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_fold5
    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: 0.8733333333333333

smids_10x_beit_large_sgd_0001_fold5

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: 0.3210
Accuracy: 0.8733

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
0.9567	1.0	750	1.0187	0.4617
0.813	2.0	1500	0.8588	0.6033
0.7071	3.0	2250	0.7412	0.6717
0.6056	4.0	3000	0.6548	0.7317
0.553	5.0	3750	0.5916	0.7767
0.5415	6.0	4500	0.5456	0.7983
0.4714	7.0	5250	0.5118	0.8083
0.4919	8.0	6000	0.4844	0.8133
0.4714	9.0	6750	0.4633	0.8167
0.408	10.0	7500	0.4458	0.8267
0.416	11.0	8250	0.4326	0.8317
0.4057	12.0	9000	0.4197	0.84
0.4411	13.0	9750	0.4091	0.8383
0.3787	14.0	10500	0.3999	0.84
0.4112	15.0	11250	0.3917	0.8433
0.3272	16.0	12000	0.3857	0.8433
0.3453	17.0	12750	0.3795	0.8467
0.2978	18.0	13500	0.3732	0.8467
0.3695	19.0	14250	0.3692	0.8533
0.3546	20.0	15000	0.3643	0.855
0.3274	21.0	15750	0.3603	0.8583
0.3708	22.0	16500	0.3566	0.8583
0.3177	23.0	17250	0.3530	0.8617
0.3259	24.0	18000	0.3501	0.865
0.3343	25.0	18750	0.3473	0.8683
0.3365	26.0	19500	0.3445	0.865
0.2524	27.0	20250	0.3419	0.865
0.3298	28.0	21000	0.3396	0.8667
0.3375	29.0	21750	0.3374	0.8667
0.3203	30.0	22500	0.3355	0.8683
0.2843	31.0	23250	0.3334	0.8683
0.3065	32.0	24000	0.3325	0.8667
0.3385	33.0	24750	0.3310	0.8717
0.2656	34.0	25500	0.3296	0.8717
0.3103	35.0	26250	0.3282	0.8733
0.3336	36.0	27000	0.3274	0.8717
0.2743	37.0	27750	0.3265	0.8733
0.3245	38.0	28500	0.3255	0.8717
0.321	39.0	29250	0.3249	0.8733
0.2652	40.0	30000	0.3240	0.8733
0.2925	41.0	30750	0.3236	0.875
0.3072	42.0	31500	0.3229	0.875
0.3317	43.0	32250	0.3226	0.875
0.2932	44.0	33000	0.3221	0.875
0.3178	45.0	33750	0.3218	0.8733
0.2606	46.0	34500	0.3214	0.875
0.3688	47.0	35250	0.3212	0.875
0.2811	48.0	36000	0.3211	0.8733
0.3003	49.0	36750	0.3211	0.8733
0.2418	50.0	37500	0.3210	0.8733

Framework versions

Transformers 4.32.1
Pytorch 2.1.0+cu121
Datasets 2.12.0
Tokenizers 0.13.2