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_001_fold4
    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: 0.4523809523809524

hushem_1x_beit_base_adamax_001_fold4

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: 4.3503
• Accuracy: 0.4524

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: 0.001
• 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	1.4229	0.2381
2.0151	2.0	12	1.3893	0.2619
2.0151	3.0	18	1.3408	0.3333
1.3963	4.0	24	1.3326	0.3095
1.3169	5.0	30	1.2412	0.4762
1.3169	6.0	36	1.0247	0.5476
1.2588	7.0	42	1.2101	0.3571
1.2588	8.0	48	1.0013	0.5238
1.1685	9.0	54	1.3288	0.4524
1.1624	10.0	60	1.0173	0.5
1.1624	11.0	66	1.2213	0.4762
1.163	12.0	72	1.3131	0.4286
1.163	13.0	78	1.0794	0.5238
1.0128	14.0	84	1.2744	0.3810
1.1156	15.0	90	1.2253	0.5
1.1156	16.0	96	1.2674	0.4048
0.9374	17.0	102	1.1623	0.4524
0.9374	18.0	108	1.5694	0.4048
0.9149	19.0	114	1.0570	0.5476
0.912	20.0	120	1.2919	0.4286
0.912	21.0	126	1.4307	0.5
0.6869	22.0	132	1.5771	0.5238
0.6869	23.0	138	2.1692	0.3571
0.6883	24.0	144	1.5822	0.5714
0.7288	25.0	150	2.0687	0.4524
0.7288	26.0	156	2.1992	0.4524
0.4823	27.0	162	2.2715	0.5238
0.4823	28.0	168	3.3968	0.4286
0.4173	29.0	174	2.2538	0.5476
0.4253	30.0	180	3.6242	0.3810
0.4253	31.0	186	2.4386	0.5952
0.3088	32.0	192	3.2728	0.4762
0.3088	33.0	198	3.5241	0.5476
0.1666	34.0	204	3.5230	0.5
0.2645	35.0	210	3.7888	0.4286
0.2645	36.0	216	4.2240	0.5238
0.1416	37.0	222	4.2393	0.5
0.1416	38.0	228	4.0612	0.4762
0.1169	39.0	234	4.3686	0.4524
0.0781	40.0	240	4.2437	0.4762
0.0781	41.0	246	4.2703	0.4286
0.06	42.0	252	4.3503	0.4524
0.06	43.0	258	4.3503	0.4524
0.0264	44.0	264	4.3503	0.4524
0.1093	45.0	270	4.3503	0.4524
0.1093	46.0	276	4.3503	0.4524
0.0479	47.0	282	4.3503	0.4524
0.0479	48.0	288	4.3503	0.4524
0.0488	49.0	294	4.3503	0.4524
0.0619	50.0	300	4.3503	0.4524

Framework versions

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