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_1x_deit_base_rms_00001_fold2
    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: 0.6222222222222222

hushem_1x_deit_base_rms_00001_fold2

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: 1.4108
• Accuracy: 0.6222

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	1.2784	0.4444
1.1219	2.0	12	1.1574	0.5556
1.1219	3.0	18	1.2284	0.5778
0.3394	4.0	24	1.2205	0.6
0.0715	5.0	30	1.2716	0.6
0.0715	6.0	36	1.1061	0.6
0.0131	7.0	42	1.2084	0.6
0.0131	8.0	48	1.1858	0.6
0.0058	9.0	54	1.2180	0.6
0.0043	10.0	60	1.2510	0.6
0.0043	11.0	66	1.2572	0.5778
0.0032	12.0	72	1.2592	0.6
0.0032	13.0	78	1.2755	0.6
0.0024	14.0	84	1.2967	0.6
0.002	15.0	90	1.2920	0.6
0.002	16.0	96	1.3006	0.6
0.0018	17.0	102	1.3094	0.6
0.0018	18.0	108	1.3282	0.6222
0.0016	19.0	114	1.3327	0.6
0.0014	20.0	120	1.3425	0.6222
0.0014	21.0	126	1.3444	0.6222
0.0013	22.0	132	1.3522	0.6222
0.0013	23.0	138	1.3622	0.6222
0.0012	24.0	144	1.3662	0.6222
0.0011	25.0	150	1.3745	0.6222
0.0011	26.0	156	1.3791	0.6222
0.001	27.0	162	1.3827	0.6222
0.001	28.0	168	1.3833	0.6222
0.0009	29.0	174	1.3854	0.6222
0.0009	30.0	180	1.3905	0.6222
0.0009	31.0	186	1.3939	0.6222
0.0008	32.0	192	1.3979	0.6222
0.0008	33.0	198	1.3983	0.6222
0.0008	34.0	204	1.3992	0.6222
0.0008	35.0	210	1.3992	0.6222
0.0008	36.0	216	1.4025	0.6222
0.0008	37.0	222	1.4059	0.6222
0.0008	38.0	228	1.4089	0.6222
0.0007	39.0	234	1.4096	0.6222
0.0008	40.0	240	1.4105	0.6222
0.0008	41.0	246	1.4108	0.6222
0.0007	42.0	252	1.4108	0.6222
0.0007	43.0	258	1.4108	0.6222
0.0007	44.0	264	1.4108	0.6222
0.0007	45.0	270	1.4108	0.6222
0.0007	46.0	276	1.4108	0.6222
0.0007	47.0	282	1.4108	0.6222
0.0007	48.0	288	1.4108	0.6222
0.0007	49.0	294	1.4108	0.6222
0.0007	50.0	300	1.4108	0.6222

Framework versions

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