Lelouchrx/Qwen2.5-VL-3B-Instruct_lora_r2r

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->

Qwen2.5-VL-3B-Instructlorar2r

This model is a LoRA adapter fine-tuned on Qwen/Qwen2.5-VL-3B-Instruct using the R2R VLN 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: 2e-05
• —trainbatchsize: 32
• —evalbatchsize: 8
• —seed: 42
• —distributed_type: multi-GPU
• —num_devices: 2
• —gradientaccumulationsteps: 4
• —totaltrainbatch_size: 256
• —totalevalbatch_size: 16
• —optimizer: Use OptimizerNames.ADAMWTORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizerargs=No additional optimizer arguments
• —lrschedulertype: linear
• —lrschedulerwarmup_ratio: 0.03
• —num_epochs: 3.0

Training results

Framework versions

• —PEFT 0.17.1
• —Transformers 4.57.1
• —Pytorch 2.8.0+cu128
• —Datasets 4.0.0
• —Tokenizers 0.22.2