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_adamax_00001_fold5
    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: 0.89

smids_1x_beit_base_adamax_00001_fold5

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: 0.6882
Accuracy: 0.89

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
0.3992	1.0	75	0.3544	0.845
0.2938	2.0	150	0.2944	0.88
0.2043	3.0	225	0.2889	0.8733
0.1457	4.0	300	0.2668	0.8917
0.1371	5.0	375	0.2691	0.8833
0.1186	6.0	450	0.2876	0.8733
0.0675	7.0	525	0.2905	0.895
0.0675	8.0	600	0.3070	0.8983
0.0951	9.0	675	0.3449	0.8917
0.0427	10.0	750	0.3642	0.885
0.0217	11.0	825	0.3880	0.8817
0.0513	12.0	900	0.3991	0.9
0.0247	13.0	975	0.4163	0.8983
0.018	14.0	1050	0.4538	0.8883
0.0291	15.0	1125	0.4599	0.8917
0.0096	16.0	1200	0.5126	0.89
0.0106	17.0	1275	0.5125	0.8867
0.0447	18.0	1350	0.5410	0.8883
0.016	19.0	1425	0.5359	0.8883
0.0033	20.0	1500	0.5522	0.8867
0.0086	21.0	1575	0.5579	0.8883
0.0299	22.0	1650	0.5864	0.8833
0.0058	23.0	1725	0.5904	0.8867
0.0156	24.0	1800	0.6102	0.89
0.0161	25.0	1875	0.6210	0.8883
0.0066	26.0	1950	0.6149	0.8883
0.0424	27.0	2025	0.6199	0.8867
0.011	28.0	2100	0.6388	0.8867
0.0021	29.0	2175	0.6358	0.8917
0.0014	30.0	2250	0.6319	0.8883
0.0203	31.0	2325	0.6459	0.89
0.0221	32.0	2400	0.6739	0.8883
0.0066	33.0	2475	0.6562	0.89
0.0119	34.0	2550	0.6704	0.885
0.0088	35.0	2625	0.6526	0.89
0.0115	36.0	2700	0.6534	0.8867
0.0355	37.0	2775	0.6663	0.8883
0.0376	38.0	2850	0.6538	0.89
0.0299	39.0	2925	0.6757	0.8867
0.0019	40.0	3000	0.6764	0.8883
0.0235	41.0	3075	0.6776	0.89
0.0081	42.0	3150	0.6798	0.8883
0.0053	43.0	3225	0.6758	0.8883
0.0234	44.0	3300	0.6788	0.8933
0.0053	45.0	3375	0.6853	0.8883
0.0121	46.0	3450	0.6875	0.8867
0.001	47.0	3525	0.6878	0.8883
0.0104	48.0	3600	0.6872	0.89
0.0042	49.0	3675	0.6870	0.8883
0.0115	50.0	3750	0.6882	0.89

Framework versions

Transformers 4.35.2
Pytorch 2.1.0+cu118
Datasets 2.15.0
Tokenizers 0.15.0