README.md

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_rms_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: 0.7857142857142857

hushem_5x_beit_base_rms_0001_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: 1.8159
• Accuracy: 0.7857

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
1.4247	1.0	28	1.3411	0.2381
1.3595	2.0	56	1.2501	0.4286
1.3116	3.0	84	1.5240	0.2381
1.303	4.0	112	1.0491	0.5238
1.1942	5.0	140	0.8861	0.7143
1.1712	6.0	168	0.9106	0.5238
0.977	7.0	196	1.1447	0.6905
0.9351	8.0	224	0.7191	0.7619
0.8453	9.0	252	1.3331	0.5714
0.8831	10.0	280	0.8305	0.6905
0.8349	11.0	308	0.6872	0.7619
0.845	12.0	336	0.7545	0.7619
0.784	13.0	364	0.7961	0.7857
0.7404	14.0	392	0.6338	0.8095
0.6277	15.0	420	0.7200	0.7143
0.6386	16.0	448	0.7383	0.8095
0.6167	17.0	476	0.5440	0.8095
0.5129	18.0	504	0.7061	0.7619
0.3836	19.0	532	0.7181	0.7381
0.3202	20.0	560	0.4277	0.8095
0.1958	21.0	588	1.1637	0.7381
0.2343	22.0	616	1.0581	0.8095
0.2016	23.0	644	0.8968	0.7857
0.116	24.0	672	1.0426	0.7857
0.1027	25.0	700	0.6841	0.8333
0.1133	26.0	728	0.8260	0.8095
0.1258	27.0	756	1.3215	0.7619
0.0595	28.0	784	1.0509	0.8810
0.0945	29.0	812	1.3868	0.7857
0.0022	30.0	840	1.7553	0.8095
0.0004	31.0	868	1.9423	0.7857
0.0466	32.0	896	2.0945	0.8095
0.0367	33.0	924	1.6928	0.8095
0.1032	34.0	952	1.3572	0.8571
0.0331	35.0	980	2.0437	0.8095
0.0001	36.0	1008	2.0414	0.8333
0.0286	37.0	1036	2.0546	0.7619
0.009	38.0	1064	2.8381	0.7857
0.0573	39.0	1092	2.4470	0.7857
0.0497	40.0	1120	1.8192	0.7857
0.0003	41.0	1148	2.1421	0.7143
0.0003	42.0	1176	2.2125	0.7381
0.0001	43.0	1204	2.1555	0.7619
0.0002	44.0	1232	1.8154	0.7381
0.0197	45.0	1260	1.7188	0.7381
0.0002	46.0	1288	1.6637	0.8095
0.0152	47.0	1316	1.6954	0.8095
0.0001	48.0	1344	1.8153	0.7857
0.0002	49.0	1372	1.8159	0.7857
0.0	50.0	1400	1.8159	0.7857

Framework versions

• Transformers 4.35.2
• Pytorch 2.1.0+cu118
• Datasets 2.15.0
• Tokenizers 0.15.0