metadata

license: mit
base_model: laion/CLIP-ViT-B-32-laion2B-s34B-b79K
tags:
  - generated_from_trainer
model-index:
  - name: laion-finetuned_v5e7_epoch10_fold0_threshold3
    results: []

laion-finetuned_room luxury annotater

This model is a fine-tuned version of laion/CLIP-ViT-B-32-laion2B-s34B-b79K on an Wahi private 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: 1e-06
train_batch_size: 384
eval_batch_size: 24
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear

Training results

Framework versions

Transformers 4.37.2
Pytorch 2.0.1+cu117
Datasets 2.14.4
Tokenizers 0.15.0