README.md

metadata

license: apache-2.0
base_model: facebook/deit-small-patch16-224
tags:
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - accuracy
model-index:
  - name: smids_5x_deit_small_rms_00001_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: 0.9232053422370617

smids_5x_deit_small_rms_00001_fold1

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: 0.7417
• Accuracy: 0.9232

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
0.2432	1.0	376	0.2964	0.8731
0.1614	2.0	752	0.2849	0.8932
0.1382	3.0	1128	0.2988	0.9048
0.0674	4.0	1504	0.3782	0.9082
0.0238	5.0	1880	0.4767	0.9132
0.0038	6.0	2256	0.4683	0.9215
0.0081	7.0	2632	0.5149	0.9015
0.0311	8.0	3008	0.6215	0.9082
0.0258	9.0	3384	0.6420	0.9015
0.0003	10.0	3760	0.7389	0.8982
0.0016	11.0	4136	0.7097	0.9032
0.0237	12.0	4512	0.7322	0.8965
0.0	13.0	4888	0.6330	0.9065
0.0121	14.0	5264	0.6713	0.8998
0.0128	15.0	5640	0.6959	0.9032
0.0	16.0	6016	0.5921	0.9165
0.0147	17.0	6392	0.7286	0.9032
0.0096	18.0	6768	0.6654	0.9115
0.0001	19.0	7144	0.7241	0.9065
0.026	20.0	7520	0.7595	0.9115
0.0004	21.0	7896	0.7089	0.9132
0.0001	22.0	8272	0.7020	0.9132
0.0189	23.0	8648	0.7064	0.9032
0.0	24.0	9024	0.6953	0.9182
0.0008	25.0	9400	0.6754	0.9048
0.0029	26.0	9776	0.6682	0.9149
0.0039	27.0	10152	0.7036	0.9115
0.0	28.0	10528	0.7901	0.9098
0.0047	29.0	10904	0.7958	0.9165
0.0042	30.0	11280	0.7246	0.9115
0.0	31.0	11656	0.7694	0.9132
0.0	32.0	12032	0.7581	0.9082
0.0	33.0	12408	0.7146	0.9149
0.0	34.0	12784	0.7034	0.9165
0.0	35.0	13160	0.7688	0.9115
0.0	36.0	13536	0.7638	0.9132
0.0	37.0	13912	0.8028	0.9115
0.0	38.0	14288	0.7323	0.9215
0.0	39.0	14664	0.7555	0.9199
0.0	40.0	15040	0.7506	0.9215
0.0	41.0	15416	0.7416	0.9215
0.0	42.0	15792	0.7376	0.9199
0.0	43.0	16168	0.7280	0.9215
0.0	44.0	16544	0.7390	0.9215
0.0	45.0	16920	0.7365	0.9232
0.0028	46.0	17296	0.7367	0.9232
0.0	47.0	17672	0.7395	0.9232
0.0	48.0	18048	0.7408	0.9232
0.0	49.0	18424	0.7418	0.9232
0.0024	50.0	18800	0.7417	0.9232

Framework versions

• Transformers 4.32.1
• Pytorch 2.1.0+cu121
• Datasets 2.12.0
• Tokenizers 0.13.2