metadata

license: apache-2.0
base_model: microsoft/beit-base-patch16-224
tags:
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - accuracy
model-index:
  - name: smids_1x_beit_base_rms_0001_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: 0.6978297161936561

smids_1x_beit_base_rms_0001_fold1

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: 0.7464
Accuracy: 0.6978

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
1.1002	1.0	76	0.9320	0.5459
0.9176	2.0	152	0.9156	0.4975
0.8828	3.0	228	1.4808	0.3239
0.9116	4.0	304	0.9182	0.5058
0.9681	5.0	380	0.8261	0.5726
0.8914	6.0	456	0.8412	0.5442
0.8118	7.0	532	0.8070	0.5843
0.7886	8.0	608	0.7873	0.6144
0.8228	9.0	684	0.8018	0.5593
0.7855	10.0	760	0.8650	0.5659
0.7506	11.0	836	0.8105	0.5726
0.8105	12.0	912	0.7718	0.5760
0.7542	13.0	988	0.7814	0.6027
0.8063	14.0	1064	0.7598	0.6244
0.6853	15.0	1140	0.9554	0.5526
0.6995	16.0	1216	0.7869	0.6277
0.7413	17.0	1292	0.7345	0.6561
0.6942	18.0	1368	0.7274	0.6511
0.7698	19.0	1444	0.7431	0.6711
0.7328	20.0	1520	0.7361	0.6327
0.7002	21.0	1596	0.7435	0.6427
0.6967	22.0	1672	0.8269	0.6010
0.651	23.0	1748	0.7688	0.6528
0.6937	24.0	1824	0.7386	0.6578
0.5694	25.0	1900	0.7657	0.6277
0.6705	26.0	1976	0.7210	0.6811
0.5989	27.0	2052	0.7453	0.6561
0.6274	28.0	2128	0.7780	0.6578
0.5748	29.0	2204	0.7338	0.6845
0.6764	30.0	2280	0.7373	0.6394
0.6934	31.0	2356	0.7055	0.6845
0.6007	32.0	2432	0.7394	0.6511
0.5933	33.0	2508	0.7124	0.6795
0.5894	34.0	2584	0.7760	0.6711
0.6837	35.0	2660	0.7002	0.6628
0.5776	36.0	2736	0.7352	0.6694
0.6485	37.0	2812	0.7046	0.6878
0.5352	38.0	2888	0.7058	0.6861
0.577	39.0	2964	0.6974	0.7028
0.5712	40.0	3040	0.7122	0.6811
0.5117	41.0	3116	0.7026	0.6845
0.4908	42.0	3192	0.7187	0.7045
0.4784	43.0	3268	0.7103	0.7028
0.4739	44.0	3344	0.7027	0.7162
0.5942	45.0	3420	0.7242	0.6962
0.4258	46.0	3496	0.7593	0.6912
0.4726	47.0	3572	0.7433	0.6895
0.4422	48.0	3648	0.7412	0.6928
0.4049	49.0	3724	0.7425	0.6995
0.5059	50.0	3800	0.7464	0.6978

Framework versions

Transformers 4.35.2
Pytorch 2.1.0+cu118
Datasets 2.15.0
Tokenizers 0.15.0