Comments (1)
@haotian-liu My training hyperparameters remain consistent with you provided. Here are my partial train logs and MME results:
100%|██████████| 10396/10396 [22:39:17<00:00, 9.15s/it]
{'train_runtime': 81561.6745, 'train_samples_per_second': 8.157, 'train_steps_per_second': 0.127, 'train_loss': 3.424769993772549, 'epoch': 1.0}
=========== Perception ===========
total score: 545.515306122449
existence score: 48.333333333333336
count score: 50.0
position score: 48.333333333333336
color score: 55.00000000000001
posters score: 46.59863945578232
celebrity score: 55.0
scene score: 55.0
landmark score: 68.25
artwork score: 71.5
OCR score: 47.5
=========== Cognition ===========
total score: 197.5
commonsense_reasoning score: 45.0
numerical_calculation score: 57.5
text_translation score: 75.0
code_reasoning score: 20.0
from llava.
Related Issues (20)
- [Question] about the --vision_tower in the scritps
- Can we use this model to identify between real and AI generated/fake image?
- load_dataset(liuhaotian/LLaVA-Instruct-150K) fails with error, when generating train split: 394276 examples HOT 1
- How to perform cross-validation during the fine-tuning process?[Question]
- Does vistion tower trained during starge 2 (Visual Instruction Tuning)?
- Batch size to reproduce llava-1.5-7B
- [Usage] How to resume a LoRA training ?
- [Usage] Error when loading adapter_model.safetensors HOT 2
- [Usage] When running Example Code in colab, CuDA out of memory is reported HOT 2
- [Usage] Merging LoRA weights using the script "LLaVA/scripts/merge_lora_weights.py" results in a model size about two times larger than the original Llama2 model.
- [Usage] Both demo links are down! Would you please check them out? HOT 1
- How to fine-tune llava-v1.6-mistral-7b on GQA dataset HOT 2
- [Question] Clarification on the Threshold for "Sufficient" Task-Specific Data for Full-Model Finetuning
- [Question] No matter what I ask, my model always gives the same answer. HOT 1
- [Question] Evaluate on OKVQA
- [Usage] Llava-Gemma Pretraining + Fine tuning Usage issue and missing Fine tuned projector.bin
- [Question] Is there a way to make llava-v1.6-mistral-7b-hf always return json?
- Pip install got an error So, do you install the llava in a new docker?
- [Discussion] Request for Guidance on Stage Two: Converting LLaVA-V1.6 into 4-bit GGUF Format (PAPER)
- [Usage] Merging LoRa weights into llava-13b fails with bizarre error
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 llava.