Edit model card

hushem_5x_beit_base_adamax_00001_fold5

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: 0.6249
  • Accuracy: 0.8049

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
1.2175 1.0 28 1.0638 0.5610
0.735 2.0 56 0.7985 0.6585
0.4163 3.0 84 0.6796 0.7561
0.279 4.0 112 0.5555 0.7805
0.1477 5.0 140 0.5113 0.7805
0.1105 6.0 168 0.4149 0.8049
0.0639 7.0 196 0.4515 0.8049
0.0449 8.0 224 0.4623 0.8049
0.0253 9.0 252 0.4728 0.8049
0.0316 10.0 280 0.4972 0.8049
0.0123 11.0 308 0.4732 0.8049
0.0128 12.0 336 0.4924 0.8049
0.0101 13.0 364 0.4570 0.8049
0.0111 14.0 392 0.4394 0.8049
0.0107 15.0 420 0.4434 0.8293
0.0064 16.0 448 0.5061 0.8049
0.0038 17.0 476 0.4264 0.8049
0.0038 18.0 504 0.4542 0.8049
0.0106 19.0 532 0.5345 0.8049
0.0043 20.0 560 0.5084 0.8049
0.0022 21.0 588 0.5182 0.8049
0.0136 22.0 616 0.4661 0.8049
0.005 23.0 644 0.4938 0.8293
0.0094 24.0 672 0.5151 0.8293
0.0106 25.0 700 0.5393 0.8049
0.0023 26.0 728 0.5196 0.8293
0.0018 27.0 756 0.5228 0.8293
0.0039 28.0 784 0.5509 0.8049
0.002 29.0 812 0.5472 0.8049
0.0023 30.0 840 0.5687 0.8049
0.0017 31.0 868 0.5888 0.8049
0.0023 32.0 896 0.5665 0.8049
0.0021 33.0 924 0.5478 0.8049
0.002 34.0 952 0.5621 0.8049
0.0027 35.0 980 0.5915 0.8049
0.0012 36.0 1008 0.6391 0.8049
0.0008 37.0 1036 0.6817 0.8049
0.0029 38.0 1064 0.6733 0.8049
0.0009 39.0 1092 0.6240 0.8049
0.0018 40.0 1120 0.6057 0.8049
0.0019 41.0 1148 0.6204 0.8049
0.0009 42.0 1176 0.6350 0.8049
0.0017 43.0 1204 0.6368 0.8049
0.006 44.0 1232 0.6329 0.8049
0.0022 45.0 1260 0.6324 0.8049
0.0014 46.0 1288 0.6308 0.8049
0.0013 47.0 1316 0.6209 0.8049
0.0019 48.0 1344 0.6248 0.8049
0.0007 49.0 1372 0.6249 0.8049
0.0012 50.0 1400 0.6249 0.8049

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