metadata

license: apache-2.0
tags:
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - accuracy
model-index:
  - name: vit-base-patch16-224-Trial007-YEL_STEM2
    results:
      - task:
          name: Image Classification
          type: image-classification
        dataset:
          name: imagefolder
          type: imagefolder
          config: default
          split: train
          args: default
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.9814814814814815

vit-base-patch16-224-Trial007-YEL_STEM2

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

Loss: 0.1172
Accuracy: 0.9815

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: 5e-05
train_batch_size: 60
eval_batch_size: 60
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 240
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
0.6676	0.89	2	0.6180	0.7222
0.5805	1.78	4	0.5004	0.7593
0.5012	2.67	6	0.3783	0.9630
0.2794	4.0	9	0.2285	0.9630
0.2695	4.89	11	0.2551	0.8889
0.2782	5.78	13	0.1079	0.9630
0.2131	6.67	15	0.1205	0.9630
0.1537	8.0	18	0.1861	0.9630
0.1739	8.89	20	0.1172	0.9815
0.1059	9.78	22	0.1092	0.9815
0.146	10.67	24	0.1072	0.9815
0.088	12.0	27	0.1015	0.9815
0.1304	12.89	29	0.1151	0.9815
0.0924	13.78	31	0.1313	0.9815
0.091	14.67	33	0.1178	0.9815
0.0508	16.0	36	0.0971	0.9815
0.1004	16.89	38	0.1175	0.9815
0.1097	17.78	40	0.1423	0.9630
0.0758	18.67	42	0.1597	0.9630
0.0687	20.0	45	0.1205	0.9815
0.0513	20.89	47	0.1107	0.9815
0.0755	21.78	49	0.1150	0.9815
0.0897	22.67	51	0.1332	0.9630
0.0439	24.0	54	0.1263	0.9815
0.0607	24.89	56	0.1111	0.9815
0.0719	25.78	58	0.1004	0.9815
0.0599	26.67	60	0.1064	0.9815
0.0613	28.0	63	0.1355	0.9815
0.0689	28.89	65	0.1444	0.9815
0.0754	29.78	67	0.1398	0.9815
0.0835	30.67	69	0.1345	0.9815
0.0801	32.0	72	0.1348	0.9815
0.0701	32.89	74	0.1365	0.9815
0.0647	33.78	76	0.1348	0.9815
0.0982	34.67	78	0.1346	0.9815
0.0671	36.0	81	0.1378	0.9815
0.054	36.89	83	0.1371	0.9815
0.0735	37.78	85	0.1355	0.9815
0.0736	38.67	87	0.1349	0.9815
0.0287	40.0	90	0.1329	0.9815
0.0539	40.89	92	0.1322	0.9815
0.0483	41.78	94	0.1324	0.9815
0.083	42.67	96	0.1319	0.9815
0.0558	44.0	99	0.1319	0.9815
0.0752	44.44	100	0.1319	0.9815

Framework versions

Transformers 4.30.0.dev0
Pytorch 1.12.1
Datasets 2.12.0
Tokenizers 0.13.1