README.md

metadata

license: apache-2.0
base_model: facebook/deit-tiny-patch16-224
tags:
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - accuracy
model-index:
  - name: hushem_1x_deit_tiny_rms_00001_fold3
    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: 0.7674418604651163

hushem_1x_deit_tiny_rms_00001_fold3

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

• Loss: 0.6755
• Accuracy: 0.7674

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	1.2450	0.3953
1.3266	2.0	12	1.0282	0.4884
1.3266	3.0	18	0.8766	0.6512
0.6113	4.0	24	0.8143	0.6279
0.301	5.0	30	0.9703	0.6047
0.301	6.0	36	0.7894	0.7209
0.1194	7.0	42	0.8712	0.6512
0.1194	8.0	48	0.7416	0.6744
0.0478	9.0	54	0.7289	0.6744
0.0192	10.0	60	0.6181	0.7209
0.0192	11.0	66	0.7194	0.6977
0.007	12.0	72	0.6519	0.6744
0.007	13.0	78	0.6428	0.7209
0.0038	14.0	84	0.6323	0.6977
0.0027	15.0	90	0.6303	0.7209
0.0027	16.0	96	0.6496	0.7209
0.0021	17.0	102	0.6367	0.7209
0.0021	18.0	108	0.6386	0.7209
0.0018	19.0	114	0.6562	0.7442
0.0015	20.0	120	0.6541	0.7442
0.0015	21.0	126	0.6493	0.7442
0.0014	22.0	132	0.6669	0.7442
0.0014	23.0	138	0.6543	0.7674
0.0012	24.0	144	0.6581	0.7442
0.0011	25.0	150	0.6534	0.7442
0.0011	26.0	156	0.6644	0.7442
0.001	27.0	162	0.6622	0.7674
0.001	28.0	168	0.6583	0.7442
0.001	29.0	174	0.6594	0.7674
0.0009	30.0	180	0.6672	0.7674
0.0009	31.0	186	0.6681	0.7674
0.0008	32.0	192	0.6656	0.7674
0.0008	33.0	198	0.6699	0.7674
0.0008	34.0	204	0.6718	0.7674
0.0008	35.0	210	0.6718	0.7674
0.0008	36.0	216	0.6735	0.7674
0.0008	37.0	222	0.6740	0.7674
0.0008	38.0	228	0.6754	0.7674
0.0007	39.0	234	0.6750	0.7674
0.0007	40.0	240	0.6751	0.7674
0.0007	41.0	246	0.6753	0.7674
0.0007	42.0	252	0.6755	0.7674
0.0007	43.0	258	0.6755	0.7674
0.0007	44.0	264	0.6755	0.7674
0.0007	45.0	270	0.6755	0.7674
0.0007	46.0	276	0.6755	0.7674
0.0007	47.0	282	0.6755	0.7674
0.0007	48.0	288	0.6755	0.7674
0.0007	49.0	294	0.6755	0.7674
0.0007	50.0	300	0.6755	0.7674

Framework versions

• Transformers 4.35.0
• Pytorch 2.1.0+cu118
• Datasets 2.14.6
• Tokenizers 0.14.1