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_5x_beit_base_adamax_00001_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: 0.8985024958402662

smids_5x_beit_base_adamax_00001_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: 0.8394
• Accuracy: 0.8985

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
0.3036	1.0	375	0.2703	0.8918
0.2118	2.0	750	0.2674	0.8968
0.1557	3.0	1125	0.2889	0.8918
0.074	4.0	1500	0.2842	0.9002
0.0616	5.0	1875	0.3403	0.8935
0.036	6.0	2250	0.3534	0.9101
0.0382	7.0	2625	0.4309	0.8985
0.0686	8.0	3000	0.4834	0.8985
0.022	9.0	3375	0.5298	0.8935
0.0159	10.0	3750	0.5866	0.8985
0.0173	11.0	4125	0.5610	0.8968
0.0241	12.0	4500	0.6962	0.8869
0.0123	13.0	4875	0.6252	0.8952
0.0054	14.0	5250	0.6170	0.9002
0.0251	15.0	5625	0.6453	0.8952
0.0003	16.0	6000	0.6804	0.8952
0.0563	17.0	6375	0.6912	0.8985
0.0079	18.0	6750	0.6905	0.9018
0.0009	19.0	7125	0.7171	0.8935
0.0206	20.0	7500	0.7602	0.8985
0.0222	21.0	7875	0.7242	0.8952
0.0005	22.0	8250	0.7227	0.9002
0.0001	23.0	8625	0.7725	0.9002
0.0002	24.0	9000	0.7700	0.8935
0.0001	25.0	9375	0.7746	0.8985
0.0001	26.0	9750	0.7609	0.9018
0.017	27.0	10125	0.8256	0.8918
0.0019	28.0	10500	0.7444	0.8952
0.0254	29.0	10875	0.7839	0.9035
0.0041	30.0	11250	0.7929	0.9002
0.0018	31.0	11625	0.7983	0.8968
0.0163	32.0	12000	0.8337	0.8968
0.0122	33.0	12375	0.8065	0.8918
0.0021	34.0	12750	0.8472	0.8968
0.0003	35.0	13125	0.8572	0.8968
0.0036	36.0	13500	0.8680	0.8935
0.0086	37.0	13875	0.8533	0.8935
0.0002	38.0	14250	0.8606	0.8885
0.0065	39.0	14625	0.8465	0.8869
0.0212	40.0	15000	0.8444	0.8952
0.0163	41.0	15375	0.8576	0.8918
0.0071	42.0	15750	0.8227	0.8952
0.0234	43.0	16125	0.8305	0.8935
0.0019	44.0	16500	0.8174	0.9002
0.0226	45.0	16875	0.8559	0.8902
0.0176	46.0	17250	0.8405	0.8918
0.0236	47.0	17625	0.8413	0.8952
0.0179	48.0	18000	0.8437	0.8985
0.0141	49.0	18375	0.8368	0.8968
0.0007	50.0	18750	0.8394	0.8985

Framework versions

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