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_0001_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: 0.8901830282861897

smids_1x_beit_base_adamax_0001_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: 0.7859
• Accuracy: 0.8902

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: 0.0001
• 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
0.357	1.0	75	0.2942	0.8852
0.196	2.0	150	0.2977	0.8769
0.1343	3.0	225	0.3454	0.8835
0.1165	4.0	300	0.4770	0.8586
0.0357	5.0	375	0.3863	0.8819
0.0407	6.0	450	0.5588	0.8785
0.0487	7.0	525	0.5410	0.8769
0.0422	8.0	600	0.5327	0.8835
0.0252	9.0	675	0.5671	0.8885
0.0072	10.0	750	0.5229	0.8852
0.0013	11.0	825	0.5397	0.9018
0.0233	12.0	900	0.6716	0.8902
0.0031	13.0	975	0.6232	0.8935
0.0106	14.0	1050	0.6722	0.8835
0.0052	15.0	1125	0.5873	0.9101
0.0117	16.0	1200	0.6014	0.8935
0.0056	17.0	1275	0.6190	0.8952
0.018	18.0	1350	0.6714	0.8902
0.0034	19.0	1425	0.6903	0.8918
0.0034	20.0	1500	0.6789	0.8902
0.0018	21.0	1575	0.7049	0.8852
0.0015	22.0	1650	0.8451	0.8802
0.0032	23.0	1725	0.6725	0.8885
0.0116	24.0	1800	0.7163	0.8952
0.0001	25.0	1875	0.6827	0.8918
0.004	26.0	1950	0.7084	0.8885
0.012	27.0	2025	0.7239	0.8968
0.0099	28.0	2100	0.7371	0.8918
0.0044	29.0	2175	0.7635	0.8869
0.0039	30.0	2250	0.7043	0.8918
0.0035	31.0	2325	0.7276	0.8902
0.0	32.0	2400	0.7428	0.8935
0.0	33.0	2475	0.7968	0.8852
0.014	34.0	2550	0.7553	0.8918
0.0048	35.0	2625	0.7230	0.8968
0.0029	36.0	2700	0.7674	0.8869
0.0	37.0	2775	0.7425	0.8918
0.0023	38.0	2850	0.7970	0.8902
0.0047	39.0	2925	0.8047	0.8869
0.0021	40.0	3000	0.7994	0.8885
0.0	41.0	3075	0.7761	0.8852
0.0025	42.0	3150	0.7890	0.8885
0.0046	43.0	3225	0.7889	0.8885
0.0	44.0	3300	0.7915	0.8852
0.0047	45.0	3375	0.7967	0.8885
0.0	46.0	3450	0.7946	0.8869
0.002	47.0	3525	0.7884	0.8885
0.0	48.0	3600	0.7873	0.8885
0.0	49.0	3675	0.7859	0.8902
0.0	50.0	3750	0.7859	0.8902

Framework versions

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