README.md

metadata

license: apache-2.0
base_model: facebook/deit-small-patch16-224
tags:
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - accuracy
model-index:
  - name: smids_1x_deit_small_sgd_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: 0.8716666666666667

smids_1x_deit_small_sgd_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: 0.3620
• Accuracy: 0.8717

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
0.9897	1.0	75	0.9617	0.5517
0.8723	2.0	150	0.8626	0.625
0.7649	3.0	225	0.7773	0.7033
0.6947	4.0	300	0.7095	0.7417
0.6117	5.0	375	0.6569	0.7517
0.5694	6.0	450	0.6132	0.7833
0.5545	7.0	525	0.5789	0.79
0.4978	8.0	600	0.5508	0.7967
0.5086	9.0	675	0.5269	0.8017
0.4854	10.0	750	0.5107	0.8033
0.442	11.0	825	0.4925	0.815
0.4253	12.0	900	0.4789	0.8217
0.4589	13.0	975	0.4669	0.8217
0.402	14.0	1050	0.4553	0.82
0.3349	15.0	1125	0.4468	0.8283
0.3869	16.0	1200	0.4398	0.8333
0.3789	17.0	1275	0.4312	0.8367
0.3564	18.0	1350	0.4255	0.84
0.3321	19.0	1425	0.4198	0.84
0.3788	20.0	1500	0.4135	0.8383
0.3599	21.0	1575	0.4108	0.8417
0.3259	22.0	1650	0.4045	0.8417
0.3384	23.0	1725	0.4010	0.8433
0.3143	24.0	1800	0.3966	0.8433
0.3495	25.0	1875	0.3938	0.8483
0.3642	26.0	1950	0.3902	0.8517
0.2826	27.0	2025	0.3879	0.855
0.3052	28.0	2100	0.3848	0.8533
0.3344	29.0	2175	0.3828	0.855
0.3229	30.0	2250	0.3809	0.8533
0.3173	31.0	2325	0.3785	0.8567
0.3012	32.0	2400	0.3761	0.8567
0.2954	33.0	2475	0.3749	0.8617
0.2924	34.0	2550	0.3731	0.8633
0.3077	35.0	2625	0.3719	0.8667
0.3047	36.0	2700	0.3705	0.8667
0.2425	37.0	2775	0.3691	0.8683
0.3384	38.0	2850	0.3680	0.8683
0.2795	39.0	2925	0.3666	0.8683
0.2754	40.0	3000	0.3660	0.87
0.2793	41.0	3075	0.3650	0.8683
0.288	42.0	3150	0.3645	0.87
0.3153	43.0	3225	0.3639	0.87
0.2599	44.0	3300	0.3636	0.8717
0.3229	45.0	3375	0.3630	0.8717
0.297	46.0	3450	0.3626	0.8717
0.2632	47.0	3525	0.3624	0.8717
0.3026	48.0	3600	0.3623	0.8717
0.3009	49.0	3675	0.3621	0.8717
0.2576	50.0	3750	0.3620	0.8717

Framework versions

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