metadata

license: apache-2.0
base_model: microsoft/beit-base-patch16-224
tags:
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - accuracy
model-index:
  - name: smids_5x_beit_base_rms_001_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: 0.7983333333333333

smids_5x_beit_base_rms_001_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: 1.7051
Accuracy: 0.7983

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: 0.001
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
0.7798	1.0	375	0.7672	0.5633
0.803	2.0	750	0.7688	0.58
0.7686	3.0	1125	0.7514	0.61
0.7375	4.0	1500	0.8350	0.5517
0.7507	5.0	1875	0.8001	0.595
0.7083	6.0	2250	0.7244	0.65
0.708	7.0	2625	0.7289	0.6467
0.7266	8.0	3000	0.7325	0.6633
0.6418	9.0	3375	0.6940	0.6917
0.673	10.0	3750	0.7042	0.6617
0.6803	11.0	4125	0.6907	0.6817
0.64	12.0	4500	0.6890	0.675
0.6467	13.0	4875	0.7095	0.67
0.6428	14.0	5250	0.6543	0.7083
0.6389	15.0	5625	0.5890	0.7383
0.5885	16.0	6000	0.5874	0.7383
0.5689	17.0	6375	0.6828	0.705
0.5988	18.0	6750	0.6153	0.74
0.5869	19.0	7125	0.5556	0.745
0.5829	20.0	7500	0.5816	0.7417
0.5202	21.0	7875	0.6299	0.7267
0.4671	22.0	8250	0.5955	0.7383
0.4713	23.0	8625	0.5489	0.7783
0.4814	24.0	9000	0.6063	0.76
0.4578	25.0	9375	0.6548	0.7367
0.4226	26.0	9750	0.5459	0.75
0.349	27.0	10125	0.6223	0.76
0.3499	28.0	10500	0.5682	0.7817
0.2869	29.0	10875	0.7135	0.7717
0.3419	30.0	11250	0.6094	0.7833
0.3402	31.0	11625	0.6473	0.785
0.3025	32.0	12000	0.6500	0.7783
0.2278	33.0	12375	0.7439	0.7633
0.2211	34.0	12750	0.7227	0.775
0.1813	35.0	13125	0.7187	0.8033
0.1887	36.0	13500	0.7980	0.7883
0.2308	37.0	13875	0.8180	0.8
0.1362	38.0	14250	0.8499	0.7867
0.1204	39.0	14625	0.8914	0.8033
0.1182	40.0	15000	0.9026	0.7933
0.1271	41.0	15375	1.1021	0.775
0.0646	42.0	15750	1.1489	0.7967
0.0428	43.0	16125	1.2387	0.8067
0.0277	44.0	16500	1.2320	0.81
0.0276	45.0	16875	1.3879	0.79
0.0246	46.0	17250	1.4881	0.8033
0.0344	47.0	17625	1.5278	0.7983
0.006	48.0	18000	1.5757	0.8017
0.0048	49.0	18375	1.6617	0.8033
0.0042	50.0	18750	1.7051	0.7983

Framework versions

Transformers 4.32.1
Pytorch 2.1.0+cu121
Datasets 2.12.0
Tokenizers 0.13.2