blip_finetuned_fashion

This model is a fine-tuned version of Salesforce/blip-vqa-base on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 0.0916

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: 5e-05
  • train_batch_size: 4
  • eval_batch_size: 8
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 10

Training results

Training Loss Epoch Step Validation Loss
9.4382 1.0 28 8.7410
5.7906 2.0 56 4.4909
2.6817 3.0 84 1.9184
0.6839 4.0 112 0.4660
0.1304 5.0 140 0.1403
0.0621 6.0 168 0.1171
0.0322 7.0 196 0.0961
0.0178 8.0 224 0.0963
0.0119 9.0 252 0.0918
0.0088 10.0 280 0.0916

Framework versions

  • Transformers 4.38.2
  • Pytorch 2.2.1+cu121
  • Datasets 2.18.0
  • Tokenizers 0.15.2
Downloads last month
14
Safetensors
Model size
385M params
Tensor type
F32
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for Ornelas/blip_finetuned_fashion

Finetuned
(5)
this model