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_sgd_001_fold2
    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: 0.8851913477537438

smids_5x_beit_base_sgd_001_fold2

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: 0.2987
Accuracy: 0.8852

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
0.6816	1.0	375	0.6833	0.7338
0.5586	2.0	750	0.5192	0.7987
0.4343	3.0	1125	0.4591	0.8037
0.3314	4.0	1500	0.4185	0.8270
0.3478	5.0	1875	0.4048	0.8369
0.3776	6.0	2250	0.3805	0.8336
0.3391	7.0	2625	0.3595	0.8403
0.3304	8.0	3000	0.3500	0.8469
0.2847	9.0	3375	0.3354	0.8602
0.2987	10.0	3750	0.3303	0.8519
0.2929	11.0	4125	0.3216	0.8669
0.3369	12.0	4500	0.3243	0.8569
0.2344	13.0	4875	0.3140	0.8619
0.2532	14.0	5250	0.3121	0.8669
0.2563	15.0	5625	0.3059	0.8769
0.2186	16.0	6000	0.3073	0.8652
0.3036	17.0	6375	0.3090	0.8669
0.2499	18.0	6750	0.3061	0.8719
0.2571	19.0	7125	0.2980	0.8752
0.287	20.0	7500	0.3028	0.8719
0.2417	21.0	7875	0.2951	0.8819
0.2578	22.0	8250	0.2968	0.8769
0.2485	23.0	8625	0.3021	0.8752
0.2288	24.0	9000	0.2899	0.8852
0.1978	25.0	9375	0.3001	0.8785
0.2856	26.0	9750	0.2985	0.8819
0.2426	27.0	10125	0.2936	0.8852
0.222	28.0	10500	0.2944	0.8852
0.2193	29.0	10875	0.2940	0.8802
0.2438	30.0	11250	0.2935	0.8802
0.1916	31.0	11625	0.2931	0.8735
0.2423	32.0	12000	0.2890	0.8869
0.207	33.0	12375	0.2979	0.8769
0.1912	34.0	12750	0.3002	0.8885
0.2247	35.0	13125	0.2940	0.8819
0.1554	36.0	13500	0.2936	0.8819
0.1927	37.0	13875	0.2998	0.8769
0.1704	38.0	14250	0.2978	0.8835
0.2119	39.0	14625	0.3017	0.8769
0.1926	40.0	15000	0.2970	0.8819
0.1898	41.0	15375	0.3000	0.8785
0.2087	42.0	15750	0.2990	0.8819
0.1865	43.0	16125	0.2976	0.8835
0.2027	44.0	16500	0.3000	0.8819
0.1873	45.0	16875	0.2993	0.8835
0.2551	46.0	17250	0.2983	0.8819
0.227	47.0	17625	0.2985	0.8852
0.2135	48.0	18000	0.3011	0.8785
0.2131	49.0	18375	0.2986	0.8852
0.2054	50.0	18750	0.2987	0.8852

Framework versions

Transformers 4.32.1
Pytorch 2.1.0+cu121
Datasets 2.12.0
Tokenizers 0.13.2