chris/MiniGPT-4
1
0
Fork 0
mirror of https://github.com/Vision-CAIR/MiniGPT-4.git synced 2025-04-03 09:30:48 +00:00
Code Issues Packages Projects Releases Wiki Activity

remove jobs

Browse Source
This commit is contained in:
junchen14 2023-10-25 09:43:44 +03:00
parent 507deb3edb
commit aabb243107
3 changed files with 1 additions and 55 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
.gitignore vendored
View File

@ -181,4 +181,4 @@ slurm*
sbatch_generate*
eval_data/
dataset/Evaluation.md
jupyter_notebook.slurm
jupyter_notebook.slurm

24
jobs/sbatch_finetune.sh
View File

@ -1,24 +0,0 @@
#!/bin/bash
#SBATCH --mem=400G # memory pool for all cores`
#SBATCH --time 24:00:00 # time, specify max time allocation`
#SBATCH --mail-type=END,FAIL # notifications for job done & fail`
#SBATCH --mail-user=jun.chen@kaust.edu.sa
#SBATCH --gres=gpu:4
#SBATCH --cpus-per-gpu=8
#SBATCH --reservation=A100
#SBATCH --job-name=finetune_test
#SBATCH --output=/ibex/project/c2090/logs/fientune_test
cd ..
job_name=finetune_test
read LOWERPORT UPPERPORT < /proc/sys/net/ipv4/ip_local_port_range
while :
do
PORT="`shuf -i $LOWERPORT-$UPPERPORT -n 1`"
ss -lpn | grep -q ":$PORT " || break
done
torchrun --master-port ${PORT} --nproc-per-node 4 train.py --job_name=${job_name} --cfg-path train_configs/minigpt_v2_finetune.yaml

30
jobs/srun_test.sh
View File

@ -1,30 +0,0 @@
cd ..
job_name=minigpt4_v2_test
read LOWERPORT UPPERPORT < /proc/sys/net/ipv4/ip_local_port_range
while :
do
PORT="`shuf -i $LOWERPORT-$UPPERPORT -n 1`"
ss -lpn | grep -q ":$PORT " || break
done
#torchrun --master-port ${PORT} --nproc-per-node 2 train.py --job_name ${job_name} --cfg-path train_configs_llama2/336_final_v1_gqa.yaml
#torchrun --master-port ${PORT} --nproc-per-node 2 train.py --job_name ${job_name} --cfg-path train_configs_llama2/448_final_v1_gqa_ablation2.yaml
torchrun --master-port ${PORT} --nproc-per-node 2 train.py --job_name ${job_name} --cfg-path train_configs/minigpt_v2_finetune.yaml
#torchrun --master-port ${PORT} --nproc-per-node 2 train.py --job_name ${job_name} --cfg-path finetune_conversation_ablation/conversation_v2_last_336_test.yaml
#torchrun --master-port ${PORT} --nproc-per-node 2 train.py --job_name ${job_name} --cfg-path train_configs_llama2/336_final_v1_13B.yaml
# torchrun --master-port ${PORT} --nproc-per-node 2 train.py --job_name ${job_name} --cfg-path train_configs_final_ablations/448_v2_llama2.yaml
#accelerate launch train.py --job_name ${job_name} --cfg-path train_configs_final_ablations/336_v2_llama2.yaml
# torchrun --master-port ${PORT} --nproc-per-node 2 train.py --job_name ${job_name} --cfg-path train_configs_final_ablations/336_v2_llama2_clip_encoder.yaml
#best_data_ratio_336_full_dataset_lr2e4_v1.yaml