mirror of
https://github.com/SakanaAI/doc-to-lora.git
synced 2026-07-23 17:01:04 +02:00
34 lines
No EOL
1,005 B
Bash
34 lines
No EOL
1,005 B
Bash
#!/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
|
|
|
|
uv run accelerate launch --num_processes=4 --gradient_accumulation_steps=2 --gradient_clipping=1.0 \
|
|
--gpu_ids all --main_process_port 29561 intx_sft.py configs/squad.yaml \
|
|
--model_name_or_path=google/gemma-3-1b-it \
|
|
--num_train_epochs=5 \
|
|
--per_device_train_batch_size=-1 \
|
|
--gradient_accumulation_steps=2 \
|
|
--per_device_eval_batch_size=64 \
|
|
--target_modules=down_proj \
|
|
--num_self_attends_per_block=8 \
|
|
--num_latent_factor=1 \
|
|
--num_pre_head_layers=1 \
|
|
--lora_r=8 \
|
|
--eval_steps=1000 \
|
|
--save_steps=1000 \
|
|
--learning_rate=4e-5 \
|
|
--lora_dropout=0.0 \
|
|
--neftune_noise_alpha=5 \
|
|
--add_negative_prompt=False \
|
|
--add_repeat_prompt=False \
|
|
--use_sequence_packing=True \
|
|
--max_packed_inp_len=16000 \
|
|
--max_packed_ctx_len=32000 \
|
|
--per_rank_gen=True \
|
|
--per_layer_processing=True \
|
|
--gen_lora_l1_reg_coef=0.1 \
|
|
--logging_steps=50 |