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_fold4
    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: 0.84

smids_1x_deit_tiny_adamax_001_fold4

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: 1.6471
• Accuracy: 0.84

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
0.7464	1.0	75	0.5642	0.795
0.5514	2.0	150	0.5108	0.8017
0.3856	3.0	225	0.5385	0.8033
0.4541	4.0	300	0.4488	0.825
0.4047	5.0	375	0.4448	0.815
0.2699	6.0	450	0.5321	0.8267
0.3444	7.0	525	0.4477	0.8367
0.1984	8.0	600	0.5491	0.81
0.1797	9.0	675	0.7263	0.8167
0.1145	10.0	750	0.6218	0.8317
0.1353	11.0	825	0.7800	0.8183
0.1658	12.0	900	0.6252	0.835
0.101	13.0	975	0.8640	0.805
0.0897	14.0	1050	0.9357	0.8
0.0267	15.0	1125	1.0487	0.8283
0.0597	16.0	1200	1.0545	0.8283
0.0984	17.0	1275	0.9221	0.83
0.0994	18.0	1350	0.9468	0.8367
0.0261	19.0	1425	1.1404	0.8117
0.0439	20.0	1500	1.1737	0.8233
0.0258	21.0	1575	1.1898	0.8383
0.0027	22.0	1650	1.4604	0.8217
0.0296	23.0	1725	1.3681	0.8267
0.004	24.0	1800	1.5826	0.83
0.0296	25.0	1875	1.2731	0.8167
0.0022	26.0	1950	1.4166	0.83
0.0213	27.0	2025	1.3755	0.8433
0.0191	28.0	2100	1.6417	0.82
0.0068	29.0	2175	1.3938	0.8417
0.0003	30.0	2250	1.4213	0.8317
0.0002	31.0	2325	1.4622	0.8417
0.0	32.0	2400	1.5110	0.8367
0.0291	33.0	2475	1.4845	0.8383
0.0005	34.0	2550	1.5757	0.8333
0.0089	35.0	2625	1.6525	0.83
0.0053	36.0	2700	1.6166	0.84
0.0078	37.0	2775	1.5899	0.8467
0.0	38.0	2850	1.6250	0.8433
0.0004	39.0	2925	1.6311	0.8433
0.0	40.0	3000	1.6268	0.8433
0.0032	41.0	3075	1.6310	0.8417
0.0	42.0	3150	1.6322	0.84
0.0	43.0	3225	1.6387	0.84
0.0	44.0	3300	1.6405	0.84
0.0	45.0	3375	1.6426	0.84
0.0	46.0	3450	1.6435	0.84
0.0	47.0	3525	1.6443	0.84
0.0	48.0	3600	1.6452	0.84
0.0	49.0	3675	1.6465	0.84
0.0	50.0	3750	1.6471	0.84

Framework versions

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