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_rms_0001_fold2
    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: 0.9001663893510815

smids_3x_beit_base_rms_0001_fold2

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: 1.0800
Accuracy: 0.9002

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: 0.0001
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
0.4112	1.0	225	0.4131	0.8602
0.2912	2.0	450	0.4363	0.8369
0.1579	3.0	675	0.3616	0.8752
0.187	4.0	900	0.2854	0.8852
0.1222	5.0	1125	0.4884	0.8835
0.0818	6.0	1350	0.4361	0.8885
0.0981	7.0	1575	0.4218	0.8769
0.1165	8.0	1800	0.5449	0.8702
0.0593	9.0	2025	0.5250	0.9002
0.0725	10.0	2250	0.5111	0.8985
0.0275	11.0	2475	0.5486	0.8702
0.0408	12.0	2700	0.6442	0.8852
0.0654	13.0	2925	0.6277	0.8968
0.0139	14.0	3150	0.6248	0.8918
0.0393	15.0	3375	0.5753	0.8935
0.0368	16.0	3600	0.6499	0.8902
0.0316	17.0	3825	0.6023	0.8918
0.0193	18.0	4050	0.7084	0.8952
0.001	19.0	4275	0.7253	0.9002
0.0578	20.0	4500	0.7248	0.8785
0.08	21.0	4725	0.6832	0.8902
0.0213	22.0	4950	0.8468	0.8902
0.008	23.0	5175	0.8669	0.8935
0.0041	24.0	5400	0.8402	0.8802
0.0205	25.0	5625	0.8106	0.8869
0.0196	26.0	5850	0.8576	0.8902
0.0001	27.0	6075	0.7352	0.8985
0.0003	28.0	6300	0.7339	0.9018
0.0078	29.0	6525	0.8497	0.8985
0.007	30.0	6750	1.0378	0.8802
0.0063	31.0	6975	0.9737	0.8902
0.0147	32.0	7200	0.9357	0.8902
0.0358	33.0	7425	0.9702	0.8885
0.0003	34.0	7650	0.7989	0.8902
0.0001	35.0	7875	0.9353	0.8885
0.0032	36.0	8100	0.8664	0.8952
0.0015	37.0	8325	0.7955	0.8968
0.0	38.0	8550	0.8664	0.8952
0.0222	39.0	8775	0.9521	0.8985
0.0042	40.0	9000	0.9427	0.8985
0.0027	41.0	9225	0.9502	0.9002
0.0	42.0	9450	1.0516	0.8935
0.0	43.0	9675	0.9695	0.8952
0.0	44.0	9900	1.0122	0.8985
0.0	45.0	10125	0.9974	0.8985
0.0	46.0	10350	1.0109	0.9002
0.0	47.0	10575	1.0770	0.8952
0.0	48.0	10800	1.0946	0.8985
0.0025	49.0	11025	1.0859	0.9002
0.002	50.0	11250	1.0800	0.9002

Framework versions

Transformers 4.32.1
Pytorch 2.1.0+cu121
Datasets 2.12.0
Tokenizers 0.13.2