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_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: 0.8416666666666667

smids_1x_deit_tiny_adamax_001_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: 1.4240
• Accuracy: 0.8417

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
0.7806	1.0	75	0.5704	0.7533
0.5207	2.0	150	0.5966	0.73
0.4092	3.0	225	0.5340	0.7933
0.4512	4.0	300	0.5755	0.76
0.3687	5.0	375	0.4431	0.8133
0.3021	6.0	450	0.4574	0.8317
0.3551	7.0	525	0.5806	0.8033
0.2614	8.0	600	0.5093	0.82
0.2361	9.0	675	0.5262	0.8333
0.1424	10.0	750	0.7202	0.83
0.1293	11.0	825	0.6267	0.8333
0.079	12.0	900	0.7445	0.845
0.1031	13.0	975	0.7831	0.8333
0.0209	14.0	1050	0.7336	0.8433
0.0822	15.0	1125	0.7507	0.8217
0.0881	16.0	1200	0.8785	0.8017
0.0659	17.0	1275	0.8910	0.8283
0.0765	18.0	1350	0.9993	0.825
0.0616	19.0	1425	0.7662	0.8417
0.0408	20.0	1500	0.7907	0.8517
0.0173	21.0	1575	1.0410	0.8383
0.0139	22.0	1650	1.0413	0.8333
0.0185	23.0	1725	1.0477	0.84
0.0006	24.0	1800	1.0787	0.8433
0.0277	25.0	1875	1.0695	0.83
0.0122	26.0	1950	1.1331	0.8517
0.0367	27.0	2025	1.3452	0.8283
0.0236	28.0	2100	1.0892	0.83
0.0104	29.0	2175	1.1352	0.8483
0.0001	30.0	2250	1.2537	0.8367
0.0002	31.0	2325	1.2507	0.8317
0.003	32.0	2400	1.2991	0.8333
0.0046	33.0	2475	1.2933	0.8333
0.0054	34.0	2550	1.3552	0.8317
0.0087	35.0	2625	1.3586	0.8333
0.0052	36.0	2700	1.3844	0.8367
0.0022	37.0	2775	1.3958	0.84
0.0	38.0	2850	1.4041	0.8417
0.0	39.0	2925	1.4038	0.84
0.0	40.0	3000	1.4046	0.8433
0.0	41.0	3075	1.4005	0.8433
0.0031	42.0	3150	1.4048	0.8417
0.0035	43.0	3225	1.4072	0.8433
0.0	44.0	3300	1.4113	0.8417
0.0028	45.0	3375	1.4120	0.8417
0.0026	46.0	3450	1.4166	0.84
0.0061	47.0	3525	1.4166	0.8417
0.0	48.0	3600	1.4221	0.84
0.0	49.0	3675	1.4223	0.84
0.0046	50.0	3750	1.4240	0.8417

Framework versions

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