metadata

license: apache-2.0
base_model: microsoft/beit-base-patch16-224
tags:
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - accuracy
model-index:
  - name: smids_5x_beit_base_adamax_001_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: 0.826955074875208

smids_5x_beit_base_adamax_001_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: 0.6098
Accuracy: 0.8270

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
1.1062	1.0	375	1.0982	0.3344
0.9246	2.0	750	0.8990	0.5008
0.869	3.0	1125	0.8746	0.5258
0.8743	4.0	1500	0.8284	0.5674
0.7741	5.0	1875	0.7937	0.5940
0.7654	6.0	2250	0.8614	0.5757
0.7957	7.0	2625	0.7450	0.6273
0.7361	8.0	3000	0.7601	0.6190
0.7832	9.0	3375	0.7148	0.6473
0.7176	10.0	3750	0.7112	0.6539
0.7021	11.0	4125	0.6760	0.6672
0.7391	12.0	4500	0.6756	0.6839
0.6718	13.0	4875	0.6548	0.6955
0.6958	14.0	5250	0.6500	0.7072
0.5987	15.0	5625	0.6407	0.7072
0.6067	16.0	6000	0.6268	0.7221
0.6185	17.0	6375	0.5757	0.7554
0.5734	18.0	6750	0.5844	0.7504
0.5355	19.0	7125	0.5955	0.7354
0.5827	20.0	7500	0.5704	0.7388
0.5749	21.0	7875	0.5428	0.7804
0.5089	22.0	8250	0.5221	0.7887
0.5094	23.0	8625	0.5782	0.7671
0.5429	24.0	9000	0.5089	0.7737
0.4205	25.0	9375	0.5382	0.7687
0.5532	26.0	9750	0.5416	0.7654
0.5743	27.0	10125	0.5044	0.7854
0.4757	28.0	10500	0.4923	0.7837
0.4893	29.0	10875	0.5093	0.7953
0.4472	30.0	11250	0.4972	0.8003
0.4925	31.0	11625	0.4677	0.8003
0.4327	32.0	12000	0.5055	0.8003
0.3876	33.0	12375	0.5066	0.8070
0.365	34.0	12750	0.5108	0.8003
0.4195	35.0	13125	0.4907	0.8136
0.3672	36.0	13500	0.5164	0.8170
0.3426	37.0	13875	0.5029	0.8136
0.3759	38.0	14250	0.4848	0.8220
0.3673	39.0	14625	0.5029	0.7953
0.3205	40.0	15000	0.4939	0.8253
0.278	41.0	15375	0.4766	0.8203
0.3125	42.0	15750	0.5477	0.8170
0.2792	43.0	16125	0.5391	0.8253
0.2594	44.0	16500	0.5619	0.8220
0.2487	45.0	16875	0.5522	0.8153
0.2997	46.0	17250	0.5706	0.8270
0.2756	47.0	17625	0.5989	0.8220
0.2505	48.0	18000	0.5806	0.8303
0.2151	49.0	18375	0.6077	0.8286
0.1705	50.0	18750	0.6098	0.8270

Framework versions

Transformers 4.32.1
Pytorch 2.1.0+cu121
Datasets 2.12.0
Tokenizers 0.13.2