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_rms_0001_fold2
    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: 0.740432612312812

smids_1x_beit_base_rms_0001_fold2

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: 0.9358
Accuracy: 0.7404

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
1.0437	1.0	75	0.9679	0.5042
0.9234	2.0	150	0.8669	0.5208
1.0795	3.0	225	0.7926	0.5874
0.9543	4.0	300	0.8244	0.5507
0.8239	5.0	375	0.7959	0.5857
0.7924	6.0	450	0.7928	0.5890
0.8468	7.0	525	0.7806	0.6256
0.8608	8.0	600	0.9027	0.5408
0.7878	9.0	675	0.7544	0.6373
0.9079	10.0	750	0.7732	0.6190
0.7705	11.0	825	0.7349	0.6290
0.7586	12.0	900	0.7322	0.6306
0.7794	13.0	975	0.7224	0.6323
0.7123	14.0	1050	0.7252	0.6572
0.744	15.0	1125	0.7450	0.5990
0.7086	16.0	1200	0.6962	0.6639
0.7295	17.0	1275	0.7508	0.6489
0.7289	18.0	1350	0.6978	0.6722
0.6947	19.0	1425	0.7112	0.6739
0.6923	20.0	1500	0.7131	0.6805
0.7545	21.0	1575	0.7480	0.6223
0.68	22.0	1650	0.6683	0.6839
0.7107	23.0	1725	0.6889	0.6772
0.6933	24.0	1800	0.6566	0.6822
0.6429	25.0	1875	0.6381	0.7005
0.6742	26.0	1950	0.6536	0.6822
0.6753	27.0	2025	0.6462	0.6889
0.6228	28.0	2100	0.6368	0.7022
0.6193	29.0	2175	0.6115	0.7171
0.5568	30.0	2250	0.6625	0.7188
0.584	31.0	2325	0.6680	0.6922
0.581	32.0	2400	0.5723	0.7654
0.5698	33.0	2475	0.6173	0.7205
0.5032	34.0	2550	0.6176	0.7338
0.5019	35.0	2625	0.6137	0.7438
0.4921	36.0	2700	0.5855	0.7571
0.453	37.0	2775	0.6724	0.7271
0.4913	38.0	2850	0.6043	0.7720
0.3871	39.0	2925	0.6124	0.7704
0.4014	40.0	3000	0.6591	0.7521
0.4698	41.0	3075	0.6575	0.7604
0.375	42.0	3150	0.6735	0.7471
0.317	43.0	3225	0.7867	0.7504
0.2968	44.0	3300	0.7423	0.7521
0.2919	45.0	3375	0.8253	0.7504
0.2598	46.0	3450	0.8629	0.7421
0.1951	47.0	3525	0.8586	0.7704
0.1905	48.0	3600	0.9010	0.7438
0.1278	49.0	3675	0.9354	0.7454
0.2294	50.0	3750	0.9358	0.7404

Framework versions

Transformers 4.35.2
Pytorch 2.1.0+cu118
Datasets 2.15.0
Tokenizers 0.15.0