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_0001_fold1
    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: 0.8497495826377296

smids_3x_beit_base_rms_0001_fold1

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: 1.4390
• Accuracy: 0.8497

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: 0.0001
• 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
0.8068	1.0	226	1.0605	0.3272
0.7543	2.0	452	0.8522	0.5943
0.6302	3.0	678	0.8188	0.6227
0.591	4.0	904	0.7284	0.6795
0.5365	5.0	1130	0.5240	0.7830
0.4875	6.0	1356	0.4715	0.8030
0.2956	7.0	1582	0.5230	0.8130
0.3385	8.0	1808	0.4637	0.8047
0.2498	9.0	2034	0.5733	0.8230
0.2375	10.0	2260	0.5001	0.8381
0.2383	11.0	2486	0.5213	0.8164
0.1638	12.0	2712	0.7500	0.8097
0.1669	13.0	2938	0.6347	0.8347
0.091	14.0	3164	0.8704	0.8164
0.0933	15.0	3390	0.6698	0.8280
0.1167	16.0	3616	0.7435	0.8481
0.0442	17.0	3842	0.8758	0.8164
0.0649	18.0	4068	0.8054	0.8247
0.0996	19.0	4294	0.8135	0.8164
0.0421	20.0	4520	0.8460	0.8464
0.0255	21.0	4746	1.2147	0.8097
0.0814	22.0	4972	0.8708	0.8331
0.07	23.0	5198	1.0564	0.8364
0.029	24.0	5424	1.0607	0.8364
0.0335	25.0	5650	1.0179	0.8464
0.0974	26.0	5876	0.8966	0.8364
0.0251	27.0	6102	1.0900	0.8297
0.0304	28.0	6328	0.9348	0.8347
0.0116	29.0	6554	1.0392	0.8447
0.036	30.0	6780	1.0080	0.8414
0.0176	31.0	7006	1.0131	0.8364
0.0187	32.0	7232	0.9626	0.8397
0.0495	33.0	7458	0.9911	0.8414
0.0106	34.0	7684	1.2195	0.8331
0.0005	35.0	7910	1.2232	0.8464
0.0148	36.0	8136	1.1060	0.8364
0.0093	37.0	8362	1.0552	0.8364
0.0212	38.0	8588	1.1910	0.8364
0.0009	39.0	8814	1.1001	0.8431
0.0083	40.0	9040	1.2874	0.8481
0.0296	41.0	9266	1.3495	0.8381
0.0225	42.0	9492	1.3683	0.8414
0.0158	43.0	9718	1.2852	0.8481
0.0056	44.0	9944	1.3620	0.8447
0.0126	45.0	10170	1.3137	0.8431
0.0	46.0	10396	1.4527	0.8497
0.013	47.0	10622	1.4028	0.8531
0.0375	48.0	10848	1.3979	0.8481
0.0006	49.0	11074	1.4369	0.8497
0.0135	50.0	11300	1.4390	0.8497

Framework versions

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