metadata

license: apache-2.0
base_model: facebook/deit-small-patch16-224
tags:
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - accuracy
model-index:
  - name: hushem_5x_deit_small_adamax_00001_fold3
    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: 0.9069767441860465

hushem_5x_deit_small_adamax_00001_fold3

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

Loss: 0.4351
Accuracy: 0.9070

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: 1e-05
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
1.3047	1.0	28	1.2727	0.3023
0.9947	2.0	56	1.1088	0.5116
0.6975	3.0	84	1.0336	0.5814
0.5355	4.0	112	0.9195	0.6047
0.3827	5.0	140	0.8325	0.6279
0.3	6.0	168	0.7235	0.7674
0.2132	7.0	196	0.6638	0.7209
0.1664	8.0	224	0.5923	0.7674
0.1004	9.0	252	0.5516	0.7674
0.0697	10.0	280	0.5067	0.7907
0.0474	11.0	308	0.5078	0.7674
0.0278	12.0	336	0.5312	0.7907
0.0177	13.0	364	0.4466	0.8372
0.0105	14.0	392	0.4059	0.8837
0.0066	15.0	420	0.4235	0.8372
0.005	16.0	448	0.4260	0.8372
0.0043	17.0	476	0.4042	0.8605
0.0033	18.0	504	0.4280	0.8605
0.003	19.0	532	0.4100	0.8837
0.0024	20.0	560	0.4096	0.9070
0.0023	21.0	588	0.4113	0.9070
0.002	22.0	616	0.4075	0.9070
0.0019	23.0	644	0.4099	0.9070
0.0015	24.0	672	0.4158	0.9070
0.0014	25.0	700	0.4120	0.9070
0.0015	26.0	728	0.4156	0.9070
0.0013	27.0	756	0.4154	0.9070
0.0013	28.0	784	0.4244	0.9070
0.0012	29.0	812	0.4172	0.9070
0.0012	30.0	840	0.4177	0.9070
0.0011	31.0	868	0.4272	0.9070
0.0011	32.0	896	0.4248	0.9070
0.001	33.0	924	0.4242	0.9070
0.001	34.0	952	0.4262	0.9070
0.0012	35.0	980	0.4213	0.9070
0.0009	36.0	1008	0.4193	0.9302
0.0009	37.0	1036	0.4299	0.9302
0.0008	38.0	1064	0.4330	0.9070
0.0008	39.0	1092	0.4363	0.9070
0.0009	40.0	1120	0.4311	0.9070
0.0008	41.0	1148	0.4367	0.9070
0.0008	42.0	1176	0.4356	0.9070
0.0008	43.0	1204	0.4345	0.9070
0.0008	44.0	1232	0.4348	0.9070
0.0007	45.0	1260	0.4351	0.9070
0.0007	46.0	1288	0.4351	0.9070
0.0007	47.0	1316	0.4349	0.9070
0.0007	48.0	1344	0.4351	0.9070
0.0007	49.0	1372	0.4351	0.9070
0.0007	50.0	1400	0.4351	0.9070

Framework versions

Transformers 4.35.2
Pytorch 2.1.0+cu118
Datasets 2.15.0
Tokenizers 0.15.0