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_rms_0001_fold1
    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: 0.35555555555555557

hushem_5x_beit_base_rms_0001_fold1

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: 3.6811
Accuracy: 0.3556

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
1.4287	1.0	27	1.3926	0.2222
1.3907	2.0	54	1.3975	0.2667
1.358	3.0	81	1.5093	0.2444
1.3416	4.0	108	1.5118	0.2444
1.2056	5.0	135	1.4928	0.2444
1.1299	6.0	162	1.6562	0.2222
1.1641	7.0	189	1.5947	0.2444
1.1473	8.0	216	1.5964	0.2444
1.1298	9.0	243	1.7663	0.2444
1.1045	10.0	270	1.6309	0.3778
0.8985	11.0	297	1.6908	0.4
0.7744	12.0	324	1.3949	0.3556
0.7617	13.0	351	1.4646	0.3778
0.6843	14.0	378	1.5910	0.3778
0.6647	15.0	405	1.8050	0.4
0.6363	16.0	432	1.7016	0.3333
0.6362	17.0	459	1.8539	0.3778
0.6858	18.0	486	1.8678	0.3556
0.7039	19.0	513	1.5776	0.3556
0.6292	20.0	540	1.8552	0.3111
0.4567	21.0	567	1.7854	0.3556
0.5954	22.0	594	2.4822	0.3556
0.5737	23.0	621	2.0564	0.4
0.4941	24.0	648	1.9451	0.3111
0.523	25.0	675	2.0359	0.3778
0.5221	26.0	702	2.1184	0.4
0.4589	27.0	729	2.0471	0.3556
0.4473	28.0	756	2.5353	0.3556
0.4328	29.0	783	2.7479	0.3556
0.4259	30.0	810	2.2239	0.3778
0.3698	31.0	837	2.5363	0.3556
0.3577	32.0	864	2.5264	0.3556
0.3882	33.0	891	2.2649	0.3333
0.3526	34.0	918	2.6438	0.3556
0.2747	35.0	945	2.3584	0.3778
0.2842	36.0	972	2.8515	0.3556
0.2603	37.0	999	2.3416	0.3778
0.2268	38.0	1026	2.7485	0.3778
0.2	39.0	1053	3.3636	0.3333
0.2049	40.0	1080	3.1692	0.3333
0.1369	41.0	1107	3.3885	0.3556
0.1813	42.0	1134	3.3020	0.3333
0.1518	43.0	1161	2.8618	0.4
0.0986	44.0	1188	3.2902	0.3778
0.131	45.0	1215	3.3898	0.3333
0.0809	46.0	1242	3.5629	0.3333
0.048	47.0	1269	3.7516	0.3333
0.038	48.0	1296	3.6814	0.3556
0.0465	49.0	1323	3.6811	0.3556
0.0644	50.0	1350	3.6811	0.3556

Framework versions

Transformers 4.35.2
Pytorch 2.1.0+cu118
Datasets 2.15.0
Tokenizers 0.15.0