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_00001_fold3
    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: 0.9066666666666666

smids_3x_beit_base_adamax_00001_fold3

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: 0.8012
Accuracy: 0.9067

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: 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
0.3558	1.0	225	0.2857	0.8817
0.2025	2.0	450	0.2548	0.9083
0.1598	3.0	675	0.2521	0.92
0.1219	4.0	900	0.2685	0.9067
0.1177	5.0	1125	0.2855	0.9167
0.0821	6.0	1350	0.3265	0.915
0.035	7.0	1575	0.3390	0.9133
0.0488	8.0	1800	0.3876	0.91
0.0333	9.0	2025	0.4069	0.9183
0.0137	10.0	2250	0.4823	0.895
0.0425	11.0	2475	0.4830	0.91
0.0131	12.0	2700	0.5278	0.9067
0.0362	13.0	2925	0.5365	0.91
0.0127	14.0	3150	0.5604	0.91
0.0059	15.0	3375	0.5988	0.9067
0.0457	16.0	3600	0.6291	0.8983
0.0096	17.0	3825	0.6121	0.905
0.0291	18.0	4050	0.6425	0.91
0.0279	19.0	4275	0.6328	0.9017
0.006	20.0	4500	0.7129	0.905
0.0195	21.0	4725	0.7320	0.9017
0.0002	22.0	4950	0.7512	0.9017
0.0352	23.0	5175	0.7248	0.9067
0.0032	24.0	5400	0.7414	0.9
0.0649	25.0	5625	0.7106	0.915
0.0454	26.0	5850	0.7165	0.91
0.0011	27.0	6075	0.7232	0.915
0.0041	28.0	6300	0.7095	0.9117
0.0099	29.0	6525	0.7308	0.9083
0.0129	30.0	6750	0.7895	0.9083
0.0212	31.0	6975	0.7650	0.91
0.0018	32.0	7200	0.7684	0.9083
0.0006	33.0	7425	0.7607	0.9133
0.0001	34.0	7650	0.7555	0.9117
0.0002	35.0	7875	0.7851	0.9083
0.0002	36.0	8100	0.7601	0.9117
0.0002	37.0	8325	0.7878	0.9083
0.0284	38.0	8550	0.7877	0.9083
0.0007	39.0	8775	0.7993	0.9067
0.002	40.0	9000	0.7969	0.91
0.0004	41.0	9225	0.8163	0.9083
0.0234	42.0	9450	0.7871	0.915
0.0006	43.0	9675	0.8006	0.9067
0.0004	44.0	9900	0.7989	0.9083
0.0007	45.0	10125	0.8058	0.9067
0.0174	46.0	10350	0.8151	0.9017
0.0003	47.0	10575	0.8093	0.9033
0.0	48.0	10800	0.8021	0.9067
0.0012	49.0	11025	0.8063	0.9067
0.0009	50.0	11250	0.8012	0.9067

Framework versions

Transformers 4.32.1
Pytorch 2.1.0+cu121
Datasets 2.12.0
Tokenizers 0.13.2