apunkt/doc-to-lora
1
0
Fork 0
mirror of https://github.com/SakanaAI/doc-to-lora.git synced 2026-07-23 17:01:04 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions

iclr 2026

Browse source
This commit is contained in:
51616 2025-09-29 00:39:17 +09:00
parent 76bf6981ba
commit c21ba2b481
20 changed files with 1204 additions and 23 deletions
Download patch file Download diff file Expand all files Collapse all files

30
scripts/large_exp/gemma_qa_exp_4_gpus.sh Normal file
View file

@ -0,0 +1,30 @@
#!/bin/bash
#SBATCH --job-name=ctxlora
#SBATCH --nodes=1
#SBATCH --partition=sakura-gpu
#SBATCH --gpus=4
#SBATCH --output=slurm_logs/%x-%j.out
#SBATCH --error=slurm_logs/%x-%j.out
port=$((10000 + ($SLURM_JOBID % 50000)))
echo "Using port: $port"
# Default arguments - these can be overridden by passing arguments to this script
default_args=(
"--model_name_or_path=google/gemma-2-2b-it"
# "--max_steps=50_000"
"--num_train_epochs=1"
"--target_modules=down_proj"
"--lora_r=8"
"--eval_strategy=no"
"--max_qas_len=2048"
"--max_qas_per_sample=1"
"--per_rank_gen=True"
"--per_layer_processing=True"
"--gen_lora_l1_reg_coef=0.1"
)
# Pass all script arguments to the training command
# $1 comes first, then defaults, then remaining arguments (which can override defaults)
uv run accelerate launch --config_file accelerate_config.yaml --main_process_port $port \
--num_processes=4 --gpu_ids all train.py $1 "${default_args[@]}" "${@:2}"

30
scripts/large_exp/gemma_qa_exp_8_gpus.sh Normal file
View file

@ -0,0 +1,30 @@
#!/bin/bash
#SBATCH --job-name=ctxlora
#SBATCH --nodes=1
#SBATCH --partition=sakura-gpu
#SBATCH --gpus=8
#SBATCH --output=slurm_logs/%x-%j.out
#SBATCH --error=slurm_logs/%x-%j.out
port=$((10000 + ($SLURM_JOBID % 50000)))
echo "Using port: $port"
# Default arguments - these can be overridden by passing arguments to this script
default_args=(
"--model_name_or_path=google/gemma-2-2b-it"
# "--max_steps=50_000"
"--num_train_epochs=1"
"--target_modules=down_proj"
"--lora_r=8"
"--eval_strategy=no"
"--max_qas_len=2048"
"--max_qas_per_sample=1"
"--per_rank_gen=True"
"--per_layer_processing=True"
"--gen_lora_l1_reg_coef=0.1"
)
# Pass all script arguments to the training command
# $1 comes first, then defaults, then remaining arguments (which can override defaults)
uv run accelerate launch --config_file accelerate_config.yaml --main_process_port $port \
--num_processes=8 --gpu_ids all train.py $1 "${default_args[@]}" "${@:2}"

10
scripts/sbatch_1_gpu.sh Normal file
View file

@ -0,0 +1,10 @@
#!/bin/bash
#SBATCH --job-name=ctxlora
#SBATCH --nodes=1
#SBATCH --partition=sakura-gpu
#SBATCH --gpus=1
#SBATCH --output=slurm_logs/%x-%j.out
#SBATCH --error=slurm_logs/%x-%j.out
"$@"