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_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: 0.8

hushem_1x_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: 1.0153
• Accuracy: 0.8

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
No log	1.0	6	1.2331	0.5556
1.3348	2.0	12	0.8218	0.6889
1.3348	3.0	18	0.6484	0.7556
0.3555	4.0	24	0.8513	0.7556
0.1239	5.0	30	0.7326	0.7333
0.1239	6.0	36	0.6190	0.8
0.0625	7.0	42	1.0407	0.7333
0.0625	8.0	48	0.7902	0.8
0.0045	9.0	54	0.8103	0.7778
0.0021	10.0	60	1.0314	0.8
0.0021	11.0	66	1.1219	0.7556
0.0013	12.0	72	1.0834	0.7556
0.0013	13.0	78	1.0270	0.7333
0.0006	14.0	84	1.0518	0.7556
0.0005	15.0	90	1.0755	0.7556
0.0005	16.0	96	1.1073	0.7556
0.0005	17.0	102	1.1726	0.7556
0.0005	18.0	108	1.2002	0.7556
0.0005	19.0	114	1.1838	0.7556
0.0007	20.0	120	1.1860	0.7556
0.0007	21.0	126	1.2997	0.7556
0.0003	22.0	132	1.3311	0.7556
0.0003	23.0	138	1.3197	0.7556
0.0002	24.0	144	1.2630	0.7556
0.0003	25.0	150	1.1925	0.7556
0.0003	26.0	156	1.1444	0.7778
0.0002	27.0	162	1.1105	0.7778
0.0002	28.0	168	1.0790	0.7778
0.0002	29.0	174	1.0616	0.7778
0.0002	30.0	180	1.0495	0.7778
0.0002	31.0	186	1.0431	0.7778
0.0002	32.0	192	1.0407	0.7778
0.0002	33.0	198	1.0375	0.8
0.0107	34.0	204	1.0331	0.8
0.0002	35.0	210	1.0311	0.8
0.0002	36.0	216	1.0289	0.8
0.0002	37.0	222	1.0264	0.8
0.0002	38.0	228	1.0203	0.8
0.0003	39.0	234	1.0167	0.8
0.0002	40.0	240	1.0146	0.8
0.0002	41.0	246	1.0152	0.8
0.0002	42.0	252	1.0153	0.8
0.0002	43.0	258	1.0153	0.8
0.0002	44.0	264	1.0153	0.8
0.0002	45.0	270	1.0153	0.8
0.0002	46.0	276	1.0153	0.8
0.002	47.0	282	1.0153	0.8
0.002	48.0	288	1.0153	0.8
0.0006	49.0	294	1.0153	0.8
0.0001	50.0	300	1.0153	0.8

Framework versions

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