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_fold3
    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: 0.813953488372093

hushem_1x_beit_base_adamax_00001_fold3

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: 0.5847
• Accuracy: 0.8140

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	1.3689	0.2558
1.2857	2.0	12	1.2466	0.4651
1.2857	3.0	18	1.1312	0.5116
0.9708	4.0	24	1.0630	0.5581
0.7059	5.0	30	0.9958	0.6279
0.7059	6.0	36	0.9376	0.6977
0.5317	7.0	42	0.9138	0.6977
0.5317	8.0	48	0.8910	0.7209
0.4018	9.0	54	0.8263	0.7209
0.2986	10.0	60	0.8004	0.7442
0.2986	11.0	66	0.7624	0.7442
0.246	12.0	72	0.7431	0.7442
0.246	13.0	78	0.7355	0.7674
0.2027	14.0	84	0.7048	0.7674
0.1517	15.0	90	0.6855	0.7674
0.1517	16.0	96	0.6737	0.7907
0.1364	17.0	102	0.6501	0.7907
0.1364	18.0	108	0.6600	0.7674
0.1145	19.0	114	0.6690	0.7674
0.1069	20.0	120	0.6546	0.7674
0.1069	21.0	126	0.6296	0.7674
0.0848	22.0	132	0.6148	0.7907
0.0848	23.0	138	0.6215	0.7907
0.0728	24.0	144	0.6245	0.7907
0.0711	25.0	150	0.6128	0.7907
0.0711	26.0	156	0.6151	0.7907
0.0595	27.0	162	0.6249	0.7907
0.0595	28.0	168	0.6313	0.7907
0.0729	29.0	174	0.6189	0.7907
0.0453	30.0	180	0.6035	0.7907
0.0453	31.0	186	0.5936	0.8140
0.0572	32.0	192	0.5852	0.8140
0.0572	33.0	198	0.5840	0.8140
0.0512	34.0	204	0.5836	0.8140
0.0479	35.0	210	0.5806	0.8140
0.0479	36.0	216	0.5792	0.8140
0.0352	37.0	222	0.5787	0.8140
0.0352	38.0	228	0.5803	0.8140
0.0412	39.0	234	0.5826	0.8140
0.0379	40.0	240	0.5843	0.8140
0.0379	41.0	246	0.5847	0.8140
0.0381	42.0	252	0.5847	0.8140
0.0381	43.0	258	0.5847	0.8140
0.0582	44.0	264	0.5847	0.8140
0.0396	45.0	270	0.5847	0.8140
0.0396	46.0	276	0.5847	0.8140
0.0561	47.0	282	0.5847	0.8140
0.0561	48.0	288	0.5847	0.8140
0.047	49.0	294	0.5847	0.8140
0.0342	50.0	300	0.5847	0.8140

Framework versions

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