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_rms_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: 0.8372093023255814

hushem_1x_beit_base_rms_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: 0.5862
• Accuracy: 0.8372

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	1.3652	0.2558
1.4655	2.0	12	0.9320	0.6512
1.4655	3.0	18	0.5733	0.7907
0.6613	4.0	24	0.3842	0.8605
0.1719	5.0	30	0.4268	0.8605
0.1719	6.0	36	0.3122	0.8837
0.0362	7.0	42	0.5635	0.7907
0.0362	8.0	48	0.2839	0.8837
0.0103	9.0	54	0.3515	0.9070
0.0048	10.0	60	0.4717	0.8837
0.0048	11.0	66	0.4775	0.8372
0.0038	12.0	72	0.5321	0.7907
0.0038	13.0	78	0.4659	0.8372
0.0022	14.0	84	0.5318	0.8140
0.0017	15.0	90	0.5328	0.8605
0.0017	16.0	96	0.4991	0.8372
0.0025	17.0	102	0.5203	0.8372
0.0025	18.0	108	0.5439	0.8372
0.0011	19.0	114	0.5049	0.8372
0.0014	20.0	120	0.5023	0.8372
0.0014	21.0	126	0.5748	0.8372
0.0013	22.0	132	0.5341	0.8372
0.0013	23.0	138	0.4866	0.8372
0.0011	24.0	144	0.5270	0.8372
0.0012	25.0	150	0.5889	0.8372
0.0012	26.0	156	0.6180	0.8372
0.0013	27.0	162	0.6227	0.8372
0.0013	28.0	168	0.6125	0.8372
0.0007	29.0	174	0.5708	0.8605
0.0004	30.0	180	0.5729	0.8372
0.0004	31.0	186	0.5789	0.8372
0.001	32.0	192	0.5842	0.8140
0.001	33.0	198	0.5989	0.8372
0.0008	34.0	204	0.5775	0.8140
0.0013	35.0	210	0.5738	0.8372
0.0013	36.0	216	0.5742	0.8140
0.0006	37.0	222	0.6172	0.8140
0.0006	38.0	228	0.5958	0.8140
0.0026	39.0	234	0.5884	0.8140
0.0006	40.0	240	0.5885	0.8140
0.0006	41.0	246	0.5863	0.8372
0.0008	42.0	252	0.5862	0.8372
0.0008	43.0	258	0.5862	0.8372
0.0006	44.0	264	0.5862	0.8372
0.0004	45.0	270	0.5862	0.8372
0.0004	46.0	276	0.5862	0.8372
0.0006	47.0	282	0.5862	0.8372
0.0006	48.0	288	0.5862	0.8372
0.0005	49.0	294	0.5862	0.8372
0.0004	50.0	300	0.5862	0.8372

Framework versions

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