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_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: 0.8783333333333333

smids_3x_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: 0.3105
Accuracy: 0.8783

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
0.8516	1.0	225	0.8297	0.6267
0.6679	2.0	450	0.6103	0.7567
0.57	3.0	675	0.5223	0.7883
0.4959	4.0	900	0.4753	0.8083
0.4424	5.0	1125	0.4319	0.8233
0.4261	6.0	1350	0.4129	0.8283
0.4396	7.0	1575	0.4075	0.8167
0.4595	8.0	1800	0.3942	0.8267
0.4172	9.0	2025	0.3692	0.8367
0.3688	10.0	2250	0.3605	0.8583
0.4132	11.0	2475	0.3610	0.8417
0.369	12.0	2700	0.3465	0.8567
0.3672	13.0	2925	0.3443	0.8517
0.3409	14.0	3150	0.3437	0.855
0.2695	15.0	3375	0.3370	0.8567
0.311	16.0	3600	0.3373	0.8533
0.3177	17.0	3825	0.3325	0.8567
0.3059	18.0	4050	0.3310	0.8567
0.3295	19.0	4275	0.3271	0.8583
0.3201	20.0	4500	0.3301	0.8667
0.2645	21.0	4725	0.3242	0.8683
0.2497	22.0	4950	0.3240	0.8633
0.2626	23.0	5175	0.3196	0.8617
0.267	24.0	5400	0.3185	0.8733
0.2637	25.0	5625	0.3155	0.8733
0.3416	26.0	5850	0.3155	0.8783
0.3255	27.0	6075	0.3159	0.8767
0.3021	28.0	6300	0.3189	0.875
0.2292	29.0	6525	0.3137	0.8783
0.2207	30.0	6750	0.3185	0.8733
0.2158	31.0	6975	0.3173	0.8683
0.2149	32.0	7200	0.3154	0.87
0.248	33.0	7425	0.3134	0.8767
0.2339	34.0	7650	0.3133	0.875
0.2585	35.0	7875	0.3147	0.8767
0.2565	36.0	8100	0.3120	0.875
0.269	37.0	8325	0.3111	0.8783
0.2546	38.0	8550	0.3139	0.8733
0.2114	39.0	8775	0.3110	0.8767
0.2032	40.0	9000	0.3108	0.8767
0.2376	41.0	9225	0.3108	0.8783
0.2558	42.0	9450	0.3092	0.8767
0.2753	43.0	9675	0.3113	0.875
0.2795	44.0	9900	0.3109	0.8767
0.2412	45.0	10125	0.3113	0.8783
0.2003	46.0	10350	0.3105	0.88
0.2528	47.0	10575	0.3109	0.88
0.2265	48.0	10800	0.3109	0.8783
0.2494	49.0	11025	0.3106	0.8783
0.2763	50.0	11250	0.3105	0.8783

Framework versions

Transformers 4.32.1
Pytorch 2.1.0+cu121
Datasets 2.12.0
Tokenizers 0.13.2