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_0001_fold4
    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: 0.77

smids_3x_beit_base_sgd_0001_fold4

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: 0.5543
Accuracy: 0.77

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
1.2016	1.0	225	1.2841	0.345
1.1719	2.0	450	1.2211	0.3617
1.0758	3.0	675	1.1630	0.3733
1.0147	4.0	900	1.1086	0.4033
1.0074	5.0	1125	1.0560	0.4317
0.9405	6.0	1350	1.0063	0.4617
0.9199	7.0	1575	0.9602	0.51
0.9125	8.0	1800	0.9177	0.5617
0.8654	9.0	2025	0.8771	0.6017
0.8229	10.0	2250	0.8432	0.6333
0.8209	11.0	2475	0.8129	0.6567
0.775	12.0	2700	0.7860	0.675
0.7435	13.0	2925	0.7620	0.6883
0.7034	14.0	3150	0.7408	0.695
0.7434	15.0	3375	0.7223	0.7033
0.7412	16.0	3600	0.7055	0.7133
0.6871	17.0	3825	0.6906	0.7167
0.6997	18.0	4050	0.6769	0.725
0.6998	19.0	4275	0.6646	0.7267
0.6623	20.0	4500	0.6540	0.7283
0.668	21.0	4725	0.6441	0.73
0.6697	22.0	4950	0.6349	0.7317
0.6394	23.0	5175	0.6268	0.7383
0.6267	24.0	5400	0.6193	0.7383
0.6154	25.0	5625	0.6125	0.7433
0.5813	26.0	5850	0.6070	0.745
0.612	27.0	6075	0.6014	0.7483
0.6011	28.0	6300	0.5964	0.7483
0.5913	29.0	6525	0.5915	0.7517
0.5609	30.0	6750	0.5872	0.76
0.5861	31.0	6975	0.5835	0.7617
0.5483	32.0	7200	0.5800	0.76
0.5986	33.0	7425	0.5766	0.7633
0.619	34.0	7650	0.5736	0.7617
0.5813	35.0	7875	0.5710	0.765
0.6084	36.0	8100	0.5683	0.7667
0.6052	37.0	8325	0.5664	0.765
0.5601	38.0	8550	0.5646	0.765
0.5878	39.0	8775	0.5631	0.7633
0.6072	40.0	9000	0.5616	0.7633
0.5597	41.0	9225	0.5601	0.7683
0.5694	42.0	9450	0.5588	0.7667
0.5553	43.0	9675	0.5575	0.77
0.5942	44.0	9900	0.5566	0.77
0.6005	45.0	10125	0.5559	0.77
0.58	46.0	10350	0.5553	0.77
0.5814	47.0	10575	0.5548	0.77
0.5609	48.0	10800	0.5545	0.7717
0.6076	49.0	11025	0.5543	0.77
0.5819	50.0	11250	0.5543	0.77

Framework versions

Transformers 4.32.1
Pytorch 2.1.0+cu121
Datasets 2.12.0
Tokenizers 0.13.2