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_adamax_00001_fold4
    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: 0.8733333333333333

smids_1x_beit_base_adamax_00001_fold4

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: 0.9690
• Accuracy: 0.8733

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
0.3842	1.0	75	0.3836	0.8567
0.2698	2.0	150	0.3565	0.8717
0.2112	3.0	225	0.3725	0.8667
0.1563	4.0	300	0.3983	0.8683
0.0925	5.0	375	0.3901	0.875
0.1014	6.0	450	0.4180	0.8817
0.0818	7.0	525	0.4236	0.8733
0.0472	8.0	600	0.4670	0.87
0.0417	9.0	675	0.5177	0.8767
0.0198	10.0	750	0.5528	0.8683
0.0232	11.0	825	0.5777	0.875
0.0159	12.0	900	0.6214	0.8683
0.0174	13.0	975	0.6477	0.87
0.0205	14.0	1050	0.7117	0.8633
0.0429	15.0	1125	0.7038	0.875
0.0098	16.0	1200	0.7398	0.8733
0.0056	17.0	1275	0.7568	0.8717
0.016	18.0	1350	0.7774	0.8733
0.0366	19.0	1425	0.7871	0.8783
0.0462	20.0	1500	0.7545	0.8867
0.0036	21.0	1575	0.8298	0.8767
0.013	22.0	1650	0.8793	0.875
0.0139	23.0	1725	0.8645	0.88
0.0044	24.0	1800	0.8813	0.8717
0.0148	25.0	1875	0.8534	0.8767
0.0146	26.0	1950	0.8817	0.8767
0.0054	27.0	2025	0.9081	0.87
0.0007	28.0	2100	0.8989	0.8767
0.0046	29.0	2175	0.8951	0.88
0.0234	30.0	2250	0.9014	0.8717
0.0106	31.0	2325	0.9119	0.8667
0.0085	32.0	2400	0.9313	0.8717
0.0036	33.0	2475	0.9195	0.8733
0.001	34.0	2550	0.9166	0.8717
0.0098	35.0	2625	0.9378	0.87
0.0089	36.0	2700	0.9278	0.8717
0.0099	37.0	2775	0.9534	0.8717
0.0248	38.0	2850	0.9419	0.8783
0.0327	39.0	2925	0.9391	0.8733
0.0223	40.0	3000	0.9364	0.875
0.0147	41.0	3075	0.9305	0.8767
0.0288	42.0	3150	0.9572	0.8783
0.0191	43.0	3225	0.9619	0.875
0.0008	44.0	3300	0.9576	0.875
0.0019	45.0	3375	0.9660	0.8733
0.0022	46.0	3450	0.9692	0.875
0.0015	47.0	3525	0.9668	0.875
0.0054	48.0	3600	0.9744	0.8733
0.0016	49.0	3675	0.9694	0.8733
0.0003	50.0	3750	0.9690	0.8733

Framework versions

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