metadata

license: apache-2.0
base_model: microsoft/beit-base-patch16-224
tags:
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - accuracy
model-index:
  - name: smids_1x_beit_base_adamax_0001_fold5
    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: 0.88

smids_1x_beit_base_adamax_0001_fold5

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: 0.8148
Accuracy: 0.88

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: 0.0001
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
0.3159	1.0	75	0.2787	0.8933
0.2494	2.0	150	0.2824	0.8917
0.1709	3.0	225	0.2857	0.89
0.0771	4.0	300	0.3708	0.8933
0.0554	5.0	375	0.4256	0.895
0.0571	6.0	450	0.4870	0.8867
0.0043	7.0	525	0.5217	0.9017
0.0346	8.0	600	0.5838	0.8983
0.0305	9.0	675	0.5589	0.89
0.0299	10.0	750	0.6507	0.8833
0.0112	11.0	825	0.7257	0.885
0.0571	12.0	900	0.6425	0.8933
0.0111	13.0	975	0.6434	0.885
0.0007	14.0	1050	0.6590	0.8917
0.0158	15.0	1125	0.6659	0.895
0.0001	16.0	1200	0.6546	0.8983
0.0007	17.0	1275	0.6736	0.8867
0.0231	18.0	1350	0.7021	0.8917
0.0081	19.0	1425	0.7031	0.8917
0.0001	20.0	1500	0.7077	0.8833
0.0034	21.0	1575	0.6794	0.885
0.0184	22.0	1650	0.7927	0.865
0.0002	23.0	1725	0.7523	0.8783
0.0048	24.0	1800	0.7237	0.885
0.0065	25.0	1875	0.7425	0.8867
0.0064	26.0	1950	0.7940	0.8833
0.0055	27.0	2025	0.7223	0.8983
0.0092	28.0	2100	0.7594	0.8933
0.0	29.0	2175	0.7361	0.89
0.0	30.0	2250	0.7567	0.89
0.017	31.0	2325	0.7474	0.8883
0.0029	32.0	2400	0.8687	0.8767
0.0165	33.0	2475	0.8109	0.8883
0.0031	34.0	2550	0.8076	0.885
0.0039	35.0	2625	0.8393	0.8833
0.0031	36.0	2700	0.8234	0.8817
0.0001	37.0	2775	0.8155	0.8833
0.0034	38.0	2850	0.8110	0.89
0.0036	39.0	2925	0.8344	0.8817
0.0002	40.0	3000	0.8172	0.8833
0.0025	41.0	3075	0.8298	0.8817
0.0021	42.0	3150	0.8481	0.8817
0.0001	43.0	3225	0.8405	0.8817
0.0035	44.0	3300	0.8375	0.8833
0.0006	45.0	3375	0.8281	0.885
0.0024	46.0	3450	0.8226	0.8833
0.0	47.0	3525	0.8109	0.8817
0.0	48.0	3600	0.8113	0.88
0.0026	49.0	3675	0.8154	0.88
0.0067	50.0	3750	0.8148	0.88

Framework versions

Transformers 4.35.2
Pytorch 2.1.0+cu118
Datasets 2.15.0
Tokenizers 0.15.0