File size: 1,610 Bytes
74b17e0 |
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 |
DATA_PATH="/home/ai/data/llava/dataset/text_files/llava_v1_5_mix665k.json"
IMAGE_PATH="/home/ai/data/llava/dataset"
MODEL_MAX_LENGTH=3072
OUTPUT_DIR="/mnt/data/sata/yinghu/checkpoints/llava_factory/custom-finetune-TinyLLaVA-Phi-2-SigLIP-3.1B-lora"
deepspeed --include localhost:0,1,2,3 --master_port 29501 tinyllava/train/custom_finetune.py \
--deepspeed ./scripts/zero2.json \
--data_path $DATA_PATH \
--image_folder $IMAGE_PATH \
--is_multimodal True \
--conv_version phi \
--mm_vision_select_layer -2 \
--image_aspect_ratio square \
--fp16 True \
--training_recipe lora \
--tune_type_llm lora \
--tune_type_vision_tower frozen \
--tune_vision_tower_from_layer 0 \
--tune_type_connector full \
--lora_r 128 \
--lora_alpha 256 \
--group_by_modality_length False \
--pretrained_model_path "tinyllava/TinyLLaVA-Phi-2-SigLIP-3.1B" \
--output_dir $OUTPUT_DIR \
--num_train_epochs 1 \
--per_device_train_batch_size 4 \
--per_device_eval_batch_size 4 \
--gradient_accumulation_steps 8 \
--evaluation_strategy "no" \
--save_strategy "steps" \
--save_steps 50000 \
--save_total_limit 1 \
--learning_rate 1e-4 \
--weight_decay 0. \
--warmup_ratio 0.03 \
--lr_scheduler_type "cosine" \
--logging_steps 1 \
--tf32 False \
--model_max_length $MODEL_MAX_LENGTH \
--gradient_checkpointing True \
--dataloader_num_workers 8 \
--lazy_preprocess True \
--report_to tensorboard \
--tokenizer_use_fast False \
--run_name custom-finetune-TinyLLaVA-Phi-2-SigLIP-3.1B-lora
|