Edit model card

Boya1_SGD_1-e3_20Epoch_09Momentum_Beit-base-patch16_fold1

This model is a fine-tuned version of microsoft/beit-base-patch16-224-pt22k-ft22k on the imagefolder dataset. It achieves the following results on the evaluation set:

  • Loss: 1.8239
  • Accuracy: 0.4165

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: 0.001
  • train_batch_size: 16
  • eval_batch_size: 16
  • 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: 20

Training results

Training Loss Epoch Step Validation Loss Accuracy
2.5085 1.0 924 2.4731 0.1963
2.3692 2.0 1848 2.3352 0.2465
2.3278 3.0 2772 2.2372 0.2780
2.1219 4.0 3696 2.1632 0.3044
2.2732 5.0 4620 2.1014 0.3342
2.0973 6.0 5544 2.0509 0.3511
2.0974 7.0 6468 2.0095 0.3633
2.0888 8.0 7392 1.9760 0.3698
1.9477 9.0 8316 1.9428 0.3842
1.937 10.0 9240 1.9178 0.3932
1.9658 11.0 10164 1.8968 0.3932
1.9052 12.0 11088 1.8809 0.3975
1.7933 13.0 12012 1.8676 0.4032
1.9046 14.0 12936 1.8552 0.4062
1.8301 15.0 13860 1.8450 0.4075
1.8479 16.0 14784 1.8378 0.4122
1.8401 17.0 15708 1.8313 0.4138
1.7985 18.0 16632 1.8281 0.4154
1.8691 19.0 17556 1.8245 0.4181
1.8762 20.0 18480 1.8239 0.4165

Framework versions

  • Transformers 4.35.0
  • Pytorch 2.1.0
  • Datasets 2.14.6
  • Tokenizers 0.14.1
Downloads last month
4
Safetensors
Model size
85.8M 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 onizukal/Boya1_SGD_1-e3_20Epoch_09Momentum_Beit-base-patch16_fold1

Finetuned
(60)
this model

Evaluation results