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_sgd_00001_fold1
    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: 0.2

hushem_1x_deit_tiny_sgd_00001_fold1

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: 1.6938
Accuracy: 0.2

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	1.6986	0.2
1.6333	2.0	12	1.6983	0.2
1.6333	3.0	18	1.6981	0.2
1.6088	4.0	24	1.6979	0.2
1.6296	5.0	30	1.6976	0.2
1.6296	6.0	36	1.6974	0.2
1.6252	7.0	42	1.6972	0.2
1.6252	8.0	48	1.6970	0.2
1.6833	9.0	54	1.6968	0.2
1.5983	10.0	60	1.6965	0.2
1.5983	11.0	66	1.6964	0.2
1.61	12.0	72	1.6962	0.2
1.61	13.0	78	1.6960	0.2
1.6125	14.0	84	1.6958	0.2
1.6595	15.0	90	1.6957	0.2
1.6595	16.0	96	1.6956	0.2
1.6372	17.0	102	1.6954	0.2
1.6372	18.0	108	1.6953	0.2
1.6292	19.0	114	1.6951	0.2
1.6414	20.0	120	1.6950	0.2
1.6414	21.0	126	1.6949	0.2
1.6168	22.0	132	1.6948	0.2
1.6168	23.0	138	1.6947	0.2
1.6445	24.0	144	1.6946	0.2
1.6172	25.0	150	1.6945	0.2
1.6172	26.0	156	1.6944	0.2
1.5925	27.0	162	1.6944	0.2
1.5925	28.0	168	1.6943	0.2
1.6351	29.0	174	1.6942	0.2
1.6161	30.0	180	1.6941	0.2
1.6161	31.0	186	1.6941	0.2
1.6095	32.0	192	1.6940	0.2
1.6095	33.0	198	1.6940	0.2
1.6215	34.0	204	1.6939	0.2
1.6213	35.0	210	1.6939	0.2
1.6213	36.0	216	1.6939	0.2
1.6372	37.0	222	1.6938	0.2
1.6372	38.0	228	1.6938	0.2
1.6199	39.0	234	1.6938	0.2
1.6087	40.0	240	1.6938	0.2
1.6087	41.0	246	1.6938	0.2
1.6309	42.0	252	1.6938	0.2
1.6309	43.0	258	1.6938	0.2
1.6203	44.0	264	1.6938	0.2
1.6564	45.0	270	1.6938	0.2
1.6564	46.0	276	1.6938	0.2
1.6178	47.0	282	1.6938	0.2
1.6178	48.0	288	1.6938	0.2
1.6557	49.0	294	1.6938	0.2
1.6181	50.0	300	1.6938	0.2

Framework versions

Transformers 4.35.2
Pytorch 2.1.0+cu118
Datasets 2.15.0
Tokenizers 0.15.0