README.md

metadata

license: apache-2.0
base_model: microsoft/beit-base-patch16-224
tags:
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - accuracy
model-index:
  - name: smids_1x_beit_base_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: 0.7903494176372712

smids_1x_beit_base_adamax_001_fold2

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

• Loss: 1.4865
• Accuracy: 0.7903

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
0.9007	1.0	75	0.8802	0.5191
0.7789	2.0	150	0.8973	0.5424
0.8219	3.0	225	0.7607	0.6406
0.7838	4.0	300	0.7358	0.6522
0.6602	5.0	375	0.6978	0.6672
0.7026	6.0	450	0.6685	0.6955
0.6394	7.0	525	0.7731	0.6589
0.6471	8.0	600	0.6234	0.7138
0.5881	9.0	675	0.6358	0.7205
0.5254	10.0	750	0.5746	0.7671
0.5153	11.0	825	0.5501	0.7704
0.5459	12.0	900	0.5543	0.7687
0.5526	13.0	975	0.5321	0.7737
0.5236	14.0	1050	0.5404	0.7937
0.4317	15.0	1125	0.6220	0.7604
0.4195	16.0	1200	0.5679	0.7854
0.3753	17.0	1275	0.6021	0.7687
0.3821	18.0	1350	0.5958	0.7854
0.3599	19.0	1425	0.6478	0.7837
0.2813	20.0	1500	0.6634	0.7671
0.224	21.0	1575	0.6766	0.7820
0.2635	22.0	1650	0.6781	0.7870
0.1832	23.0	1725	0.8041	0.7604
0.1751	24.0	1800	0.8069	0.7671
0.2421	25.0	1875	0.8820	0.7737
0.2115	26.0	1950	0.8838	0.7970
0.1798	27.0	2025	0.8954	0.7787
0.1341	28.0	2100	1.0505	0.7987
0.0669	29.0	2175	1.2992	0.7770
0.0892	30.0	2250	1.1168	0.7987
0.1159	31.0	2325	1.2066	0.7870
0.1289	32.0	2400	1.5859	0.7687
0.0687	33.0	2475	1.1777	0.7887
0.0226	34.0	2550	1.4423	0.7854
0.04	35.0	2625	1.4594	0.7870
0.0552	36.0	2700	1.3867	0.7820
0.0439	37.0	2775	1.4599	0.7720
0.0308	38.0	2850	1.4968	0.7903
0.0564	39.0	2925	1.5256	0.7953
0.0227	40.0	3000	1.4454	0.7953
0.0214	41.0	3075	1.3100	0.8087
0.0167	42.0	3150	1.4699	0.7987
0.0299	43.0	3225	1.4525	0.7903
0.0171	44.0	3300	1.3889	0.8053
0.011	45.0	3375	1.3819	0.7920
0.014	46.0	3450	1.5122	0.7903
0.0198	47.0	3525	1.4328	0.7920
0.0085	48.0	3600	1.5057	0.7920
0.0028	49.0	3675	1.4856	0.7903
0.0049	50.0	3750	1.4865	0.7903

Framework versions

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