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: hushem_5x_deit_small_rms_0001_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: 0.9302325581395349

hushem_5x_deit_small_rms_0001_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: 0.6867
• Accuracy: 0.9302

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
0.8625	1.0	28	0.7655	0.7442
0.213	2.0	56	0.3346	0.9070
0.0427	3.0	84	0.3169	0.8837
0.0088	4.0	112	0.2583	0.9070
0.0019	5.0	140	0.3591	0.9070
0.0013	6.0	168	0.3828	0.8837
0.0008	7.0	196	0.3548	0.9070
0.0007	8.0	224	0.3758	0.9302
0.0005	9.0	252	0.4221	0.9070
0.0004	10.0	280	0.4042	0.9302
0.0004	11.0	308	0.4067	0.9302
0.0003	12.0	336	0.4099	0.9302
0.0002	13.0	364	0.4211	0.9302
0.0002	14.0	392	0.4323	0.9302
0.0002	15.0	420	0.4463	0.9302
0.0002	16.0	448	0.4550	0.9302
0.0001	17.0	476	0.4114	0.9302
0.0001	18.0	504	0.4747	0.9302
0.0001	19.0	532	0.4880	0.9302
0.0001	20.0	560	0.4798	0.9302
0.0001	21.0	588	0.5078	0.9302
0.0001	22.0	616	0.5161	0.9302
0.0001	23.0	644	0.5322	0.9302
0.0001	24.0	672	0.5391	0.9302
0.0	25.0	700	0.5387	0.9302
0.0	26.0	728	0.5518	0.9302
0.0	27.0	756	0.5912	0.9302
0.0	28.0	784	0.5723	0.9302
0.0	29.0	812	0.5780	0.9302
0.0	30.0	840	0.5909	0.9302
0.0	31.0	868	0.5963	0.9302
0.0	32.0	896	0.6068	0.9302
0.0	33.0	924	0.6067	0.9302
0.0	34.0	952	0.6107	0.9302
0.0	35.0	980	0.5868	0.9302
0.0	36.0	1008	0.6292	0.9302
0.0	37.0	1036	0.6428	0.9302
0.0	38.0	1064	0.6729	0.9070
0.0	39.0	1092	0.6601	0.9302
0.0	40.0	1120	0.6776	0.9070
0.0	41.0	1148	0.6683	0.9302
0.0	42.0	1176	0.6712	0.9302
0.0	43.0	1204	0.6721	0.9302
0.0	44.0	1232	0.6819	0.9302
0.0	45.0	1260	0.6829	0.9302
0.0	46.0	1288	0.6827	0.9302
0.0	47.0	1316	0.6864	0.9302
0.0	48.0	1344	0.6865	0.9302
0.0	49.0	1372	0.6867	0.9302
0.0	50.0	1400	0.6867	0.9302

Framework versions

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