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: smids_1x_deit_tiny_rms_0001_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: 0.8647746243739566

smids_1x_deit_tiny_rms_0001_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: 1.0693
• Accuracy: 0.8648

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
0.7287	1.0	76	0.8533	0.6394
0.5852	2.0	152	0.6881	0.7195
0.3351	3.0	228	0.4986	0.7997
0.2896	4.0	304	0.4784	0.8280
0.1989	5.0	380	0.4421	0.8664
0.1697	6.0	456	0.5180	0.8381
0.1375	7.0	532	0.6205	0.8331
0.099	8.0	608	0.5628	0.8631
0.0915	9.0	684	0.7872	0.8464
0.0302	10.0	760	0.6523	0.8748
0.067	11.0	836	0.7797	0.8447
0.0423	12.0	912	0.7040	0.8548
0.0283	13.0	988	0.7674	0.8631
0.0338	14.0	1064	0.7877	0.8564
0.0931	15.0	1140	0.9177	0.8381
0.0232	16.0	1216	0.9119	0.8531
0.0145	17.0	1292	0.9967	0.8514
0.0553	18.0	1368	0.9035	0.8531
0.0024	19.0	1444	0.9160	0.8631
0.0523	20.0	1520	0.8356	0.8648
0.033	21.0	1596	1.0628	0.8531
0.0448	22.0	1672	0.8647	0.8664
0.0183	23.0	1748	1.0897	0.8481
0.0002	24.0	1824	1.0415	0.8431
0.0163	25.0	1900	0.9932	0.8581
0.0047	26.0	1976	1.1496	0.8514
0.0072	27.0	2052	1.0645	0.8531
0.0133	28.0	2128	1.1427	0.8297
0.0062	29.0	2204	1.0607	0.8531
0.0	30.0	2280	0.9174	0.8715
0.0155	31.0	2356	1.0165	0.8598
0.0239	32.0	2432	1.0075	0.8698
0.0001	33.0	2508	1.0034	0.8731
0.0	34.0	2584	1.0346	0.8598
0.0119	35.0	2660	0.9934	0.8631
0.0037	36.0	2736	1.0215	0.8614
0.0079	37.0	2812	0.9915	0.8698
0.0	38.0	2888	1.0008	0.8698
0.0032	39.0	2964	1.0184	0.8731
0.0	40.0	3040	1.0021	0.8664
0.0033	41.0	3116	1.0395	0.8698
0.0	42.0	3192	1.0443	0.8664
0.0049	43.0	3268	1.0447	0.8681
0.0	44.0	3344	1.0507	0.8664
0.0	45.0	3420	1.0520	0.8648
0.0	46.0	3496	1.0585	0.8648
0.0	47.0	3572	1.0642	0.8648
0.0026	48.0	3648	1.0682	0.8648
0.0	49.0	3724	1.0688	0.8648
0.0	50.0	3800	1.0693	0.8648

Framework versions

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