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_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: 0.9047619047619048

hushem_1x_beit_base_adamax_0001_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: 0.2926
• Accuracy: 0.9048

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	1.1428	0.6905
1.3492	2.0	12	0.5681	0.7857
1.3492	3.0	18	0.2529	0.9286
0.3166	4.0	24	0.2221	0.9524
0.0428	5.0	30	0.2913	0.9048
0.0428	6.0	36	0.3814	0.8571
0.0093	7.0	42	0.2701	0.9524
0.0093	8.0	48	0.2796	0.9286
0.0019	9.0	54	0.3043	0.9048
0.0029	10.0	60	0.4551	0.8810
0.0029	11.0	66	0.3262	0.9286
0.001	12.0	72	0.2680	0.9524
0.001	13.0	78	0.2601	0.9524
0.0006	14.0	84	0.3353	0.9048
0.0008	15.0	90	0.3915	0.9048
0.0008	16.0	96	0.4398	0.8810
0.0004	17.0	102	0.3988	0.9048
0.0004	18.0	108	0.3416	0.9048
0.0053	19.0	114	0.2975	0.9286
0.0004	20.0	120	0.2890	0.9286
0.0004	21.0	126	0.2852	0.9286
0.0061	22.0	132	0.2652	0.9286
0.0061	23.0	138	0.2502	0.9286
0.0002	24.0	144	0.2495	0.9286
0.0003	25.0	150	0.2641	0.9286
0.0003	26.0	156	0.2771	0.9286
0.0002	27.0	162	0.2877	0.9286
0.0002	28.0	168	0.3003	0.9286
0.0002	29.0	174	0.3118	0.9286
0.0002	30.0	180	0.3215	0.9286
0.0002	31.0	186	0.3282	0.9286
0.0003	32.0	192	0.3381	0.9286
0.0003	33.0	198	0.3472	0.9048
0.0002	34.0	204	0.3491	0.9048
0.0049	35.0	210	0.3154	0.9048
0.0049	36.0	216	0.2965	0.9048
0.0002	37.0	222	0.2887	0.9048
0.0002	38.0	228	0.2886	0.9048
0.0002	39.0	234	0.2894	0.9048
0.0002	40.0	240	0.2903	0.9048
0.0002	41.0	246	0.2922	0.9048
0.0004	42.0	252	0.2926	0.9048
0.0004	43.0	258	0.2926	0.9048
0.0002	44.0	264	0.2926	0.9048
0.0002	45.0	270	0.2926	0.9048
0.0002	46.0	276	0.2926	0.9048
0.0009	47.0	282	0.2926	0.9048
0.0009	48.0	288	0.2926	0.9048
0.0004	49.0	294	0.2926	0.9048
0.0001	50.0	300	0.2926	0.9048

Framework versions

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