add

models/LLaVA/scripts/train_lightning_mpt.sh

@@ -0,0 +1,74 @@
+#!/bin/bash
+
+# Pretraining (2 hours)
+torchrun --nnodes=1 --nproc_per_node=8 --master_port=25001 \
+    llava/train/train_mem.py \
+    --model_name_or_path mosaicml/mpt-7b-chat \
+    --version v1 \
+    --data_path /path/to/blip_laion_cc_sbu_558k.json \
+    --image_folder /path/to/blip_laion_cc_sbu_558k \
+    --vision_tower openai/clip-vit-large-patch14 \
+    --tune_mm_mlp_adapter True \
+    --mm_vision_select_layer -2 \
+    --mm_use_im_start_end \
+    --bf16 True \
+    --output_dir ./checkpoints/llava-lightning-mpt-7b-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 2400 \
+    --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
+
+# Extract projector features
+python scripts/extract_mm_projector.py \
+  --model_name_or_path ./checkpoints/llava-lightning-mpt-7b-pretrain \
+  --output ./checkpoints/mm_projector/llava-lightning-mpt-7b-pretrain.bin
+
+# Visual instruction tuning (1 hour)
+torchrun --nnodes=1 --nproc_per_node=8 --master_port=25001 \
+    llava/train/train_mem.py \
+    --model_name_or_path mosaicml/mpt-7b-chat \
+    --version v1 \
+    --data_path /path/to/llava_instruct_80k.json \
+    --image_folder /Data/haotian/coco/train2014 \
+    --vision_tower openai/clip-vit-large-patch14 \
+    --pretrain_mm_mlp_adapter ./checkpoints/mm_projector/llava-lightning-mpt-7b-pretrain.bin \
+    --mm_vision_select_layer -2 \
+    --mm_use_im_start_end True \
+    --bf16 True \
+    --output_dir ./checkpoints \
+    --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 5000 \
+    --save_total_limit 1 \
+    --learning_rate 2e-5 \
+    --weight_decay 0. \
+    --warmup_ratio 0.03 \
+    --lr_scheduler_type "cosine" \
+    --logging_steps 1 \
+    --tf32 True \
+    --fsdp "full_shard auto_wrap" \
+    --fsdp_transformer_layer_cls_to_wrap 'MPTBlock' \
+    --model_max_length 2048 \
+    --gradient_checkpointing True \
+    --dataloader_num_workers 4 \
+    --lazy_preprocess True \
+    --report_to wandb