metadata

license: apache-2.0
tags:
  - generated_from_trainer
metrics:
  - accuracy
  - precision
  - recall
  - f1
base_model: google/vit-base-patch16-224-in21k
model-index:
  - name: ViT_Flower102_2
    results: []

ViT_Flower102_2

This model is a fine-tuned version of google/vit-base-patch16-224-in21k on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.1502
Accuracy: 0.9755
Precision: 0.9755
Recall: 0.9755
F1: 0.9755

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: 0.0002
train_batch_size: 16
eval_batch_size: 8
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision	Recall	F1
0.053	0.22	100	0.3198	0.9235	0.9235	0.9235	0.9235
0.1225	0.45	200	0.4087	0.9167	0.9167	0.9167	0.9167
0.1985	0.67	300	0.2068	0.9569	0.9569	0.9569	0.9569
0.0804	0.89	400	0.3181	0.9333	0.9333	0.9333	0.9333
0.1672	1.11	500	0.3582	0.9275	0.9275	0.9275	0.9275
0.1287	1.34	600	0.2700	0.9451	0.9451	0.9451	0.9451
0.0147	1.56	700	0.3691	0.9206	0.9206	0.9206	0.9206
0.0416	1.78	800	0.2535	0.9471	0.9471	0.9471	0.9471
0.0211	2.0	900	0.2575	0.9471	0.9471	0.9471	0.9471
0.088	2.23	1000	0.1908	0.9529	0.9529	0.9529	0.9529
0.1849	2.45	1100	0.2201	0.9529	0.9529	0.9529	0.9529
0.0009	2.67	1200	0.2229	0.9549	0.9549	0.9549	0.9549
0.0599	2.9	1300	0.1781	0.9608	0.9608	0.9608	0.9608
0.0004	3.12	1400	0.1751	0.9667	0.9667	0.9667	0.9667
0.0004	3.34	1500	0.1684	0.9686	0.9686	0.9686	0.9686
0.0352	3.56	1600	0.1502	0.9755	0.9755	0.9755	0.9755
0.0003	3.79	1700	0.1597	0.9745	0.9745	0.9745	0.9745
0.0003	4.01	1800	0.2573	0.9559	0.9559	0.9559	0.9559
0.0005	4.23	1900	0.1907	0.9667	0.9667	0.9667	0.9667
0.0741	4.45	2000	0.2038	0.9637	0.9637	0.9637	0.9637
0.0025	4.68	2100	0.1929	0.9647	0.9647	0.9647	0.9647
0.0293	4.9	2200	0.1740	0.9608	0.9608	0.9608	0.9608
0.0003	5.12	2300	0.2598	0.9569	0.9569	0.9569	0.9569
0.0037	5.35	2400	0.1772	0.9618	0.9618	0.9618	0.9618
0.0213	5.57	2500	0.2911	0.9520	0.9520	0.9520	0.9520
0.027	5.79	2600	0.2540	0.9520	0.9520	0.9520	0.9520
0.0155	6.01	2700	0.2252	0.9549	0.9549	0.9549	0.9549
0.0002	6.24	2800	0.3040	0.9431	0.9431	0.9431	0.9431
0.011	6.46	2900	0.1923	0.9598	0.9598	0.9598	0.9598
0.0006	6.68	3000	0.2089	0.9637	0.9637	0.9637	0.9637
0.0002	6.9	3100	0.2206	0.9578	0.9578	0.9578	0.9578
0.0006	7.13	3200	0.2267	0.9627	0.9627	0.9627	0.9627
0.0001	7.35	3300	0.1735	0.9637	0.9637	0.9637	0.9637
0.0001	7.57	3400	0.1611	0.9686	0.9686	0.9686	0.9686
0.0003	7.8	3500	0.1584	0.9676	0.9676	0.9676	0.9676
0.0001	8.02	3600	0.1591	0.9716	0.9716	0.9716	0.9716
0.0005	8.24	3700	0.1596	0.9706	0.9706	0.9706	0.9706
0.0002	8.46	3800	0.1563	0.9716	0.9716	0.9716	0.9716
0.0002	8.69	3900	0.1550	0.9716	0.9716	0.9716	0.9716
0.0001	8.91	4000	0.1542	0.9706	0.9706	0.9706	0.9706
0.0001	9.13	4100	0.1538	0.9716	0.9716	0.9716	0.9716
0.0001	9.35	4200	0.1536	0.9716	0.9716	0.9716	0.9716
0.0001	9.58	4300	0.1534	0.9716	0.9716	0.9716	0.9716
0.0001	9.8	4400	0.1533	0.9716	0.9716	0.9716	0.9716

Framework versions

Transformers 4.39.3
Pytorch 2.2.1+cu121
Datasets 2.18.0
Tokenizers 0.15.2