README.md

metadata

license: apache-2.0
base_model: microsoft/beit-large-patch16-224
tags:
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - accuracy
model-index:
  - name: smids_10x_beit_large_adamax_001_fold1
    results:
      - task:
          name: Image Classification
          type: image-classification
        dataset:
          name: imagefolder
          type: imagefolder
          config: default
          split: test
          args: default
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.9048414023372288

smids_10x_beit_large_adamax_001_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: 0.9751
• Accuracy: 0.9048

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: 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
0.3471	1.0	751	0.3720	0.8631
0.2879	2.0	1502	0.4078	0.8364
0.2355	3.0	2253	0.4002	0.8831
0.2335	4.0	3004	0.2992	0.8831
0.1816	5.0	3755	0.3290	0.8965
0.1386	6.0	4506	0.3986	0.8898
0.1637	7.0	5257	0.4542	0.8681
0.0627	8.0	6008	0.4567	0.8965
0.0985	9.0	6759	0.3926	0.9015
0.1363	10.0	7510	0.4519	0.8848
0.0463	11.0	8261	0.5853	0.8898
0.023	12.0	9012	0.5711	0.8865
0.0292	13.0	9763	0.5829	0.8932
0.0137	14.0	10514	0.5739	0.8965
0.0034	15.0	11265	0.6922	0.8815
0.0201	16.0	12016	0.6833	0.8948
0.0068	17.0	12767	0.7845	0.8898
0.0084	18.0	13518	0.6851	0.8781
0.0033	19.0	14269	0.6219	0.8998
0.0023	20.0	15020	0.5986	0.8982
0.0011	21.0	15771	0.6825	0.8965
0.0011	22.0	16522	0.7971	0.8932
0.027	23.0	17273	0.5546	0.9098
0.0061	24.0	18024	0.6400	0.8932
0.0001	25.0	18775	0.6875	0.8965
0.0111	26.0	19526	0.7316	0.8965
0.0029	27.0	20277	0.8142	0.8865
0.0004	28.0	21028	0.7441	0.8915
0.0043	29.0	21779	0.7052	0.8965
0.0	30.0	22530	0.7049	0.9048
0.0	31.0	23281	0.8253	0.9149
0.0005	32.0	24032	0.6696	0.9065
0.0001	33.0	24783	0.8050	0.9065
0.0	34.0	25534	0.8833	0.9015
0.0	35.0	26285	0.8344	0.9032
0.0	36.0	27036	0.8190	0.8982
0.0	37.0	27787	0.8357	0.9032
0.0	38.0	28538	0.9401	0.9015
0.0	39.0	29289	0.7726	0.9115
0.0	40.0	30040	0.8975	0.8965
0.0	41.0	30791	0.8489	0.9065
0.0	42.0	31542	0.9519	0.8998
0.0	43.0	32293	0.9084	0.9032
0.0	44.0	33044	0.9097	0.9048
0.0	45.0	33795	0.9438	0.9098
0.0	46.0	34546	0.9461	0.9082
0.0	47.0	35297	0.9632	0.9048
0.0	48.0	36048	0.9598	0.9065
0.0	49.0	36799	0.9723	0.9048
0.0	50.0	37550	0.9751	0.9048

Framework versions

• Transformers 4.32.1
• Pytorch 2.1.0+cu121
• Datasets 2.12.0
• Tokenizers 0.13.2