Comments (4)
Hi @Luo-Z13 , thank you for your interest. We trained the model on 4 A100 40 GB gpus. You can train on one A100 80GB or on a single 40 GB A100 by using the quantised models,in 4 or 8 bit.
from geochat.
How long your model training?
from geochat.
Hi @vvuonghn, we finetuned the model for around 10 hrs for the complete dataset, and further fine-tuned for 4-5 hours on the grounding part of the dataset. Please let me know if you have any further queries.
from geochat.
Hi @vvuonghn, we finetuned the model for around 10 hrs for the complete dataset, and further fine-tuned for 4-5 hours on the grounding part of the dataset. Please let me know if you have any further queries.
Hi @KjAeRsTuIsK ,
Thanks for you nice work.
May I ask how to fine-tune the model on the grounding part of the datasets?
I already fine-tuned it with this:
################## VICUNA ##################
PROMPT_VERSION=v1
MODEL_VERSION="vicuna-v1.5-7b"
gpu_ids=0,1,2,3
################## VICUNA ##################
deepspeed --master_port=$((RANDOM + 10000)) --include localhost:$gpu_ids geochat/train/train_mem.py \
--deepspeed ./scripts/zero2.json \
--lora_enable True \
--model_name_or_path /data/.../geochat/llava-v1.5-7b \
--version $PROMPT_VERSION \
--data_path /data/.../geochat/GeoChat_Instruct.json \
--image_folder /data/.../geochat/final_images_llava \
--vision_tower openai/clip-vit-large-patch14-336 \
--mm_projector_type mlp2x_gelu \
--pretrain_mm_mlp_adapter /data/.../geochat/llava-v1.5-mlp2x-336px-pretrain-vicuna-7b-v1.5/mm_projector.bin \
--mm_vision_select_layer -2 \
--mm_use_im_start_end False \
--mm_use_im_patch_token False \
--image_aspect_ratio pad \
--bf16 True \
--output_dir /data/.../geochat/outckpts/geochat_reproduce \
--num_train_epochs 1 \
--per_device_train_batch_size 18 \
--per_device_eval_batch_size 4 \
--gradient_accumulation_steps 2 \
--evaluation_strategy "no" \
--save_strategy "epoch" \
--save_steps 7000 \
--save_total_limit 1 \
--learning_rate 2e-4 \
--weight_decay 0. \
--warmup_ratio 0.03 \
--lr_scheduler_type "cosine" \
--logging_steps 1 \
--tf32 True \
--model_max_length 2048 \
--gradient_checkpointing True \
--lazy_preprocess True \
--dataloader_num_workers 16 \
--report_to wandb
What should I do next for fine-tuning it on the grounding part of the datasets?
I am not so familiar with the finturning of llava. Could you give me more detailed instructions when you are free recently?
Bests
from geochat.
Related Issues (20)
- How to calculate the metrics [email protected], [email protected], ROUGE and METEOR score in table 7, 8, 9? HOT 6
- get_chunk method in batch_geochat_scene.py seems to be undefined HOT 1
- Minimum memory for the training process
- how to run the lora finetuned model? HOT 6
- metrics about region captioning HOT 2
- training data corrupted HOT 1
- is training necessary ?
- Model for visual grounding
- Calculation of metrics
- Evaluation results about Grounding
- The results of MiniGPT in the paper HOT 2
- when training had an error!
- License for Commercial use
- merge lora
- how to finetune on my custom dataset
- training data corrupt
- Using transformers to use geochat directly
- The error encountered when using ZeRO-2 for training.
- Could you describe the procedure of reproduce the GeoChat? HOT 1
- Multi images HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from geochat.