metadata

license: apache-2.0
base_model: facebook/deit-small-patch16-224
tags:
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - accuracy
model-index:
  - name: smids_10x_deit_small_sgd_001_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: 0.8685524126455907

smids_10x_deit_small_sgd_001_fold2

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: 0.3138
Accuracy: 0.8686

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
0.5167	1.0	750	0.5666	0.7737
0.3469	2.0	1500	0.4420	0.8136
0.3157	3.0	2250	0.3924	0.8336
0.3366	4.0	3000	0.3644	0.8469
0.2937	5.0	3750	0.3504	0.8569
0.2683	6.0	4500	0.3342	0.8602
0.2786	7.0	5250	0.3236	0.8636
0.2458	8.0	6000	0.3168	0.8619
0.2409	9.0	6750	0.3122	0.8586
0.2266	10.0	7500	0.3079	0.8652
0.2724	11.0	8250	0.3033	0.8586
0.2793	12.0	9000	0.3021	0.8586
0.2082	13.0	9750	0.3016	0.8619
0.152	14.0	10500	0.3001	0.8669
0.1732	15.0	11250	0.2977	0.8636
0.1629	16.0	12000	0.2993	0.8636
0.1493	17.0	12750	0.2962	0.8669
0.1762	18.0	13500	0.2975	0.8669
0.1954	19.0	14250	0.2989	0.8735
0.1979	20.0	15000	0.2956	0.8636
0.1452	21.0	15750	0.2997	0.8636
0.1414	22.0	16500	0.2986	0.8636
0.131	23.0	17250	0.2989	0.8652
0.1633	24.0	18000	0.2990	0.8652
0.1429	25.0	18750	0.3003	0.8636
0.2373	26.0	19500	0.3030	0.8735
0.1884	27.0	20250	0.3051	0.8702
0.1254	28.0	21000	0.3031	0.8602
0.1804	29.0	21750	0.3034	0.8719
0.1437	30.0	22500	0.3048	0.8686
0.1608	31.0	23250	0.3012	0.8669
0.1618	32.0	24000	0.3040	0.8652
0.1429	33.0	24750	0.3043	0.8602
0.1612	34.0	25500	0.3075	0.8652
0.1719	35.0	26250	0.3075	0.8619
0.1633	36.0	27000	0.3103	0.8669
0.1619	37.0	27750	0.3071	0.8636
0.1665	38.0	28500	0.3086	0.8669
0.1293	39.0	29250	0.3088	0.8669
0.1641	40.0	30000	0.3125	0.8719
0.1466	41.0	30750	0.3125	0.8702
0.1482	42.0	31500	0.3110	0.8652
0.1022	43.0	32250	0.3124	0.8652
0.1075	44.0	33000	0.3116	0.8669
0.1257	45.0	33750	0.3131	0.8669
0.1217	46.0	34500	0.3119	0.8669
0.1431	47.0	35250	0.3120	0.8686
0.1086	48.0	36000	0.3131	0.8686
0.1041	49.0	36750	0.3136	0.8686
0.1201	50.0	37500	0.3138	0.8686

Framework versions

Transformers 4.32.1
Pytorch 2.1.0+cu121
Datasets 2.12.0
Tokenizers 0.13.2