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_3x_beit_base_sgd_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: 0.7886855241264559

smids_3x_beit_base_sgd_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: 0.5470
• Accuracy: 0.7887

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
1.1643	1.0	225	1.2557	0.3494
1.1336	2.0	450	1.1964	0.3727
1.0702	3.0	675	1.1415	0.3960
1.0744	4.0	900	1.0897	0.4226
0.9272	5.0	1125	1.0392	0.4526
0.9348	6.0	1350	0.9924	0.4908
0.9221	7.0	1575	0.9474	0.5374
0.8806	8.0	1800	0.9069	0.5890
0.8541	9.0	2025	0.8693	0.6206
0.8102	10.0	2250	0.8367	0.6439
0.7893	11.0	2475	0.8072	0.6672
0.7786	12.0	2700	0.7812	0.6872
0.7601	13.0	2925	0.7581	0.7038
0.7654	14.0	3150	0.7376	0.7105
0.7556	15.0	3375	0.7195	0.7171
0.7319	16.0	3600	0.7031	0.7321
0.6868	17.0	3825	0.6881	0.7354
0.7278	18.0	4050	0.6745	0.7421
0.6222	19.0	4275	0.6623	0.7454
0.6905	20.0	4500	0.6515	0.7471
0.6715	21.0	4725	0.6419	0.7554
0.7342	22.0	4950	0.6326	0.7554
0.6844	23.0	5175	0.6245	0.7621
0.6577	24.0	5400	0.6173	0.7654
0.6177	25.0	5625	0.6101	0.7687
0.647	26.0	5850	0.6037	0.7671
0.6355	27.0	6075	0.5976	0.7704
0.6059	28.0	6300	0.5926	0.7704
0.5954	29.0	6525	0.5873	0.7770
0.6256	30.0	6750	0.5829	0.7787
0.6261	31.0	6975	0.5789	0.7820
0.5804	32.0	7200	0.5748	0.7820
0.5936	33.0	7425	0.5711	0.7854
0.5647	34.0	7650	0.5682	0.7854
0.6238	35.0	7875	0.5657	0.7854
0.5976	36.0	8100	0.5630	0.7854
0.5852	37.0	8325	0.5605	0.7870
0.5826	38.0	8550	0.5584	0.7854
0.5619	39.0	8775	0.5564	0.7854
0.5946	40.0	9000	0.5547	0.7870
0.5381	41.0	9225	0.5529	0.7870
0.5966	42.0	9450	0.5514	0.7870
0.588	43.0	9675	0.5504	0.7870
0.5705	44.0	9900	0.5494	0.7854
0.6073	45.0	10125	0.5486	0.7870
0.5915	46.0	10350	0.5480	0.7887
0.5988	47.0	10575	0.5476	0.7887
0.542	48.0	10800	0.5472	0.7887
0.5885	49.0	11025	0.5471	0.7887
0.5585	50.0	11250	0.5470	0.7887

Framework versions

• Transformers 4.32.1
• Pytorch 2.1.0+cu121
• Datasets 2.12.0
• Tokenizers 0.13.2