README.md

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_sgd_001_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: 0.84

smids_1x_beit_base_sgd_001_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: 0.3960
• Accuracy: 0.84

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
1.0915	1.0	75	1.0482	0.46
0.8641	2.0	150	0.8453	0.6317
0.8005	3.0	225	0.7497	0.67
0.7495	4.0	300	0.6945	0.7067
0.7055	5.0	375	0.6553	0.7467
0.7202	6.0	450	0.6245	0.75
0.6588	7.0	525	0.6019	0.7583
0.6049	8.0	600	0.5871	0.76
0.6317	9.0	675	0.5605	0.7833
0.5775	10.0	750	0.5437	0.785
0.5951	11.0	825	0.5303	0.7933
0.5297	12.0	900	0.5191	0.79
0.5261	13.0	975	0.5051	0.7933
0.5545	14.0	1050	0.4974	0.7983
0.4597	15.0	1125	0.4949	0.805
0.4273	16.0	1200	0.4837	0.8017
0.4781	17.0	1275	0.4758	0.8067
0.4613	18.0	1350	0.4662	0.815
0.4966	19.0	1425	0.4609	0.8133
0.5166	20.0	1500	0.4558	0.81
0.4529	21.0	1575	0.4548	0.8167
0.4333	22.0	1650	0.4478	0.8233
0.4673	23.0	1725	0.4422	0.8183
0.402	24.0	1800	0.4383	0.8283
0.4207	25.0	1875	0.4375	0.8283
0.4343	26.0	1950	0.4301	0.8267
0.4249	27.0	2025	0.4265	0.8283
0.4127	28.0	2100	0.4255	0.8267
0.4286	29.0	2175	0.4192	0.8367
0.3988	30.0	2250	0.4174	0.8367
0.3838	31.0	2325	0.4145	0.8383
0.3896	32.0	2400	0.4157	0.835
0.4348	33.0	2475	0.4153	0.825
0.41	34.0	2550	0.4109	0.8367
0.3989	35.0	2625	0.4069	0.84
0.3824	36.0	2700	0.4101	0.8367
0.3688	37.0	2775	0.4062	0.8367
0.4091	38.0	2850	0.4063	0.8367
0.3672	39.0	2925	0.4039	0.835
0.4219	40.0	3000	0.4009	0.8383
0.4047	41.0	3075	0.4024	0.8383
0.4168	42.0	3150	0.3989	0.835
0.4198	43.0	3225	0.3971	0.8417
0.4236	44.0	3300	0.3971	0.84
0.3959	45.0	3375	0.3975	0.8433
0.3933	46.0	3450	0.3984	0.8433
0.3443	47.0	3525	0.3963	0.8417
0.3626	48.0	3600	0.3958	0.8417
0.38	49.0	3675	0.3960	0.8417
0.3733	50.0	3750	0.3960	0.84

Framework versions

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