metadata

license: apache-2.0
base_model: facebook/deit-small-patch16-224
tags:
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - accuracy
model-index:
  - name: smids_3x_deit_small_rms_001_fold3
    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: 0.715

smids_3x_deit_small_rms_001_fold3

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

Loss: 0.6470
Accuracy: 0.715

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: 0.001
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
1.1298	1.0	225	1.0984	0.34
1.1021	2.0	450	1.0452	0.4267
0.8891	3.0	675	0.8675	0.52
0.8324	4.0	900	0.9012	0.57
0.8729	5.0	1125	0.9895	0.4433
0.8594	6.0	1350	0.8010	0.605
1.2058	7.0	1575	0.8492	0.5583
0.8886	8.0	1800	0.8315	0.6067
0.825	9.0	2025	0.7910	0.6167
0.82	10.0	2250	0.8740	0.545
0.8151	11.0	2475	0.8350	0.54
0.8595	12.0	2700	0.8022	0.5917
0.7431	13.0	2925	0.7832	0.6233
0.7711	14.0	3150	0.8235	0.6017
0.743	15.0	3375	0.7910	0.6083
0.7919	16.0	3600	0.7423	0.645
0.7646	17.0	3825	0.7716	0.645
0.7563	18.0	4050	0.7602	0.6017
0.7776	19.0	4275	0.7391	0.6517
0.679	20.0	4500	0.9075	0.585
0.7215	21.0	4725	0.8407	0.5817
0.697	22.0	4950	0.7647	0.6367
0.6799	23.0	5175	0.7300	0.65
0.6618	24.0	5400	0.7249	0.6533
0.7275	25.0	5625	0.6970	0.6783
0.6922	26.0	5850	0.7048	0.66
0.6032	27.0	6075	0.7956	0.6433
0.6867	28.0	6300	0.7208	0.6633
0.7286	29.0	6525	0.7360	0.6533
0.5865	30.0	6750	0.7249	0.6833
0.6196	31.0	6975	0.7133	0.6933
0.6323	32.0	7200	0.7099	0.6617
0.6683	33.0	7425	0.6777	0.6967
0.6008	34.0	7650	0.7425	0.6517
0.6135	35.0	7875	0.6674	0.6967
0.6008	36.0	8100	0.6639	0.7033
0.6752	37.0	8325	0.6658	0.6867
0.5964	38.0	8550	0.6380	0.7067
0.57	39.0	8775	0.6573	0.7033
0.5546	40.0	9000	0.6537	0.71
0.556	41.0	9225	0.6444	0.72
0.5972	42.0	9450	0.6277	0.7217
0.4929	43.0	9675	0.6416	0.7217
0.5311	44.0	9900	0.6558	0.72
0.5177	45.0	10125	0.6499	0.7183
0.5402	46.0	10350	0.6436	0.7283
0.5836	47.0	10575	0.6389	0.7133
0.531	48.0	10800	0.6442	0.7133
0.5194	49.0	11025	0.6460	0.7117
0.5631	50.0	11250	0.6470	0.715

Framework versions

Transformers 4.32.1
Pytorch 2.1.0+cu121
Datasets 2.12.0
Tokenizers 0.13.2