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_adamax_00001_fold5
    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: 0.9083333333333333

smids_3x_beit_base_adamax_00001_fold5

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: 0.7465
Accuracy: 0.9083

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
0.2292	1.0	375	0.3140	0.8683
0.2093	2.0	750	0.2336	0.9067
0.1226	3.0	1125	0.2477	0.9117
0.0876	4.0	1500	0.2419	0.92
0.0679	5.0	1875	0.3315	0.8983
0.0323	6.0	2250	0.3578	0.9033
0.0877	7.0	2625	0.4065	0.91
0.0394	8.0	3000	0.4499	0.91
0.0357	9.0	3375	0.4692	0.9167
0.0126	10.0	3750	0.5130	0.9083
0.0533	11.0	4125	0.4610	0.915
0.018	12.0	4500	0.5545	0.9167
0.0014	13.0	4875	0.6258	0.905
0.0294	14.0	5250	0.5991	0.9133
0.0147	15.0	5625	0.5948	0.91
0.0096	16.0	6000	0.6032	0.905
0.03	17.0	6375	0.6625	0.9017
0.0009	18.0	6750	0.6142	0.9067
0.0073	19.0	7125	0.7447	0.8917
0.0002	20.0	7500	0.6954	0.9067
0.0056	21.0	7875	0.7051	0.9133
0.0361	22.0	8250	0.6457	0.9067
0.0618	23.0	8625	0.6671	0.905
0.0003	24.0	9000	0.7426	0.905
0.0152	25.0	9375	0.6683	0.905
0.0005	26.0	9750	0.7087	0.9067
0.0002	27.0	10125	0.7480	0.905
0.004	28.0	10500	0.7511	0.905
0.0094	29.0	10875	0.7080	0.9017
0.0056	30.0	11250	0.7631	0.905
0.0441	31.0	11625	0.7580	0.9083
0.0024	32.0	12000	0.7682	0.9083
0.0002	33.0	12375	0.7496	0.9133
0.0005	34.0	12750	0.7614	0.9067
0.0057	35.0	13125	0.7635	0.9083
0.0004	36.0	13500	0.7425	0.9117
0.0153	37.0	13875	0.7300	0.91
0.0003	38.0	14250	0.7331	0.9083
0.0149	39.0	14625	0.7175	0.905
0.0093	40.0	15000	0.7444	0.9067
0.0001	41.0	15375	0.7317	0.9117
0.0	42.0	15750	0.7474	0.9033
0.0002	43.0	16125	0.7578	0.905
0.0004	44.0	16500	0.7636	0.905
0.0	45.0	16875	0.7676	0.91
0.0005	46.0	17250	0.7589	0.91
0.0158	47.0	17625	0.7484	0.9083
0.0001	48.0	18000	0.7568	0.91
0.0001	49.0	18375	0.7501	0.9083
0.0109	50.0	18750	0.7465	0.9083

Framework versions

Transformers 4.32.1
Pytorch 2.1.0+cu121
Datasets 2.12.0
Tokenizers 0.13.2