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_3x_beit_base_rms_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: 0.8833333333333333

smids_3x_beit_base_rms_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: 1.2428
• Accuracy: 0.8833

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
0.2439	1.0	225	0.3063	0.88
0.0996	2.0	450	0.3661	0.8767
0.0787	3.0	675	0.4587	0.8667
0.0663	4.0	900	0.5189	0.8733
0.0442	5.0	1125	0.7230	0.8683
0.049	6.0	1350	0.6529	0.885
0.0264	7.0	1575	0.8061	0.8817
0.0229	8.0	1800	0.7781	0.89
0.0395	9.0	2025	0.9069	0.88
0.0034	10.0	2250	0.8845	0.885
0.0389	11.0	2475	1.0336	0.8783
0.0025	12.0	2700	0.9857	0.8867
0.0142	13.0	2925	1.0341	0.885
0.0196	14.0	3150	1.1721	0.8767
0.0094	15.0	3375	1.0615	0.8767
0.0053	16.0	3600	1.1359	0.8767
0.0019	17.0	3825	1.1838	0.88
0.0236	18.0	4050	1.3731	0.8617
0.0037	19.0	4275	1.2473	0.8683
0.0001	20.0	4500	1.1836	0.8833
0.0008	21.0	4725	1.2284	0.8733
0.0	22.0	4950	1.1971	0.8867
0.015	23.0	5175	1.2985	0.8783
0.0	24.0	5400	1.3191	0.8683
0.0386	25.0	5625	1.3376	0.88
0.0001	26.0	5850	1.3273	0.8717
0.0019	27.0	6075	1.3269	0.8683
0.0001	28.0	6300	1.3093	0.8733
0.0	29.0	6525	1.2247	0.88
0.0	30.0	6750	1.2682	0.8733
0.0	31.0	6975	1.2123	0.8833
0.0	32.0	7200	1.2162	0.885
0.0027	33.0	7425	1.2786	0.8783
0.0	34.0	7650	1.3256	0.8817
0.0286	35.0	7875	1.2152	0.89
0.0	36.0	8100	1.2207	0.8833
0.0001	37.0	8325	1.2285	0.885
0.0004	38.0	8550	1.1956	0.89
0.0	39.0	8775	1.1853	0.8867
0.0401	40.0	9000	1.1341	0.8967
0.0	41.0	9225	1.1526	0.8883
0.0032	42.0	9450	1.1907	0.8817
0.0002	43.0	9675	1.2154	0.8833
0.0022	44.0	9900	1.1934	0.8833
0.0	45.0	10125	1.2765	0.88
0.0	46.0	10350	1.2545	0.8767
0.0002	47.0	10575	1.2393	0.8817
0.0	48.0	10800	1.2475	0.8817
0.0	49.0	11025	1.2453	0.8817
0.0	50.0	11250	1.2428	0.8833

Framework versions

• Transformers 4.32.1
• Pytorch 2.1.0+cu121
• Datasets 2.12.0
• Tokenizers 0.13.2