base_model: Qwen/Qwen2.5-VL-7B-Instruct

processor_type: AutoProcessor
trust_remote_code: true

load_in_8bit: false
load_in_4bit: true
bf16: true
fp16: false

adapter: lora
lora_r: 16
lora_alpha: 32
lora_dropout: 0.05
lora_target_modules:
  - q_proj
  - k_proj
  - v_proj
  - o_proj
  - gate_proj
  - up_proj
  - down_proj

datasets:
  - path: Legad/scangas-images
    type: chat_template
    field_messages: messages
    field_images: images

remove_unused_columns: false
skip_prepare_dataset: true
sample_packing: false

sequence_len: 2048
micro_batch_size: 1
gradient_checkpointing: true
gradient_accumulation_steps: 4
num_epochs: 10
learning_rate: 2e-4
optimizer: adamw_bnb_8bit
lr_scheduler: cosine

output_dir: ./outputs/qwen25-vl-finetuned
save_safetensors: true

outputs/qwen25-vl-finetuned

This model is a fine-tuned version of Qwen/Qwen2.5-VL-7B-Instruct on the Legad/scangas-images dataset.

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 0.0002
train_batch_size: 1
eval_batch_size: 1
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 4
optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 5
training_steps: 188

Training results

Framework versions

PEFT 0.17.1
Transformers 4.57.0
Pytorch 2.7.1+cu126
Datasets 4.0.0
Tokenizers 0.22.1

Legad/qwen25-vl-scangas

outputs/qwen25-vl-finetuned

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

Legad/
qwen25-vl-scangas