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_adamax_0001_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: 0.9068219633943427

smids_5x_beit_base_adamax_0001_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: 1.0996
Accuracy: 0.9068

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
0.3388	1.0	375	0.2592	0.8918
0.2336	2.0	750	0.6135	0.8403
0.171	3.0	1125	0.4021	0.8636
0.1223	4.0	1500	0.5420	0.8769
0.1021	5.0	1875	0.4050	0.9018
0.1121	6.0	2250	0.4217	0.8952
0.1055	7.0	2625	0.5917	0.8785
0.0936	8.0	3000	0.5515	0.8902
0.0292	9.0	3375	0.5916	0.8952
0.0288	10.0	3750	0.4755	0.9002
0.0249	11.0	4125	0.6337	0.8702
0.0449	12.0	4500	0.5405	0.8918
0.0538	13.0	4875	0.7447	0.8769
0.0351	14.0	5250	0.7235	0.8852
0.0643	15.0	5625	0.8669	0.8686
0.0207	16.0	6000	0.8090	0.8752
0.0143	17.0	6375	0.7492	0.8802
0.0274	18.0	6750	0.6970	0.8852
0.033	19.0	7125	0.6368	0.8819
0.0159	20.0	7500	0.6552	0.8735
0.0363	21.0	7875	0.6430	0.8819
0.0001	22.0	8250	0.7685	0.8885
0.0004	23.0	8625	0.8828	0.8735
0.0808	24.0	9000	0.5316	0.8918
0.0051	25.0	9375	0.9086	0.8769
0.0009	26.0	9750	0.7387	0.8835
0.014	27.0	10125	0.7630	0.9035
0.0182	28.0	10500	0.6195	0.9035
0.0001	29.0	10875	0.8510	0.8952
0.0216	30.0	11250	0.8683	0.8785
0.0043	31.0	11625	0.7909	0.8985
0.0064	32.0	12000	0.9052	0.8902
0.0153	33.0	12375	0.8789	0.8968
0.0001	34.0	12750	0.8661	0.8935
0.0	35.0	13125	0.8999	0.8885
0.0	36.0	13500	1.0043	0.8918
0.0001	37.0	13875	0.9274	0.8968
0.0113	38.0	14250	0.8785	0.9052
0.0	39.0	14625	0.9514	0.9018
0.0025	40.0	15000	1.0212	0.9052
0.0	41.0	15375	0.9947	0.8952
0.0027	42.0	15750	0.9897	0.9018
0.0024	43.0	16125	0.9906	0.9085
0.0024	44.0	16500	1.0802	0.8952
0.0028	45.0	16875	1.0813	0.8985
0.0	46.0	17250	1.0748	0.8985
0.0059	47.0	17625	1.0853	0.9052
0.0	48.0	18000	1.1050	0.9068
0.0036	49.0	18375	1.1002	0.9052
0.0022	50.0	18750	1.0996	0.9068

Framework versions

Transformers 4.32.1
Pytorch 2.1.0+cu121
Datasets 2.12.0
Tokenizers 0.13.2