metadata

license: apache-2.0
base_model: microsoft/beit-base-patch16-224
tags:
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - accuracy
model-index:
  - name: hushem_5x_beit_base_adamax_001_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: 0.7380952380952381

hushem_5x_beit_base_adamax_001_fold4

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: 2.1895
Accuracy: 0.7381

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
1.398	1.0	28	1.3161	0.2619
1.3348	2.0	56	1.1486	0.5
1.2598	3.0	84	1.2723	0.4762
1.0258	4.0	112	2.5380	0.3571
0.9514	5.0	140	0.7752	0.6667
0.9022	6.0	168	0.7061	0.7381
0.894	7.0	196	0.9563	0.6190
0.9803	8.0	224	0.6994	0.7381
0.8819	9.0	252	0.6742	0.7619
0.8414	10.0	280	0.7881	0.6667
0.8005	11.0	308	0.9825	0.7143
0.8103	12.0	336	0.6127	0.7619
0.8302	13.0	364	0.8926	0.7143
0.7477	14.0	392	0.8951	0.6190
0.7772	15.0	420	0.6142	0.7619
0.6718	16.0	448	0.6386	0.7619
0.6971	17.0	476	0.8030	0.6429
0.6705	18.0	504	0.8028	0.6667
0.6156	19.0	532	0.8667	0.6429
0.4804	20.0	560	0.6053	0.7381
0.3939	21.0	588	0.8598	0.7381
0.485	22.0	616	0.7061	0.7381
0.4778	23.0	644	1.0522	0.6190
0.4222	24.0	672	0.8683	0.7381
0.2892	25.0	700	1.0772	0.7143
0.3633	26.0	728	0.8242	0.7857
0.4528	27.0	756	1.4370	0.6667
0.2621	28.0	784	1.0095	0.8095
0.1921	29.0	812	1.3782	0.7143
0.1811	30.0	840	1.8693	0.7143
0.1481	31.0	868	1.8742	0.7619
0.1394	32.0	896	1.7130	0.7143
0.0623	33.0	924	1.6326	0.7619
0.1726	34.0	952	1.5273	0.7381
0.1641	35.0	980	1.3046	0.8333
0.0573	36.0	1008	2.1424	0.6667
0.0574	37.0	1036	2.1687	0.7143
0.0558	38.0	1064	1.6907	0.7619
0.0165	39.0	1092	2.0112	0.7619
0.052	40.0	1120	1.7998	0.7619
0.0524	41.0	1148	2.3373	0.7143
0.0976	42.0	1176	2.2060	0.7381
0.0064	43.0	1204	2.2711	0.7619
0.0205	44.0	1232	2.4091	0.7619
0.0254	45.0	1260	2.3470	0.7381
0.0473	46.0	1288	2.3652	0.7381
0.0464	47.0	1316	2.2959	0.7381
0.0006	48.0	1344	2.1947	0.7381
0.0143	49.0	1372	2.1895	0.7381
0.0223	50.0	1400	2.1895	0.7381

Framework versions

Transformers 4.35.2
Pytorch 2.1.0+cu118
Datasets 2.15.0
Tokenizers 0.15.0