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: hushem_5x_beit_base_adamax_0001_fold3
    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: 0.9069767441860465

hushem_5x_beit_base_adamax_0001_fold3

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: 0.6694
• Accuracy: 0.9070

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
0.6265	1.0	28	0.3819	0.8605
0.0727	2.0	56	0.5303	0.8605
0.0183	3.0	84	0.1970	0.9535
0.0423	4.0	112	0.6710	0.8837
0.0178	5.0	140	0.4713	0.9070
0.0022	6.0	168	0.7231	0.8837
0.021	7.0	196	0.4951	0.9302
0.0006	8.0	224	0.4984	0.8837
0.0004	9.0	252	0.7699	0.8837
0.0781	10.0	280	0.7123	0.9070
0.0003	11.0	308	0.6383	0.9070
0.0002	12.0	336	0.6654	0.9302
0.0055	13.0	364	0.4551	0.9070
0.0001	14.0	392	0.4856	0.9070
0.0001	15.0	420	0.5026	0.9070
0.0003	16.0	448	0.2950	0.8837
0.0001	17.0	476	0.4641	0.8837
0.0001	18.0	504	0.4082	0.8837
0.0001	19.0	532	0.3703	0.9070
0.0001	20.0	560	0.3892	0.9070
0.0001	21.0	588	0.5289	0.9302
0.0001	22.0	616	0.4284	0.9070
0.0002	23.0	644	0.4542	0.9070
0.0001	24.0	672	0.4331	0.9070
0.0001	25.0	700	0.4393	0.9070
0.0	26.0	728	0.4637	0.9070
0.0	27.0	756	0.5072	0.9070
0.0	28.0	784	0.5234	0.9070
0.0001	29.0	812	0.5189	0.9070
0.0	30.0	840	0.5184	0.9070
0.0003	31.0	868	0.6238	0.9070
0.0001	32.0	896	0.6644	0.9070
0.0	33.0	924	0.6539	0.9070
0.0	34.0	952	0.6525	0.9070
0.0011	35.0	980	0.6265	0.9070
0.0001	36.0	1008	0.6208	0.9070
0.0001	37.0	1036	0.6404	0.9070
0.0001	38.0	1064	0.6545	0.9070
0.0	39.0	1092	0.6632	0.9070
0.0006	40.0	1120	0.6346	0.9070
0.0001	41.0	1148	0.6383	0.9070
0.0	42.0	1176	0.6312	0.9070
0.0	43.0	1204	0.6573	0.9070
0.0	44.0	1232	0.6635	0.9070
0.0002	45.0	1260	0.6659	0.9070
0.0002	46.0	1288	0.6644	0.9070
0.0	47.0	1316	0.6681	0.9070
0.0001	48.0	1344	0.6694	0.9070
0.0	49.0	1372	0.6694	0.9070
0.0	50.0	1400	0.6694	0.9070

Framework versions

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