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_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: 0.8292682926829268

hushem_1x_beit_base_adamax_0001_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: 0.8158
• Accuracy: 0.8293

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	1.1847	0.3902
1.4269	2.0	12	0.7266	0.7073
1.4269	3.0	18	0.6792	0.7073
0.5553	4.0	24	0.4456	0.7805
0.1357	5.0	30	0.2904	0.9024
0.1357	6.0	36	0.6815	0.8049
0.0115	7.0	42	0.6208	0.8049
0.0115	8.0	48	0.5124	0.8537
0.0146	9.0	54	0.7063	0.7805
0.0021	10.0	60	0.7320	0.8049
0.0021	11.0	66	0.5435	0.8537
0.0012	12.0	72	0.6105	0.8293
0.0012	13.0	78	0.6174	0.8537
0.0009	14.0	84	0.6224	0.8293
0.0011	15.0	90	0.5560	0.8293
0.0011	16.0	96	0.6136	0.8293
0.0005	17.0	102	0.6179	0.8537
0.0005	18.0	108	0.6489	0.8049
0.0019	19.0	114	0.7624	0.7561
0.0003	20.0	120	0.8499	0.7561
0.0003	21.0	126	0.8910	0.7805
0.0005	22.0	132	0.7310	0.7805
0.0005	23.0	138	0.6709	0.8049
0.0003	24.0	144	0.6558	0.8049
0.0004	25.0	150	0.6700	0.8049
0.0004	26.0	156	0.6879	0.8049
0.0003	27.0	162	0.7678	0.8049
0.0003	28.0	168	0.8154	0.8049
0.0002	29.0	174	0.8459	0.8049
0.0002	30.0	180	0.8632	0.8049
0.0002	31.0	186	0.8601	0.8049
0.001	32.0	192	0.8142	0.8049
0.001	33.0	198	0.7931	0.8049
0.0005	34.0	204	0.7822	0.8049
0.0004	35.0	210	0.7974	0.8293
0.0004	36.0	216	0.8092	0.8293
0.0001	37.0	222	0.8155	0.8293
0.0001	38.0	228	0.8178	0.8293
0.0001	39.0	234	0.8178	0.8293
0.0002	40.0	240	0.8165	0.8293
0.0002	41.0	246	0.8159	0.8293
0.0004	42.0	252	0.8158	0.8293
0.0004	43.0	258	0.8158	0.8293
0.0003	44.0	264	0.8158	0.8293
0.0001	45.0	270	0.8158	0.8293
0.0001	46.0	276	0.8158	0.8293
0.0011	47.0	282	0.8158	0.8293
0.0011	48.0	288	0.8158	0.8293
0.0001	49.0	294	0.8158	0.8293
0.0001	50.0	300	0.8158	0.8293

Framework versions

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