README.md

metadata

license: apache-2.0
base_model: microsoft/beit-base-patch16-224
tags:
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - accuracy
model-index:
  - name: smids_3x_beit_base_adamax_001_fold4
    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: 0.8533333333333334

smids_3x_beit_base_adamax_001_fold4

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: 1.5511
• Accuracy: 0.8533

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
0.4815	1.0	225	0.6186	0.7683
0.3544	2.0	450	0.5568	0.81
0.3541	3.0	675	0.4838	0.8283
0.3428	4.0	900	0.5170	0.8317
0.2833	5.0	1125	0.5822	0.7917
0.2012	6.0	1350	0.4801	0.8333
0.1747	7.0	1575	0.5354	0.8283
0.244	8.0	1800	0.5484	0.8467
0.2186	9.0	2025	0.6193	0.8167
0.155	10.0	2250	0.5230	0.8483
0.088	11.0	2475	0.6574	0.8367
0.1048	12.0	2700	0.5983	0.8517
0.0758	13.0	2925	0.7255	0.835
0.0236	14.0	3150	0.7448	0.835
0.088	15.0	3375	0.9152	0.84
0.0685	16.0	3600	0.9354	0.8167
0.0326	17.0	3825	0.9022	0.8417
0.0167	18.0	4050	0.9397	0.8417
0.0222	19.0	4275	0.9135	0.8433
0.0409	20.0	4500	1.1656	0.8467
0.0192	21.0	4725	1.0036	0.8617
0.0016	22.0	4950	0.9822	0.8467
0.0233	23.0	5175	0.9225	0.845
0.0233	24.0	5400	1.0565	0.8483
0.0482	25.0	5625	1.2063	0.835
0.005	26.0	5850	1.0210	0.8467
0.0014	27.0	6075	1.0482	0.8517
0.0002	28.0	6300	1.2044	0.8383
0.0037	29.0	6525	1.0861	0.8533
0.0174	30.0	6750	1.1444	0.85
0.0	31.0	6975	1.2721	0.8567
0.0109	32.0	7200	1.2042	0.8583
0.0095	33.0	7425	1.1796	0.8517
0.0112	34.0	7650	1.2147	0.8583
0.0005	35.0	7875	1.2717	0.85
0.0001	36.0	8100	1.3234	0.8517
0.0015	37.0	8325	1.3845	0.8567
0.0007	38.0	8550	1.3111	0.8583
0.0	39.0	8775	1.3423	0.8567
0.0	40.0	9000	1.3863	0.855
0.0	41.0	9225	1.3890	0.8567
0.0025	42.0	9450	1.5279	0.855
0.0	43.0	9675	1.5233	0.855
0.0023	44.0	9900	1.5389	0.8567
0.0	45.0	10125	1.5451	0.8517
0.0	46.0	10350	1.5273	0.8517
0.0	47.0	10575	1.5407	0.8517
0.0	48.0	10800	1.5468	0.8517
0.0	49.0	11025	1.5542	0.8533
0.0	50.0	11250	1.5511	0.8533

Framework versions

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