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

scripts

Browse source
This commit is contained in:
51616 2025-07-29 07:00:03 +00:00
parent 29719f4d19
commit 2b824ed813
3 changed files with 6 additions and 6 deletions
Download patch file Download diff file Expand all files Collapse all files

4
scripts/short_ctx/gemma_qa_short_ctx_perceiver.sh
View file

@ -13,9 +13,9 @@ echo "Using port: $port"
uv run accelerate launch --main_process_port $port \
--num_processes=4 --gpu_ids all intx_sft.py $1 \
--model_name_or_path=google/gemma-2-2b-it \
--max_steps=10_000 \
--max_steps=30_000 \
--per_device_train_batch_size=-1 \
--gradient_accumulation_steps=2 \
--gradient_accumulation_steps=4 \
--per_device_eval_batch_size=64 \
--target_modules=down_proj \
--num_blocks=8 \

4
scripts/short_ctx/gemma_qa_short_ctx_perceiver_l2l.sh
View file

@ -13,9 +13,9 @@ echo "Using port: $port"
uv run accelerate launch --main_process_port $port \
--num_processes=4 --gpu_ids all intx_sft.py $1 \
--model_name_or_path=google/gemma-2-2b-it \
--max_steps=10_000 \
--max_steps=30_000 \
--per_device_train_batch_size=-1 \
--gradient_accumulation_steps=4 \
--gradient_accumulation_steps=8 \
--per_device_eval_batch_size=32 \
--target_modules=down_proj \
--num_blocks=8 \

4
scripts/short_ctx/gemma_qa_short_ctx_perceiver_l2l_max_qas_per_sample_1.sh
View file

@ -13,9 +13,9 @@ echo "Using port: $port"
uv run accelerate launch --main_process_port $port \
--num_processes=4 --gpu_ids all intx_sft.py $1 \
--model_name_or_path=google/gemma-2-2b-it \
--max_steps=10_000 \
--max_steps=30_000 \
--per_device_train_batch_size=-1 \
--gradient_accumulation_steps=4 \
--gradient_accumulation_steps=8 \
--per_device_eval_batch_size=32 \
--target_modules=down_proj \
--num_blocks=8 \