metadata

license: apache-2.0
base_model: microsoft/beit-base-patch16-224
tags:
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - accuracy
model-index:
  - name: smids_3x_beit_base_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: 0.8966666666666666

smids_3x_beit_base_sgd_001_fold3

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

Loss: 0.2937
Accuracy: 0.8967

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
0.8635	1.0	225	0.8411	0.6267
0.6523	2.0	450	0.6173	0.7583
0.5403	3.0	675	0.5212	0.8017
0.4896	4.0	900	0.4692	0.8233
0.4594	5.0	1125	0.4353	0.8333
0.4326	6.0	1350	0.4063	0.8467
0.3692	7.0	1575	0.3897	0.855
0.4088	8.0	1800	0.3756	0.8567
0.4036	9.0	2025	0.3600	0.8667
0.387	10.0	2250	0.3535	0.8717
0.349	11.0	2475	0.3460	0.8717
0.3537	12.0	2700	0.3401	0.875
0.3714	13.0	2925	0.3342	0.8783
0.3497	14.0	3150	0.3327	0.8817
0.2955	15.0	3375	0.3234	0.8867
0.346	16.0	3600	0.3197	0.8933
0.3452	17.0	3825	0.3164	0.89
0.3182	18.0	4050	0.3143	0.8867
0.3047	19.0	4275	0.3110	0.8933
0.3008	20.0	4500	0.3105	0.8883
0.2783	21.0	4725	0.3050	0.8917
0.2751	22.0	4950	0.3037	0.8967
0.2477	23.0	5175	0.3059	0.8917
0.2485	24.0	5400	0.3040	0.8917
0.2841	25.0	5625	0.3099	0.8917
0.2803	26.0	5850	0.3058	0.8967
0.2313	27.0	6075	0.3019	0.8933
0.2302	28.0	6300	0.3005	0.895
0.2775	29.0	6525	0.2994	0.895
0.2039	30.0	6750	0.2961	0.9
0.261	31.0	6975	0.2949	0.9
0.2791	32.0	7200	0.2986	0.895
0.2917	33.0	7425	0.2938	0.8983
0.2364	34.0	7650	0.2966	0.895
0.2087	35.0	7875	0.2917	0.9
0.2544	36.0	8100	0.2944	0.8983
0.2254	37.0	8325	0.2941	0.8967
0.2119	38.0	8550	0.2972	0.8933
0.2445	39.0	8775	0.2905	0.9
0.204	40.0	9000	0.2909	0.8967
0.2353	41.0	9225	0.2968	0.895
0.2574	42.0	9450	0.2926	0.9
0.2197	43.0	9675	0.2953	0.8967
0.2519	44.0	9900	0.2939	0.8967
0.2337	45.0	10125	0.2971	0.895
0.2047	46.0	10350	0.2932	0.8967
0.2633	47.0	10575	0.2935	0.8967
0.2254	48.0	10800	0.2947	0.895
0.2679	49.0	11025	0.2937	0.895
0.2687	50.0	11250	0.2937	0.8967

Framework versions

Transformers 4.32.1
Pytorch 2.1.0+cu121
Datasets 2.12.0
Tokenizers 0.13.2