qwen2_2b_lora_expert_chart-102400

<h2 align="center"> Linear Model Merging Unlocks Simple and Scalable Multimodal Data Mixture Optimization <br>

</h2>

This is an official checkpoint from the paper: "Linear Model Merging Unlocks Simple and Scalable Multimodal Data Mixture Optimization " (link). See the official implementation for more information on how to use the models.

qwen2_2b_lora_expert_chart-102400

This model is a fine-tuned version of Qwen/Qwen2-VL-2B on a custom dataset with Chart data (~100k samples).

It achieves the following results on the evaluation set:

• Loss: 0.9304

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 2e-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• distributed_type: multi-GPU
• num_devices: 4
• gradient_accumulation_steps: 4
• total_train_batch_size: 128
• total_eval_batch_size: 32
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: cosine
• lr_scheduler_warmup_ratio: 0.1
• training_steps: 800

Training results

Framework versions

• PEFT 0.15.2
• Transformers 4.52.4
• Pytorch 2.7.1+cu126
• Datasets 3.6.0
• Tokenizers 0.21.1