metadata

license: apache-2.0
base_model: facebook/deit-tiny-patch16-224
tags:
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - accuracy
model-index:
  - name: smids_1x_deit_tiny_sgd_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: 0.657762938230384

smids_1x_deit_tiny_sgd_0001_fold1

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

Loss: 0.8020
Accuracy: 0.6578

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
1.277	1.0	76	1.2939	0.2771
1.2116	2.0	152	1.2225	0.3172
1.1682	3.0	228	1.1693	0.3740
1.1189	4.0	304	1.1270	0.4073
1.0545	5.0	380	1.0950	0.4240
1.0649	6.0	456	1.0693	0.4574
1.0629	7.0	532	1.0475	0.4858
1.0345	8.0	608	1.0290	0.5142
1.012	9.0	684	1.0130	0.5392
0.9959	10.0	760	0.9988	0.5526
0.9617	11.0	836	0.9857	0.5626
1.0119	12.0	912	0.9733	0.5710
0.951	13.0	988	0.9618	0.5810
0.8944	14.0	1064	0.9511	0.5876
0.9729	15.0	1140	0.9409	0.5910
0.9626	16.0	1216	0.9311	0.5927
0.9103	17.0	1292	0.9219	0.6043
0.9088	18.0	1368	0.9131	0.6144
0.9045	19.0	1444	0.9046	0.6160
0.9231	20.0	1520	0.8968	0.6160
0.9054	21.0	1596	0.8893	0.6177
0.854	22.0	1672	0.8821	0.6227
0.8305	23.0	1748	0.8753	0.6294
0.8621	24.0	1824	0.8689	0.6311
0.8299	25.0	1900	0.8629	0.6327
0.8471	26.0	1976	0.8573	0.6344
0.817	27.0	2052	0.8521	0.6344
0.792	28.0	2128	0.8472	0.6361
0.8136	29.0	2204	0.8426	0.6377
0.7461	30.0	2280	0.8383	0.6411
0.8135	31.0	2356	0.8343	0.6427
0.7863	32.0	2432	0.8305	0.6461
0.7659	33.0	2508	0.8271	0.6494
0.8238	34.0	2584	0.8240	0.6528
0.8196	35.0	2660	0.8211	0.6528
0.7577	36.0	2736	0.8184	0.6528
0.8136	37.0	2812	0.8159	0.6528
0.7544	38.0	2888	0.8137	0.6561
0.7769	39.0	2964	0.8116	0.6561
0.8539	40.0	3040	0.8098	0.6561
0.7796	41.0	3116	0.8081	0.6544
0.765	42.0	3192	0.8067	0.6578
0.7732	43.0	3268	0.8054	0.6578
0.7585	44.0	3344	0.8044	0.6561
0.7325	45.0	3420	0.8036	0.6561
0.7699	46.0	3496	0.8029	0.6578
0.7818	47.0	3572	0.8024	0.6578
0.7946	48.0	3648	0.8021	0.6578
0.7345	49.0	3724	0.8020	0.6578
0.833	50.0	3800	0.8020	0.6578

Framework versions

Transformers 4.35.2
Pytorch 2.1.0+cu118
Datasets 2.15.0
Tokenizers 0.15.0