metadata

license: apache-2.0
base_model: facebook/deit-tiny-patch16-224
tags:
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - accuracy
model-index:
  - name: hushem_1x_deit_tiny_rms_00001_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: 0.8571428571428571

hushem_1x_deit_tiny_rms_00001_fold4

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

Loss: 0.4549
Accuracy: 0.8571

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	1.4075	0.2857
1.4145	2.0	12	1.3443	0.3571
1.4145	3.0	18	0.8612	0.6667
0.7818	4.0	24	0.9127	0.6190
0.3833	5.0	30	0.5998	0.8810
0.3833	6.0	36	0.5796	0.7857
0.1457	7.0	42	0.5756	0.8333
0.1457	8.0	48	0.5188	0.7857
0.0559	9.0	54	0.5146	0.8571
0.0198	10.0	60	0.5290	0.7857
0.0198	11.0	66	0.4513	0.8571
0.007	12.0	72	0.4696	0.8571
0.007	13.0	78	0.4668	0.8333
0.0039	14.0	84	0.4642	0.8333
0.0028	15.0	90	0.4519	0.8571
0.0028	16.0	96	0.4562	0.8333
0.0022	17.0	102	0.4543	0.8571
0.0022	18.0	108	0.4588	0.8571
0.0018	19.0	114	0.4546	0.8571
0.0016	20.0	120	0.4551	0.8333
0.0016	21.0	126	0.4570	0.8333
0.0013	22.0	132	0.4556	0.8333
0.0013	23.0	138	0.4547	0.8333
0.0012	24.0	144	0.4556	0.8571
0.0011	25.0	150	0.4547	0.8571
0.0011	26.0	156	0.4538	0.8571
0.001	27.0	162	0.4593	0.8333
0.001	28.0	168	0.4560	0.8333
0.0009	29.0	174	0.4555	0.8333
0.0009	30.0	180	0.4554	0.8333
0.0009	31.0	186	0.4563	0.8333
0.0008	32.0	192	0.4547	0.8571
0.0008	33.0	198	0.4545	0.8571
0.0008	34.0	204	0.4547	0.8571
0.0007	35.0	210	0.4541	0.8571
0.0007	36.0	216	0.4545	0.8571
0.0007	37.0	222	0.4550	0.8571
0.0007	38.0	228	0.4547	0.8571
0.0007	39.0	234	0.4549	0.8571
0.0007	40.0	240	0.4549	0.8571
0.0007	41.0	246	0.4549	0.8571
0.0007	42.0	252	0.4549	0.8571
0.0007	43.0	258	0.4549	0.8571
0.0007	44.0	264	0.4549	0.8571
0.0007	45.0	270	0.4549	0.8571
0.0007	46.0	276	0.4549	0.8571
0.0007	47.0	282	0.4549	0.8571
0.0007	48.0	288	0.4549	0.8571
0.0007	49.0	294	0.4549	0.8571
0.0007	50.0	300	0.4549	0.8571

Framework versions

Transformers 4.35.0
Pytorch 2.1.0+cu118
Datasets 2.14.6
Tokenizers 0.14.1