emendes3/llava_13b_city_synthetic

<!-- 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. -->

llava13bcity_synthetic

This model is a fine-tuned version of liuhaotian/llava-v1.5-13b on an unknown dataset. It achieves the following results on the evaluation set:

• —eval_loss: 0.0047
• —eval_runtime: 152.033
• —evalsamplesper_second: 12.405
• —evalstepsper_second: 0.388
• —epoch: 19.0
• —step: 1121

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
• —trainbatchsize: 4
• —evalbatchsize: 4
• —seed: 42
• —distributed_type: multi-GPU
• —num_devices: 8
• —totaltrainbatch_size: 32
• —totalevalbatch_size: 32
• —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• —lrschedulertype: cosine
• —lrschedulerwarmup_ratio: 0.03
• —num_epochs: 20.0

Framework versions

• —PEFT 0.10.0
• —Transformers 4.37.2
• —Pytorch 2.1.2+cu121
• —Tokenizers 0.15.1