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_1x_beit_base_rms_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: 0.895

smids_1x_beit_base_rms_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: 0.9075
• Accuracy: 0.895

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
0.3429	1.0	75	0.3196	0.8817
0.2319	2.0	150	0.2825	0.8883
0.1642	3.0	225	0.2956	0.8883
0.0613	4.0	300	0.2991	0.905
0.0375	5.0	375	0.4173	0.89
0.0392	6.0	450	0.4376	0.895
0.0266	7.0	525	0.5591	0.8933
0.0211	8.0	600	0.6357	0.8883
0.0129	9.0	675	0.5589	0.8967
0.039	10.0	750	0.6087	0.8933
0.0196	11.0	825	0.6853	0.8967
0.0875	12.0	900	0.6905	0.8833
0.0161	13.0	975	0.7505	0.8867
0.0005	14.0	1050	0.7592	0.875
0.0258	15.0	1125	0.7859	0.8783
0.0008	16.0	1200	0.7624	0.8783
0.0078	17.0	1275	0.7129	0.8917
0.0151	18.0	1350	0.7730	0.885
0.015	19.0	1425	0.7612	0.88
0.0036	20.0	1500	0.7765	0.89
0.0036	21.0	1575	0.7746	0.89
0.0163	22.0	1650	0.7920	0.88
0.0002	23.0	1725	0.7971	0.8867
0.0013	24.0	1800	0.8091	0.8833
0.0084	25.0	1875	0.8422	0.8817
0.0077	26.0	1950	0.8718	0.89
0.0059	27.0	2025	0.8359	0.89
0.0135	28.0	2100	0.8777	0.8833
0.0007	29.0	2175	0.8422	0.895
0.0059	30.0	2250	0.8920	0.8933
0.0039	31.0	2325	0.9311	0.875
0.0027	32.0	2400	0.8796	0.89
0.0001	33.0	2475	0.9632	0.88
0.0031	34.0	2550	0.8453	0.89
0.0036	35.0	2625	0.8275	0.895
0.003	36.0	2700	0.8573	0.8883
0.0273	37.0	2775	0.8009	0.8967
0.0042	38.0	2850	0.8716	0.8917
0.0032	39.0	2925	0.9439	0.88
0.0005	40.0	3000	0.8577	0.8917
0.0023	41.0	3075	0.8426	0.8867
0.0083	42.0	3150	0.8441	0.895
0.0	43.0	3225	0.8722	0.8883
0.0036	44.0	3300	0.8679	0.8883
0.0009	45.0	3375	0.9113	0.8917
0.0131	46.0	3450	0.8965	0.89
0.0	47.0	3525	0.8892	0.8933
0.0001	48.0	3600	0.9072	0.8933
0.0024	49.0	3675	0.9074	0.8933
0.0054	50.0	3750	0.9075	0.895

Framework versions

• Transformers 4.35.2
• Pytorch 2.1.0+cu118
• Datasets 2.15.0
• Tokenizers 0.15.0