metadata

license: apache-2.0
base_model: microsoft/beit-large-patch16-224
tags:
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - accuracy
model-index:
  - name: smids_10x_beit_large_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: 0.8583333333333333

smids_10x_beit_large_sgd_0001_fold4

This model is a fine-tuned version of microsoft/beit-large-patch16-224 on the imagefolder dataset. It achieves the following results on the evaluation set:

Loss: 0.3577
Accuracy: 0.8583

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
0.956	1.0	750	0.9742	0.4667
0.7783	2.0	1500	0.8200	0.63
0.7323	3.0	2250	0.7096	0.71
0.6337	4.0	3000	0.6341	0.7517
0.5065	5.0	3750	0.5795	0.775
0.4965	6.0	4500	0.5386	0.8
0.4578	7.0	5250	0.5091	0.8117
0.4692	8.0	6000	0.4857	0.825
0.4711	9.0	6750	0.4676	0.8333
0.3709	10.0	7500	0.4525	0.835
0.4051	11.0	8250	0.4402	0.8367
0.4533	12.0	9000	0.4305	0.8417
0.3537	13.0	9750	0.4215	0.8467
0.4025	14.0	10500	0.4147	0.8483
0.3254	15.0	11250	0.4082	0.8467
0.3312	16.0	12000	0.4031	0.8467
0.2854	17.0	12750	0.3983	0.8483
0.3355	18.0	13500	0.3942	0.8517
0.3881	19.0	14250	0.3905	0.8483
0.3257	20.0	15000	0.3873	0.8517
0.3303	21.0	15750	0.3846	0.8483
0.3308	22.0	16500	0.3815	0.8517
0.3025	23.0	17250	0.3791	0.85
0.3591	24.0	18000	0.3770	0.8517
0.3426	25.0	18750	0.3750	0.8567
0.2909	26.0	19500	0.3737	0.8567
0.3106	27.0	20250	0.3719	0.855
0.3129	28.0	21000	0.3704	0.855
0.2957	29.0	21750	0.3688	0.855
0.2639	30.0	22500	0.3673	0.855
0.2821	31.0	23250	0.3660	0.855
0.2912	32.0	24000	0.3649	0.8567
0.3006	33.0	24750	0.3640	0.8583
0.3129	34.0	25500	0.3632	0.8583
0.2463	35.0	26250	0.3625	0.86
0.3133	36.0	27000	0.3619	0.8583
0.3061	37.0	27750	0.3612	0.8583
0.3206	38.0	28500	0.3606	0.8583
0.3433	39.0	29250	0.3601	0.8583
0.3138	40.0	30000	0.3597	0.8583
0.2988	41.0	30750	0.3593	0.8583
0.3075	42.0	31500	0.3589	0.8583
0.3059	43.0	32250	0.3587	0.8583
0.3142	44.0	33000	0.3585	0.8583
0.3034	45.0	33750	0.3583	0.8583
0.2744	46.0	34500	0.3580	0.8583
0.2599	47.0	35250	0.3579	0.8583
0.2643	48.0	36000	0.3578	0.8583
0.2927	49.0	36750	0.3577	0.8583
0.2381	50.0	37500	0.3577	0.8583

Framework versions

Transformers 4.32.1
Pytorch 2.1.0+cu121
Datasets 2.12.0
Tokenizers 0.13.2