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_3x_beit_base_rms_00001_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: 0.9066666666666666

smids_3x_beit_base_rms_00001_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: 0.9210
• Accuracy: 0.9067

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: 1e-05
• 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
0.2705	1.0	225	0.2918	0.8867
0.1226	2.0	450	0.2558	0.9033
0.1086	3.0	675	0.3279	0.9017
0.0616	4.0	900	0.4060	0.9
0.004	5.0	1125	0.5441	0.8967
0.0253	6.0	1350	0.5043	0.91
0.1141	7.0	1575	0.5368	0.9083
0.0284	8.0	1800	0.6779	0.8917
0.0461	9.0	2025	0.6024	0.9067
0.0081	10.0	2250	0.7134	0.8983
0.0002	11.0	2475	0.6405	0.9083
0.0399	12.0	2700	0.7188	0.9017
0.0307	13.0	2925	0.8188	0.8983
0.0003	14.0	3150	0.8326	0.8967
0.0034	15.0	3375	0.8891	0.895
0.063	16.0	3600	0.7795	0.8933
0.0282	17.0	3825	0.9130	0.9
0.0319	18.0	4050	0.8993	0.91
0.0347	19.0	4275	0.8296	0.9033
0.0001	20.0	4500	1.0072	0.895
0.0006	21.0	4725	0.8448	0.9067
0.0067	22.0	4950	0.8063	0.9017
0.0	23.0	5175	0.8686	0.905
0.0081	24.0	5400	0.9096	0.905
0.0036	25.0	5625	0.9376	0.9083
0.0003	26.0	5850	0.8940	0.9017
0.0002	27.0	6075	1.0157	0.9017
0.0	28.0	6300	0.9199	0.9033
0.0087	29.0	6525	0.8828	0.9133
0.0028	30.0	6750	0.9260	0.9083
0.0022	31.0	6975	0.8719	0.9183
0.0	32.0	7200	0.9025	0.9083
0.0039	33.0	7425	0.8825	0.9017
0.0	34.0	7650	0.8973	0.91
0.0019	35.0	7875	0.9103	0.9083
0.0	36.0	8100	0.9383	0.9033
0.0067	37.0	8325	1.0089	0.8983
0.0	38.0	8550	0.9107	0.9067
0.0004	39.0	8775	0.9825	0.9133
0.0	40.0	9000	1.0136	0.9017
0.0	41.0	9225	0.9657	0.905
0.0	42.0	9450	0.9670	0.9033
0.0042	43.0	9675	0.9419	0.9117
0.0	44.0	9900	0.9412	0.9083
0.0	45.0	10125	0.9113	0.91
0.0	46.0	10350	0.9674	0.9
0.0	47.0	10575	0.9600	0.9033
0.0	48.0	10800	0.9470	0.9083
0.015	49.0	11025	0.9211	0.9067
0.0	50.0	11250	0.9210	0.9067

Framework versions

• Transformers 4.32.1
• Pytorch 2.1.0+cu121
• Datasets 2.12.0
• Tokenizers 0.13.2