metadata

license: apache-2.0
base_model: facebook/deit-base-patch16-224
tags:
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - accuracy
model-index:
  - name: hushem_1x_deit_base_adamax_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: 0.6

hushem_1x_deit_base_adamax_00001_fold1

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: 1.0627
Accuracy: 0.6

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
No log	1.0	6	1.3659	0.3111
1.3159	2.0	12	1.3205	0.3556
1.3159	3.0	18	1.2809	0.4667
1.085	4.0	24	1.2473	0.4222
0.9044	5.0	30	1.2084	0.4444
0.9044	6.0	36	1.1791	0.4667
0.7189	7.0	42	1.1564	0.4889
0.7189	8.0	48	1.1293	0.5333
0.581	9.0	54	1.1065	0.5333
0.4841	10.0	60	1.0861	0.5111
0.4841	11.0	66	1.0742	0.4889
0.3956	12.0	72	1.0532	0.5333
0.3956	13.0	78	1.0465	0.5333
0.3295	14.0	84	1.0354	0.5556
0.2581	15.0	90	1.0353	0.5333
0.2581	16.0	96	1.0286	0.5111
0.2137	17.0	102	1.0149	0.5333
0.2137	18.0	108	1.0065	0.6
0.1577	19.0	114	1.0262	0.5556
0.1394	20.0	120	1.0304	0.5556
0.1394	21.0	126	1.0253	0.5556
0.1165	22.0	132	1.0218	0.6
0.1165	23.0	138	1.0233	0.6
0.0915	24.0	144	1.0232	0.6
0.0772	25.0	150	1.0205	0.6
0.0772	26.0	156	1.0346	0.6
0.0656	27.0	162	1.0276	0.6
0.0656	28.0	168	1.0281	0.6
0.0525	29.0	174	1.0381	0.6
0.0442	30.0	180	1.0380	0.6
0.0442	31.0	186	1.0415	0.6
0.0405	32.0	192	1.0435	0.6
0.0405	33.0	198	1.0498	0.6
0.0407	34.0	204	1.0508	0.6
0.0336	35.0	210	1.0488	0.6
0.0336	36.0	216	1.0496	0.6
0.0325	37.0	222	1.0547	0.6
0.0325	38.0	228	1.0616	0.6
0.0286	39.0	234	1.0647	0.6
0.0307	40.0	240	1.0644	0.6
0.0307	41.0	246	1.0630	0.6
0.0285	42.0	252	1.0627	0.6
0.0285	43.0	258	1.0627	0.6
0.0286	44.0	264	1.0627	0.6
0.0294	45.0	270	1.0627	0.6
0.0294	46.0	276	1.0627	0.6
0.0294	47.0	282	1.0627	0.6
0.0294	48.0	288	1.0627	0.6
0.0276	49.0	294	1.0627	0.6
0.0301	50.0	300	1.0627	0.6

Framework versions

Transformers 4.35.2
Pytorch 2.1.0+cu118
Datasets 2.14.7
Tokenizers 0.15.0