README.md

metadata

license: apache-2.0
base_model: facebook/deit-base-patch16-224
tags:
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - accuracy
model-index:
  - name: hushem_1x_deit_base_rms_00001_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: 0.9523809523809523

hushem_1x_deit_base_rms_00001_fold4

This model is a fine-tuned version of facebook/deit-base-patch16-224 on the imagefolder dataset. It achieves the following results on the evaluation set:

• Loss: 0.1646
• Accuracy: 0.9524

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	1.2420	0.5476
1.2334	2.0	12	1.0719	0.4762
1.2334	3.0	18	0.5624	0.8333
0.5394	4.0	24	0.4815	0.8333
0.1826	5.0	30	0.4341	0.8333
0.1826	6.0	36	0.3198	0.9286
0.0424	7.0	42	0.2589	0.9286
0.0424	8.0	48	0.2146	0.9286
0.0113	9.0	54	0.1989	0.9286
0.0057	10.0	60	0.1966	0.9286
0.0057	11.0	66	0.1888	0.9286
0.004	12.0	72	0.1874	0.9286
0.004	13.0	78	0.1826	0.9286
0.0032	14.0	84	0.1800	0.9524
0.0027	15.0	90	0.1793	0.9524
0.0027	16.0	96	0.1777	0.9524
0.0022	17.0	102	0.1759	0.9524
0.0022	18.0	108	0.1747	0.9524
0.002	19.0	114	0.1746	0.9524
0.0018	20.0	120	0.1735	0.9524
0.0018	21.0	126	0.1728	0.9524
0.0015	22.0	132	0.1728	0.9524
0.0015	23.0	138	0.1714	0.9524
0.0014	24.0	144	0.1703	0.9524
0.0013	25.0	150	0.1698	0.9524
0.0013	26.0	156	0.1687	0.9524
0.0012	27.0	162	0.1685	0.9524
0.0012	28.0	168	0.1678	0.9524
0.0011	29.0	174	0.1675	0.9524
0.001	30.0	180	0.1677	0.9524
0.001	31.0	186	0.1670	0.9524
0.001	32.0	192	0.1667	0.9524
0.001	33.0	198	0.1661	0.9524
0.001	34.0	204	0.1660	0.9524
0.0009	35.0	210	0.1655	0.9524
0.0009	36.0	216	0.1652	0.9524
0.0009	37.0	222	0.1650	0.9524
0.0009	38.0	228	0.1648	0.9524
0.0009	39.0	234	0.1647	0.9524
0.0009	40.0	240	0.1647	0.9524
0.0009	41.0	246	0.1646	0.9524
0.0009	42.0	252	0.1646	0.9524
0.0009	43.0	258	0.1646	0.9524
0.0008	44.0	264	0.1646	0.9524
0.0009	45.0	270	0.1646	0.9524
0.0009	46.0	276	0.1646	0.9524
0.0008	47.0	282	0.1646	0.9524
0.0008	48.0	288	0.1646	0.9524
0.0008	49.0	294	0.1646	0.9524
0.0009	50.0	300	0.1646	0.9524

Framework versions

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