README.md

metadata

license: apache-2.0
base_model: facebook/deit-base-patch16-224
tags:
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - accuracy
model-index:
  - name: hushem_5x_deit_base_rms_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: 0.8837209302325582

hushem_5x_deit_base_rms_00001_fold3

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

• Loss: 0.6600
• Accuracy: 0.8837

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
0.7956	1.0	28	0.6205	0.7674
0.1411	2.0	56	0.3123	0.8837
0.014	3.0	84	0.3844	0.9070
0.0034	4.0	112	0.3408	0.8837
0.0022	5.0	140	0.4472	0.8605
0.0015	6.0	168	0.3917	0.8605
0.0011	7.0	196	0.3836	0.8837
0.0008	8.0	224	0.4047	0.8837
0.0006	9.0	252	0.4079	0.8605
0.0005	10.0	280	0.4138	0.8837
0.0004	11.0	308	0.4271	0.8837
0.0004	12.0	336	0.4048	0.8837
0.0003	13.0	364	0.4452	0.8837
0.0002	14.0	392	0.4491	0.8837
0.0002	15.0	420	0.4640	0.8837
0.0002	16.0	448	0.4755	0.8837
0.0002	17.0	476	0.4421	0.8837
0.0001	18.0	504	0.4868	0.8837
0.0001	19.0	532	0.5095	0.8837
0.0001	20.0	560	0.5094	0.8837
0.0001	21.0	588	0.5135	0.8837
0.0001	22.0	616	0.5162	0.8837
0.0001	23.0	644	0.5296	0.8837
0.0001	24.0	672	0.5403	0.8837
0.0001	25.0	700	0.5417	0.8837
0.0001	26.0	728	0.5505	0.8837
0.0	27.0	756	0.5557	0.8837
0.0	28.0	784	0.5868	0.8837
0.0	29.0	812	0.5803	0.8837
0.0	30.0	840	0.5730	0.8837
0.0	31.0	868	0.5921	0.8837
0.0	32.0	896	0.5971	0.8837
0.0	33.0	924	0.5949	0.8837
0.0	34.0	952	0.6083	0.8837
0.0	35.0	980	0.5834	0.8837
0.0	36.0	1008	0.6025	0.8605
0.0	37.0	1036	0.6316	0.8837
0.0	38.0	1064	0.6619	0.8837
0.0	39.0	1092	0.6540	0.8837
0.0	40.0	1120	0.6507	0.8837
0.0	41.0	1148	0.6507	0.8837
0.0	42.0	1176	0.6547	0.8837
0.0	43.0	1204	0.6523	0.8837
0.0	44.0	1232	0.6524	0.8837
0.0	45.0	1260	0.6538	0.8837
0.0	46.0	1288	0.6554	0.8837
0.0	47.0	1316	0.6605	0.8837
0.0	48.0	1344	0.6600	0.8837
0.0	49.0	1372	0.6600	0.8837
0.0	50.0	1400	0.6600	0.8837

Framework versions

• Transformers 4.35.2
• Pytorch 2.1.0+cu118
• Datasets 2.15.0
• Tokenizers 0.15.0