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_fold3
    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: 0.8783333333333333

smids_10x_beit_large_sgd_0001_fold3

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: 0.3045
Accuracy: 0.8783

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
0.9373	1.0	750	1.0091	0.4617
0.7639	2.0	1500	0.8536	0.6117
0.6803	3.0	2250	0.7396	0.6933
0.5905	4.0	3000	0.6588	0.75
0.5735	5.0	3750	0.5968	0.7833
0.5021	6.0	4500	0.5507	0.8017
0.4704	7.0	5250	0.5159	0.8133
0.4872	8.0	6000	0.4878	0.8267
0.4458	9.0	6750	0.4650	0.83
0.4154	10.0	7500	0.4469	0.8417
0.4321	11.0	8250	0.4318	0.845
0.3944	12.0	9000	0.4172	0.8433
0.3976	13.0	9750	0.4054	0.8483
0.4242	14.0	10500	0.3948	0.85
0.3817	15.0	11250	0.3850	0.8517
0.3695	16.0	12000	0.3777	0.8517
0.3394	17.0	12750	0.3711	0.8533
0.3418	18.0	13500	0.3639	0.8583
0.3927	19.0	14250	0.3584	0.8633
0.3355	20.0	15000	0.3536	0.8617
0.3182	21.0	15750	0.3485	0.86
0.3252	22.0	16500	0.3442	0.8617
0.3481	23.0	17250	0.3402	0.86
0.352	24.0	18000	0.3367	0.8617
0.3814	25.0	18750	0.3335	0.865
0.3436	26.0	19500	0.3305	0.865
0.2353	27.0	20250	0.3280	0.865
0.3097	28.0	21000	0.3253	0.8683
0.3673	29.0	21750	0.3232	0.8683
0.316	30.0	22500	0.3211	0.87
0.2736	31.0	23250	0.3193	0.8733
0.3111	32.0	24000	0.3172	0.875
0.3586	33.0	24750	0.3157	0.875
0.3482	34.0	25500	0.3143	0.875
0.2894	35.0	26250	0.3130	0.875
0.3247	36.0	27000	0.3121	0.8733
0.3266	37.0	27750	0.3109	0.8733
0.3501	38.0	28500	0.3098	0.8733
0.3018	39.0	29250	0.3089	0.875
0.3416	40.0	30000	0.3082	0.875
0.318	41.0	30750	0.3074	0.875
0.3558	42.0	31500	0.3067	0.8767
0.2993	43.0	32250	0.3061	0.8767
0.2907	44.0	33000	0.3056	0.8767
0.2783	45.0	33750	0.3053	0.8767
0.2937	46.0	34500	0.3050	0.8767
0.3037	47.0	35250	0.3048	0.8783
0.3233	48.0	36000	0.3046	0.8783
0.3074	49.0	36750	0.3045	0.8783
0.2861	50.0	37500	0.3045	0.8783

Framework versions

Transformers 4.32.1
Pytorch 2.1.0+cu121
Datasets 2.12.0
Tokenizers 0.13.2