metadata

license: apache-2.0
base_model: microsoft/beit-large-patch16-224
tags:
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - accuracy
model-index:
  - name: smids_10x_beit_large_sgd_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: 0.8768718801996672

smids_10x_beit_large_sgd_0001_fold2

This model is a fine-tuned version of microsoft/beit-large-patch16-224 on the imagefolder dataset. It achieves the following results on the evaluation set:

Loss: 0.3022
Accuracy: 0.8769

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
0.9337	1.0	750	0.9902	0.5025
0.7559	2.0	1500	0.8323	0.6206
0.6418	3.0	2250	0.7119	0.7205
0.6498	4.0	3000	0.6261	0.7737
0.5308	5.0	3750	0.5616	0.8020
0.5189	6.0	4500	0.5157	0.8186
0.4977	7.0	5250	0.4808	0.8303
0.4495	8.0	6000	0.4552	0.8369
0.4544	9.0	6750	0.4332	0.8303
0.4325	10.0	7500	0.4166	0.8336
0.4708	11.0	8250	0.4025	0.8419
0.4375	12.0	9000	0.3904	0.8419
0.3875	13.0	9750	0.3796	0.8486
0.338	14.0	10500	0.3718	0.8486
0.3613	15.0	11250	0.3643	0.8502
0.3159	16.0	12000	0.3576	0.8569
0.313	17.0	12750	0.3520	0.8602
0.3243	18.0	13500	0.3466	0.8619
0.3747	19.0	14250	0.3420	0.8619
0.3494	20.0	15000	0.3382	0.8652
0.3628	21.0	15750	0.3347	0.8652
0.2681	22.0	16500	0.3313	0.8686
0.3103	23.0	17250	0.3283	0.8686
0.3029	24.0	18000	0.3255	0.8686
0.3439	25.0	18750	0.3228	0.8686
0.363	26.0	19500	0.3205	0.8735
0.3457	27.0	20250	0.3186	0.8735
0.3118	28.0	21000	0.3168	0.8719
0.3203	29.0	21750	0.3151	0.8719
0.2897	30.0	22500	0.3135	0.8702
0.3287	31.0	23250	0.3118	0.8702
0.3672	32.0	24000	0.3107	0.8719
0.3139	33.0	24750	0.3101	0.8702
0.3173	34.0	25500	0.3088	0.8719
0.3321	35.0	26250	0.3079	0.8735
0.3146	36.0	27000	0.3071	0.8735
0.3221	37.0	27750	0.3062	0.8735
0.2973	38.0	28500	0.3058	0.8752
0.275	39.0	29250	0.3050	0.8752
0.3603	40.0	30000	0.3045	0.8752
0.3249	41.0	30750	0.3040	0.8752
0.3107	42.0	31500	0.3036	0.8752
0.2783	43.0	32250	0.3032	0.8752
0.2901	44.0	33000	0.3029	0.8752
0.3257	45.0	33750	0.3026	0.8752
0.2732	46.0	34500	0.3025	0.8752
0.3622	47.0	35250	0.3024	0.8769
0.3082	48.0	36000	0.3023	0.8769
0.2937	49.0	36750	0.3022	0.8769
0.3097	50.0	37500	0.3022	0.8769

Framework versions

Transformers 4.32.1
Pytorch 2.1.0+cu121
Datasets 2.12.0
Tokenizers 0.13.2