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_lr00001_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: 0.6666666666666666

hushem_1x_deit_tiny_rms_lr00001_fold1

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: 1.0041
Accuracy: 0.6667

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
gradient_accumulation_steps: 4
total_train_batch_size: 128
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	0.67	1	1.7459	0.2667
No log	2.0	3	1.4578	0.3111
No log	2.67	4	1.4179	0.3333
No log	4.0	6	1.3720	0.3333
No log	4.67	7	1.2817	0.3778
No log	6.0	9	1.2475	0.5333
1.1452	6.67	10	1.3553	0.3556
1.1452	8.0	12	1.2165	0.4222
1.1452	8.67	13	1.1259	0.5778
1.1452	10.0	15	1.1917	0.4667
1.1452	10.67	16	1.0971	0.5111
1.1452	12.0	18	1.0749	0.5111
1.1452	12.67	19	1.0701	0.4889
0.4031	14.0	21	1.0259	0.5333
0.4031	14.67	22	1.2004	0.4222
0.4031	16.0	24	1.0966	0.4667
0.4031	16.67	25	0.9736	0.5333
0.4031	18.0	27	1.0248	0.5556
0.4031	18.67	28	0.9806	0.6222
0.1191	20.0	30	0.9437	0.6222
0.1191	20.67	31	1.0574	0.5778
0.1191	22.0	33	1.0173	0.6
0.1191	22.67	34	0.9322	0.6222
0.1191	24.0	36	0.9638	0.6222
0.1191	24.67	37	1.0436	0.6
0.1191	26.0	39	1.0020	0.6222
0.0416	26.67	40	0.9820	0.6
0.0416	28.0	42	0.9872	0.6222
0.0416	28.67	43	1.0109	0.6222
0.0416	30.0	45	0.9982	0.6444
0.0416	30.67	46	0.9968	0.6222
0.0416	32.0	48	1.0043	0.6667
0.0416	32.67	49	1.0074	0.6667
0.0206	33.33	50	1.0041	0.6667

Framework versions

Transformers 4.35.0
Pytorch 2.1.0+cu118
Datasets 2.14.6
Tokenizers 0.14.1