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_rms_00001_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: 0.8885191347753744

smids_1x_beit_base_rms_00001_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: 0.7810
• Accuracy: 0.8885

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: 1e-05
• 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
0.3067	1.0	75	0.2670	0.9018
0.1737	2.0	150	0.2937	0.8918
0.1236	3.0	225	0.2592	0.8968
0.093	4.0	300	0.2806	0.9085
0.0342	5.0	375	0.3377	0.9035
0.0514	6.0	450	0.4662	0.8769
0.0285	7.0	525	0.4751	0.8902
0.0245	8.0	600	0.4931	0.8968
0.0336	9.0	675	0.4686	0.9035
0.0057	10.0	750	0.6619	0.8852
0.0005	11.0	825	0.5601	0.9018
0.045	12.0	900	0.6300	0.8869
0.0006	13.0	975	0.6005	0.8968
0.0104	14.0	1050	0.6903	0.8769
0.0013	15.0	1125	0.6574	0.8968
0.0022	16.0	1200	0.6330	0.8952
0.0138	17.0	1275	0.6340	0.9018
0.0109	18.0	1350	0.7199	0.8902
0.007	19.0	1425	0.7166	0.8968
0.009	20.0	1500	0.8141	0.8802
0.0077	21.0	1575	0.8216	0.8935
0.0199	22.0	1650	0.8347	0.8802
0.0056	23.0	1725	0.7454	0.8869
0.0076	24.0	1800	0.6539	0.8968
0.0001	25.0	1875	0.7625	0.8819
0.0105	26.0	1950	0.7771	0.8918
0.0191	27.0	2025	0.7871	0.8902
0.0146	28.0	2100	0.7395	0.8968
0.0063	29.0	2175	0.7297	0.8968
0.0064	30.0	2250	0.6880	0.8952
0.0044	31.0	2325	0.7924	0.8918
0.0115	32.0	2400	0.7709	0.8918
0.0213	33.0	2475	0.6964	0.8918
0.0034	34.0	2550	0.7612	0.8918
0.0052	35.0	2625	0.7685	0.8968
0.0043	36.0	2700	0.8478	0.8869
0.0001	37.0	2775	0.7661	0.8902
0.0031	38.0	2850	0.7393	0.8968
0.0464	39.0	2925	0.7536	0.8918
0.0026	40.0	3000	0.7768	0.8852
0.0001	41.0	3075	0.8423	0.8835
0.0041	42.0	3150	0.7762	0.8918
0.0072	43.0	3225	0.7847	0.8902
0.0	44.0	3300	0.7699	0.8835
0.0049	45.0	3375	0.7675	0.8852
0.0001	46.0	3450	0.7767	0.8885
0.0029	47.0	3525	0.7697	0.8885
0.0	48.0	3600	0.7734	0.8885
0.0	49.0	3675	0.7813	0.8885
0.0231	50.0	3750	0.7810	0.8885

Framework versions

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