metadata

license: apache-2.0
base_model: google/vit-base-patch16-224
tags:
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - accuracy
model-index:
  - name: vit-base-patch16-224-ve-Ub
    results:
      - task:
          name: Image Classification
          type: image-classification
        dataset:
          name: imagefolder
          type: imagefolder
          config: default
          split: validation
          args: default
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.7254901960784313

vit-base-patch16-224-ve-Ub

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: 0.8470
Accuracy: 0.7255

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: 32
eval_batch_size: 32
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 128
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.1
num_epochs: 80

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	0.57	1	1.3863	0.0980
No log	1.71	3	1.3813	0.4706
No log	2.86	5	1.3686	0.4706
No log	4.0	7	1.3480	0.4706
No log	4.57	8	1.3345	0.4706
1.3658	5.71	10	1.3040	0.4706
1.3658	6.86	12	1.2754	0.4706
1.3658	8.0	14	1.2477	0.4902
1.3658	8.57	15	1.2347	0.5294
1.3658	9.71	17	1.2109	0.5490
1.3658	10.86	19	1.1889	0.6078
1.2512	12.0	21	1.1671	0.6275
1.2512	12.57	22	1.1560	0.6078
1.2512	13.71	24	1.1311	0.6471
1.2512	14.86	26	1.1128	0.6275
1.2512	16.0	28	1.0874	0.6667
1.2512	16.57	29	1.0828	0.6863
1.1299	17.71	31	1.0586	0.6667
1.1299	18.86	33	1.0362	0.6667
1.1299	20.0	35	1.0173	0.6863
1.1299	20.57	36	1.0065	0.6667
1.1299	21.71	38	1.0070	0.6471
1.0212	22.86	40	0.9792	0.6667
1.0212	24.0	42	0.9612	0.6667
1.0212	24.57	43	0.9584	0.6471
1.0212	25.71	45	0.9494	0.6667
1.0212	26.86	47	0.9294	0.6667
1.0212	28.0	49	0.9196	0.6667
0.9222	28.57	50	0.9100	0.7059
0.9222	29.71	52	0.9061	0.6863
0.9222	30.86	54	0.8904	0.7059
0.9222	32.0	56	0.8797	0.7059
0.9222	32.57	57	0.8747	0.6863
0.9222	33.71	59	0.8691	0.6863
0.8419	34.86	61	0.8550	0.7059
0.8419	36.0	63	0.8470	0.7255
0.8419	36.57	64	0.8430	0.7255
0.8419	37.71	66	0.8389	0.7059
0.8419	38.86	68	0.8298	0.7255
0.7865	40.0	70	0.8270	0.7255
0.7865	40.57	71	0.8258	0.7255
0.7865	41.71	73	0.8235	0.7059
0.7865	42.86	75	0.8211	0.7059
0.7865	44.0	77	0.8189	0.7059
0.7865	44.57	78	0.8189	0.7059
0.7555	45.71	80	0.8187	0.7059

Framework versions

Transformers 4.36.2
Pytorch 2.1.2+cu118
Datasets 2.16.1
Tokenizers 0.15.0