Gemma 3 Lithuanian Weather Caption LoRA — Run C
This is the third LoRA adapter fine-tuned for Lithuanian weather-focused image captioning.
This version uses the same number of epochs as Run A, but with a slower learning rate.
The goal of Run C is to test whether a smaller learning rate produces more stable Lithuanian captions and fewer strange phrases.
The model was trained to describe the weather in an image using short, simple Lithuanian sentences.
Task
Given an image, the model generates a short Lithuanian caption focused on:
- cloudiness
- sunlight
- precipitation
- visibility
- time of day
- general weather conditions
Base model
unsloth/gemma-3-4b-it
Dataset
Dataset: Matas5/GMM_team_task
Training examples used: 103
The dataset contains images with Lithuanian weather captions. Captions were standardized to focus mainly on weather conditions rather than unrelated objects.
Training setup
Training method: LoRA fine-tuning with Unsloth
Model loading: 4-bit quantized base model
Fine-tuning type: PEFT / LoRA adapter
Run version: C
Purpose of this run: slower learning rate for more stable outputs
Number of epochs: 3
Total training steps: approximately 78
Per-device batch size: 1
Gradient accumulation steps: 2
Number of GPUs: 2 Tesla T4 GPUs
Effective total batch size: 4
Learning rate: 1e-4
Optimizer: adamw_8bit
Gradient checkpointing: enabled
Save strategy: save every epoch
LoRA rank: 4
LoRA alpha: 8
Target modules: q_proj, v_proj
Vision layers fine-tuned: yes
Prompt used during training
Trumpai apibūdink orą šioje nuotraukoje lietuviškai. Atsakyk vienu paprastu sakiniu.
Example expected output style
Dangus giedras ir ryškiai mėlynas, debesų beveik nėra. Oras saulėtas, sausas, matomumas labai geras.
Training result summary
Run C was trained for 3 epochs, like Run A, but with a smaller learning rate.
Run A used learning rate 2e-4.
Run B used 2 epochs with learning rate 2e-4.
Run C uses 3 epochs with learning rate 1e-4.
The purpose of this run is to test whether slower parameter updates produce more natural Lithuanian text and reduce strange or unstable phrases.
Because the dataset contains only 103 training examples, the result still needs to be evaluated on unseen test images.
Intended use
This adapter is intended for a university project demonstrating fine-tuning of a vision-language model for Lithuanian weather captioning.
It is not intended for professional meteorological forecasting.
- Downloads last month
- 15