File size: 1,460 Bytes
8874c09 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 |
#!/bin/bash
# IMPORTANT: this is the training script for the original LLaVA, NOT FOR LLaVA V1.5!
# Uncomment and set the following variables correspondingly to run this script:
# MODEL_VERSION=vicuna-v1-3-7b
# MODEL_VERSION=llama-2-7b-chat
########### DO NOT CHANGE ###########
########### USE THIS FOR BOTH ###########
PROMPT_VERSION=plain
########### DO NOT CHANGE ###########
deepspeed llava/train/train_mem.py \
--deepspeed ./scripts/zero2.json \
--model_name_or_path ./checkpoints/$MODEL_VERSION \
--version $PROMPT_VERSION \
--data_path /path/to/pretrain_data.json \
--image_folder /path/to/images \
--vision_tower openai/clip-vit-large-patch14 \
--tune_mm_mlp_adapter True \
--mm_vision_select_layer -2 \
--mm_use_im_start_end False \
--mm_use_im_patch_token False \
--bf16 True \
--output_dir ./checkpoints/llava-$MODEL_VERSION-pretrain \
--num_train_epochs 1 \
--per_device_train_batch_size 16 \
--per_device_eval_batch_size 4 \
--gradient_accumulation_steps 1 \
--evaluation_strategy "no" \
--save_strategy "steps" \
--save_steps 24000 \
--save_total_limit 1 \
--learning_rate 2e-3 \
--weight_decay 0. \
--warmup_ratio 0.03 \
--lr_scheduler_type "cosine" \
--logging_steps 1 \
--tf32 True \
--model_max_length 2048 \
--gradient_checkpointing True \
--dataloader_num_workers 4 \
--lazy_preprocess True \
--report_to wandb
|