README.md

metadata

license: apache-2.0
base_model: facebook/deit-small-patch16-224
tags:
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - accuracy
model-index:
  - name: hushem_1x_deit_small_adamax_001_fold2
    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: 0.5777777777777777

hushem_1x_deit_small_adamax_001_fold2

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

• Loss: 3.0653
• Accuracy: 0.5778

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	1.5866	0.2444
1.9023	2.0	12	1.3764	0.2444
1.9023	3.0	18	1.3051	0.4222
1.349	4.0	24	1.1457	0.4889
1.2765	5.0	30	1.1296	0.5333
1.2765	6.0	36	1.0799	0.4667
0.9532	7.0	42	0.9251	0.5778
0.9532	8.0	48	0.9697	0.6
0.606	9.0	54	1.3926	0.4889
0.572	10.0	60	1.7732	0.5778
0.572	11.0	66	1.3882	0.5556
0.5961	12.0	72	1.7835	0.5333
0.5961	13.0	78	1.6876	0.5111
0.36	14.0	84	2.6292	0.5556
0.1021	15.0	90	3.3955	0.4444
0.1021	16.0	96	2.7199	0.5333
0.0705	17.0	102	3.2188	0.5778
0.0705	18.0	108	2.9572	0.5778
0.1408	19.0	114	3.4311	0.6222
0.0481	20.0	120	3.3680	0.5111
0.0481	21.0	126	3.9440	0.4889
0.0285	22.0	132	3.0805	0.5111
0.0285	23.0	138	3.2788	0.4889
0.0077	24.0	144	3.3798	0.5111
0.0144	25.0	150	3.3118	0.5333
0.0144	26.0	156	3.1251	0.5111
0.0005	27.0	162	2.9134	0.5778
0.0005	28.0	168	2.8352	0.6
0.0006	29.0	174	2.7529	0.5778
0.0002	30.0	180	2.8235	0.6
0.0002	31.0	186	2.8802	0.6
0.0001	32.0	192	2.9253	0.5778
0.0001	33.0	198	2.9651	0.5778
0.0001	34.0	204	2.9943	0.5778
0.0001	35.0	210	3.0146	0.5778
0.0001	36.0	216	3.0314	0.5778
0.0001	37.0	222	3.0446	0.5778
0.0001	38.0	228	3.0538	0.5778
0.0001	39.0	234	3.0596	0.5778
0.0001	40.0	240	3.0631	0.5778
0.0001	41.0	246	3.0649	0.5778
0.0001	42.0	252	3.0653	0.5778
0.0001	43.0	258	3.0653	0.5778
0.0001	44.0	264	3.0653	0.5778
0.0001	45.0	270	3.0653	0.5778
0.0001	46.0	276	3.0653	0.5778
0.0001	47.0	282	3.0653	0.5778
0.0001	48.0	288	3.0653	0.5778
0.0001	49.0	294	3.0653	0.5778
0.0001	50.0	300	3.0653	0.5778

Framework versions

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