Edit model card

test1

This model is a fine-tuned version of apple/mobilevit-small on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 1.1366
  • Accuracy: 0.7952
  • F1: 0.7855
  • Recall: 0.7952

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: 0.0008
  • train_batch_size: 32
  • eval_batch_size: 32
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 10
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Accuracy F1 Recall
No log 0.4554 500 0.6376 0.7896 0.7429 0.7896
0.657 0.9107 1000 0.5839 0.8109 0.7679 0.8109
0.657 1.3661 1500 0.7632 0.7322 0.7195 0.7322
0.5653 1.8215 2000 0.5927 0.8144 0.7689 0.8144
0.5653 2.2769 2500 0.5855 0.8174 0.7765 0.8174
0.5128 2.7322 3000 0.5567 0.8210 0.7931 0.8210
0.5128 3.1876 3500 0.5578 0.8214 0.7894 0.8214
0.4648 3.6430 4000 0.5699 0.8236 0.7928 0.8236
0.4648 4.0984 4500 0.6039 0.8053 0.7850 0.8053
0.411 4.5537 5000 0.5662 0.8203 0.7989 0.8203
0.411 5.0091 5500 0.6043 0.8252 0.7962 0.8252
0.3532 5.4645 6000 0.6559 0.8060 0.7915 0.8060
0.3532 5.9199 6500 0.6310 0.8175 0.7919 0.8175
0.2847 6.3752 7000 0.7075 0.8029 0.7890 0.8029
0.2847 6.8306 7500 0.8056 0.7743 0.7745 0.7743
0.2265 7.2860 8000 0.8991 0.7957 0.7875 0.7957
0.2265 7.7413 8500 0.8929 0.7904 0.7866 0.7904
0.1626 8.1967 9000 0.9503 0.8022 0.7883 0.8022
0.1626 8.6521 9500 1.0467 0.7904 0.7838 0.7904
0.1099 9.1075 10000 1.0435 0.8009 0.7877 0.8009
0.1099 9.5628 10500 1.1366 0.7952 0.7855 0.7952

Framework versions

  • Transformers 4.41.2
  • Pytorch 2.2.1
  • Datasets 2.19.1
  • Tokenizers 0.19.1
Downloads last month
8
Safetensors
Model size
4.95M 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 JoshuaKelleyDs/test1

Finetuned
(9)
this model