| 233 |
+
_CE_CONDA=
|
| 234 |
+
_CE_M=
|
| 235 |
+
_LMFILES_=/cm/local/modulefiles/gcc/13.1.0:/cm/local/modulefiles/slurm/slurm/23.02.8
|
| 236 |
+
_LMFILES__modshare=/cm/local/modulefiles/gcc/13.1.0:1:/cm/local/modulefiles/slurm/slurm/23.02.8:1
|
stderr.log
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
stdout.log
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|