Edit model card

Boya2_3Class_RMSprop_1e5_20Epoch_Beit-large-224_fold1

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

  • Loss: 1.5790
  • Accuracy: 0.8549

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: 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: 10

Training results

Training Loss Epoch Step Validation Loss Accuracy
0.3103 1.0 914 0.3588 0.8494
0.3671 2.0 1828 0.3382 0.8669
0.2679 3.0 2742 0.4568 0.8491
0.13 4.0 3656 0.7675 0.8595
0.0539 5.0 4570 1.0063 0.8543
0.0034 6.0 5484 1.3345 0.8543
0.001 7.0 6398 1.4146 0.8562
0.0013 8.0 7312 1.6343 0.8529
0.0023 9.0 8226 1.5956 0.8486
0.0001 10.0 9140 1.5790 0.8549

Framework versions

  • Transformers 4.32.1
  • Pytorch 2.0.1
  • Datasets 2.12.0
  • Tokenizers 0.13.2
Downloads last month
0
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/Boya2_3Class_RMSprop_1e5_20Epoch_Beit-large-224_fold1

Finetuned
(95)
this model

Evaluation results