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: hushem_1x_beit_base_adamax_00001_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: 0.6888888888888889

hushem_1x_beit_base_adamax_00001_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: 1.0038
• Accuracy: 0.6889

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
No log	1.0	6	1.2765	0.4
1.3322	2.0	12	1.2154	0.4444
1.3322	3.0	18	1.1631	0.4889
0.9388	4.0	24	1.0966	0.4889
0.7193	5.0	30	1.0653	0.6
0.7193	6.0	36	1.0660	0.5556
0.5374	7.0	42	1.0203	0.5778
0.5374	8.0	48	1.0147	0.6
0.4187	9.0	54	1.0003	0.6222
0.3224	10.0	60	0.9783	0.6
0.3224	11.0	66	0.9383	0.6444
0.2464	12.0	72	0.9513	0.6444
0.2464	13.0	78	0.9808	0.6444
0.1839	14.0	84	0.9939	0.6667
0.1568	15.0	90	1.0128	0.6667
0.1568	16.0	96	0.9589	0.6889
0.1288	17.0	102	0.9172	0.6889
0.1288	18.0	108	0.9617	0.6667
0.1076	19.0	114	0.9784	0.6889
0.1101	20.0	120	0.9555	0.6889
0.1101	21.0	126	0.9639	0.6889
0.0715	22.0	132	1.0124	0.6667
0.0715	23.0	138	1.0281	0.6889
0.0643	24.0	144	0.9837	0.6889
0.062	25.0	150	0.9706	0.6889
0.062	26.0	156	0.9680	0.6889
0.0557	27.0	162	0.9640	0.6889
0.0557	28.0	168	0.9912	0.6889
0.0524	29.0	174	1.0047	0.7111
0.0432	30.0	180	1.0048	0.6889
0.0432	31.0	186	1.0092	0.6889
0.0454	32.0	192	1.0117	0.6889
0.0454	33.0	198	1.0112	0.6889
0.0405	34.0	204	0.9915	0.6889
0.0406	35.0	210	0.9689	0.6889
0.0406	36.0	216	0.9643	0.6889
0.0354	37.0	222	0.9716	0.6889
0.0354	38.0	228	0.9874	0.6889
0.0426	39.0	234	0.9950	0.6889
0.0369	40.0	240	0.9999	0.6889
0.0369	41.0	246	1.0036	0.6889
0.0338	42.0	252	1.0038	0.6889
0.0338	43.0	258	1.0038	0.6889
0.0349	44.0	264	1.0038	0.6889
0.0361	45.0	270	1.0038	0.6889
0.0361	46.0	276	1.0038	0.6889
0.0398	47.0	282	1.0038	0.6889
0.0398	48.0	288	1.0038	0.6889
0.0375	49.0	294	1.0038	0.6889
0.0265	50.0	300	1.0038	0.6889

Framework versions

• Transformers 4.35.2
• Pytorch 2.1.0+cu118
• Datasets 2.15.0
• Tokenizers 0.15.0