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_fold5
    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: 0.7633333333333333

smids_1x_beit_base_adamax_001_fold5

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: 2.1833
• Accuracy: 0.7633

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
0.9804	1.0	75	0.8561	0.5383
0.8823	2.0	150	0.7905	0.5767
0.8002	3.0	225	0.7961	0.5633
0.8142	4.0	300	0.8679	0.6133
0.6765	5.0	375	0.6964	0.6817
0.652	6.0	450	0.6686	0.7
0.6785	7.0	525	0.6625	0.7067
0.5659	8.0	600	0.6154	0.7217
0.6383	9.0	675	0.6262	0.7117
0.5991	10.0	750	0.5856	0.7633
0.4627	11.0	825	0.5901	0.7633
0.5021	12.0	900	0.5968	0.7433
0.5421	13.0	975	0.5857	0.74
0.3951	14.0	1050	0.5723	0.7733
0.4943	15.0	1125	0.6046	0.7533
0.4076	16.0	1200	0.6196	0.7567
0.379	17.0	1275	0.5906	0.7817
0.3759	18.0	1350	0.5998	0.775
0.3383	19.0	1425	0.6508	0.7567
0.2622	20.0	1500	0.6675	0.775
0.316	21.0	1575	0.7118	0.785
0.2478	22.0	1650	0.7508	0.78
0.2696	23.0	1725	0.7052	0.7733
0.1441	24.0	1800	0.8658	0.7783
0.1966	25.0	1875	0.9393	0.7417
0.1228	26.0	1950	1.0783	0.7567
0.2151	27.0	2025	1.0051	0.7533
0.1799	28.0	2100	1.0898	0.755
0.1053	29.0	2175	1.0567	0.7533
0.122	30.0	2250	1.1544	0.7583
0.1375	31.0	2325	1.3014	0.7617
0.0659	32.0	2400	1.6359	0.765
0.0997	33.0	2475	1.4213	0.7717
0.0852	34.0	2550	1.6657	0.7467
0.0752	35.0	2625	1.5943	0.7733
0.0405	36.0	2700	1.5865	0.7583
0.0174	37.0	2775	1.8002	0.7533
0.0364	38.0	2850	1.6078	0.7583
0.0269	39.0	2925	2.0543	0.7667
0.0034	40.0	3000	2.1698	0.7517
0.0428	41.0	3075	1.8011	0.74
0.0355	42.0	3150	2.1588	0.7567
0.0068	43.0	3225	2.0789	0.7617
0.013	44.0	3300	2.0235	0.76
0.0102	45.0	3375	1.9567	0.7567
0.0216	46.0	3450	1.9788	0.765
0.0016	47.0	3525	2.1056	0.765
0.0046	48.0	3600	2.1156	0.7633
0.0115	49.0	3675	2.2014	0.7617
0.0156	50.0	3750	2.1833	0.7633

Framework versions

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