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_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: 0.8336106489184693

smids_1x_deit_tiny_adamax_001_fold2

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: 1.3785
• Accuracy: 0.8336

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
0.8106	1.0	75	0.7856	0.5657
0.8289	2.0	150	0.7551	0.7121
0.6607	3.0	225	0.6595	0.7288
0.5966	4.0	300	0.5724	0.7671
0.5316	5.0	375	0.5404	0.7854
0.3929	6.0	450	0.5052	0.7970
0.407	7.0	525	0.4685	0.8303
0.3944	8.0	600	0.4515	0.8236
0.2836	9.0	675	0.4807	0.8070
0.2744	10.0	750	0.4423	0.8469
0.2808	11.0	825	0.4896	0.7953
0.152	12.0	900	0.5241	0.8319
0.1786	13.0	975	0.4922	0.8486
0.1372	14.0	1050	0.6687	0.8220
0.1982	15.0	1125	0.7505	0.8253
0.1651	16.0	1200	0.8354	0.8236
0.1906	17.0	1275	1.1129	0.7737
0.0899	18.0	1350	1.0319	0.8003
0.0875	19.0	1425	1.0962	0.7987
0.0186	20.0	1500	0.9631	0.8270
0.0742	21.0	1575	1.2547	0.7887
0.0229	22.0	1650	0.9476	0.8303
0.0161	23.0	1725	1.3651	0.8070
0.0097	24.0	1800	1.0596	0.8286
0.0082	25.0	1875	0.9954	0.8386
0.0036	26.0	1950	0.9671	0.8353
0.0205	27.0	2025	1.0817	0.8253
0.0109	28.0	2100	0.9995	0.8353
0.007	29.0	2175	1.1573	0.8369
0.0048	30.0	2250	1.2320	0.8303
0.0312	31.0	2325	1.1062	0.8453
0.0003	32.0	2400	1.3037	0.8436
0.0002	33.0	2475	1.2278	0.8403
0.0041	34.0	2550	1.3384	0.8286
0.0096	35.0	2625	1.3396	0.8303
0.0049	36.0	2700	1.3638	0.8403
0.0054	37.0	2775	1.3303	0.8303
0.0	38.0	2850	1.3273	0.8303
0.0017	39.0	2925	1.3584	0.8336
0.0	40.0	3000	1.3526	0.8319
0.0031	41.0	3075	1.3529	0.8303
0.0029	42.0	3150	1.3744	0.8336
0.0052	43.0	3225	1.3603	0.8319
0.0041	44.0	3300	1.3711	0.8336
0.0	45.0	3375	1.3741	0.8353
0.0002	46.0	3450	1.3699	0.8336
0.0029	47.0	3525	1.3797	0.8336
0.0	48.0	3600	1.3781	0.8336
0.0022	49.0	3675	1.3784	0.8336
0.0022	50.0	3750	1.3785	0.8336

Framework versions

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