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_5x_beit_base_rms_00001_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: 0.8048780487804879

hushem_5x_beit_base_rms_00001_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: 1.1845
• Accuracy: 0.8049

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
0.9367	1.0	28	0.6533	0.7073
0.1926	2.0	56	0.5512	0.7805
0.047	3.0	84	0.6007	0.8049
0.0193	4.0	112	0.2590	0.9024
0.0089	5.0	140	0.4654	0.8293
0.0038	6.0	168	0.5932	0.8293
0.0017	7.0	196	0.6877	0.8293
0.0014	8.0	224	0.7982	0.8049
0.0007	9.0	252	0.6044	0.8293
0.0007	10.0	280	0.6788	0.8537
0.0003	11.0	308	0.6662	0.8537
0.0003	12.0	336	0.6588	0.8537
0.0002	13.0	364	0.6343	0.8293
0.0046	14.0	392	1.0649	0.7805
0.0012	15.0	420	0.7359	0.8293
0.0005	16.0	448	0.7345	0.8293
0.0066	17.0	476	0.7816	0.8537
0.0014	18.0	504	0.6553	0.8780
0.0003	19.0	532	0.5879	0.8780
0.0001	20.0	560	0.6539	0.8537
0.0001	21.0	588	0.5762	0.8293
0.0006	22.0	616	0.3307	0.8293
0.0001	23.0	644	0.6447	0.8293
0.0002	24.0	672	0.7471	0.8537
0.0002	25.0	700	0.6200	0.8537
0.0001	26.0	728	0.9057	0.8537
0.0001	27.0	756	0.8578	0.8537
0.0004	28.0	784	0.7354	0.8537
0.0001	29.0	812	0.8285	0.8537
0.0004	30.0	840	0.7442	0.8780
0.0001	31.0	868	0.9315	0.8049
0.0002	32.0	896	1.0255	0.8049
0.0	33.0	924	1.0401	0.7805
0.0001	34.0	952	1.0520	0.8293
0.0004	35.0	980	0.9869	0.8537
0.0	36.0	1008	0.9764	0.8537
0.0001	37.0	1036	0.9356	0.8537
0.0001	38.0	1064	1.1522	0.8049
0.0	39.0	1092	1.0978	0.8049
0.0005	40.0	1120	1.0647	0.8293
0.0003	41.0	1148	1.2331	0.8049
0.0	42.0	1176	1.3110	0.8049
0.0	43.0	1204	1.2050	0.8049
0.0	44.0	1232	1.1647	0.8049
0.0002	45.0	1260	1.2154	0.8049
0.0001	46.0	1288	1.2000	0.8049
0.0001	47.0	1316	1.1915	0.8049
0.0	48.0	1344	1.1844	0.8049
0.0001	49.0	1372	1.1845	0.8049
0.0	50.0	1400	1.1845	0.8049

Framework versions

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