Edit model card

hushem_5x_beit_base_adamax_00001_fold3

This model is a fine-tuned version of microsoft/beit-base-patch16-224 on the imagefolder dataset. It achieves the following results on the evaluation set:

  • Loss: 0.4974
  • Accuracy: 0.9070

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-05
  • 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
  • lr_scheduler_warmup_ratio: 0.1
  • num_epochs: 50

Training results

Training Loss Epoch Step Validation Loss Accuracy
1.2118 1.0 28 1.1325 0.6047
0.7198 2.0 56 0.8388 0.6744
0.3881 3.0 84 0.6224 0.7674
0.2597 4.0 112 0.4679 0.8140
0.1551 5.0 140 0.4682 0.8140
0.1015 6.0 168 0.3870 0.8372
0.0767 7.0 196 0.3615 0.8837
0.0522 8.0 224 0.3630 0.8837
0.0344 9.0 252 0.4112 0.8837
0.0303 10.0 280 0.4026 0.8837
0.0199 11.0 308 0.3842 0.9070
0.0106 12.0 336 0.3943 0.8605
0.0205 13.0 364 0.3879 0.9070
0.008 14.0 392 0.3444 0.8837
0.0066 15.0 420 0.3829 0.9070
0.0068 16.0 448 0.4064 0.8837
0.0104 17.0 476 0.3534 0.9302
0.0048 18.0 504 0.3744 0.9070
0.0062 19.0 532 0.4146 0.9070
0.0025 20.0 560 0.3803 0.9070
0.0032 21.0 588 0.4244 0.9070
0.0031 22.0 616 0.4663 0.9070
0.0021 23.0 644 0.4157 0.9070
0.0026 24.0 672 0.4816 0.9070
0.0013 25.0 700 0.4216 0.9070
0.0017 26.0 728 0.4591 0.9070
0.0021 27.0 756 0.4515 0.9070
0.0024 28.0 784 0.4442 0.8837
0.0026 29.0 812 0.4504 0.9070
0.0009 30.0 840 0.4703 0.9070
0.0047 31.0 868 0.4689 0.9070
0.0067 32.0 896 0.4798 0.9070
0.0009 33.0 924 0.5058 0.9070
0.0013 34.0 952 0.4786 0.9070
0.0022 35.0 980 0.4689 0.9070
0.009 36.0 1008 0.4633 0.9070
0.0009 37.0 1036 0.4823 0.9070
0.0013 38.0 1064 0.4868 0.9070
0.0024 39.0 1092 0.5030 0.9070
0.004 40.0 1120 0.4969 0.9070
0.0014 41.0 1148 0.4951 0.9070
0.0017 42.0 1176 0.4894 0.9070
0.0014 43.0 1204 0.4881 0.9070
0.0013 44.0 1232 0.4878 0.9070
0.0022 45.0 1260 0.4914 0.9070
0.0023 46.0 1288 0.4962 0.9070
0.0015 47.0 1316 0.4961 0.9070
0.0017 48.0 1344 0.4974 0.9070
0.0007 49.0 1372 0.4974 0.9070
0.0006 50.0 1400 0.4974 0.9070

Framework versions

  • Transformers 4.35.2
  • Pytorch 2.1.0+cu118
  • Datasets 2.15.0
  • Tokenizers 0.15.0
Downloads last month
1
Safetensors
Model size
85.8M params
Tensor type
F32
·
Inference API
Drag image file here or click to browse from your device
This model can be loaded on Inference API (serverless).

Finetuned from

Evaluation results