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_0001_fold4
    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: 0.9047619047619048

hushem_5x_deit_base_rms_0001_fold4

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: 0.5888
• Accuracy: 0.9048

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
1.6398	1.0	28	1.4620	0.2381
1.4471	2.0	56	1.4867	0.2619
1.4043	3.0	84	1.4639	0.2381
1.6225	4.0	112	1.1986	0.4524
1.0459	5.0	140	1.1310	0.4762
0.7275	6.0	168	0.7753	0.6429
0.4185	7.0	196	0.5503	0.7857
0.2249	8.0	224	0.5491	0.8571
0.0749	9.0	252	0.2650	0.9286
0.0643	10.0	280	0.5070	0.8333
0.083	11.0	308	0.5183	0.8810
0.0258	12.0	336	0.5166	0.8571
0.0004	13.0	364	0.4395	0.9524
0.03	14.0	392	0.5344	0.9048
0.0374	15.0	420	1.0859	0.8095
0.032	16.0	448	0.4372	0.9048
0.0018	17.0	476	0.4691	0.9048
0.0319	18.0	504	0.5620	0.8810
0.022	19.0	532	0.4782	0.9048
0.0002	20.0	560	0.4687	0.9048
0.0001	21.0	588	0.4749	0.9048
0.0001	22.0	616	0.4799	0.9048
0.0001	23.0	644	0.4865	0.9048
0.0001	24.0	672	0.4924	0.9048
0.0001	25.0	700	0.4977	0.9048
0.0001	26.0	728	0.5030	0.9048
0.0	27.0	756	0.5085	0.9048
0.0	28.0	784	0.5132	0.9048
0.0	29.0	812	0.5184	0.9048
0.0	30.0	840	0.5233	0.9048
0.0	31.0	868	0.5283	0.9048
0.0	32.0	896	0.5333	0.9048
0.0	33.0	924	0.5383	0.9048
0.0	34.0	952	0.5430	0.9048
0.0	35.0	980	0.5476	0.9048
0.0	36.0	1008	0.5522	0.9048
0.0	37.0	1036	0.5569	0.9048
0.0	38.0	1064	0.5613	0.9048
0.0	39.0	1092	0.5655	0.9048
0.0	40.0	1120	0.5694	0.9048
0.0	41.0	1148	0.5725	0.9048
0.0	42.0	1176	0.5761	0.9048
0.0	43.0	1204	0.5794	0.9048
0.0	44.0	1232	0.5824	0.9048
0.0	45.0	1260	0.5848	0.9048
0.0	46.0	1288	0.5868	0.9048
0.0	47.0	1316	0.5882	0.9048
0.0	48.0	1344	0.5888	0.9048
0.0	49.0	1372	0.5888	0.9048
0.0	50.0	1400	0.5888	0.9048

Framework versions

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