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_1x_beit_base_adamax_0001_fold1
    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: 0.7333333333333333

hushem_1x_beit_base_adamax_0001_fold1

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: 1.1942
• Accuracy: 0.7333

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
No log	1.0	6	1.1737	0.5111
1.2996	2.0	12	0.6731	0.7111
1.2996	3.0	18	0.5816	0.7778
0.3034	4.0	24	0.5950	0.7778
0.0484	5.0	30	0.7873	0.7333
0.0484	6.0	36	0.7472	0.7556
0.0106	7.0	42	0.8528	0.8
0.0106	8.0	48	0.7211	0.7778
0.0205	9.0	54	0.6347	0.7778
0.0012	10.0	60	0.6115	0.8
0.0012	11.0	66	0.6050	0.8222
0.0005	12.0	72	0.6253	0.8222
0.0005	13.0	78	0.7723	0.8
0.0021	14.0	84	0.9287	0.8
0.0003	15.0	90	1.0136	0.7778
0.0003	16.0	96	0.9985	0.7778
0.0004	17.0	102	0.9348	0.7778
0.0004	18.0	108	0.8985	0.8
0.0003	19.0	114	0.8733	0.8222
0.0009	20.0	120	0.8790	0.8222
0.0009	21.0	126	1.1330	0.7778
0.0002	22.0	132	1.2620	0.7556
0.0002	23.0	138	1.3184	0.7556
0.0003	24.0	144	1.3104	0.7778
0.0003	25.0	150	1.2554	0.7556
0.0003	26.0	156	1.2162	0.7556
0.0002	27.0	162	1.1923	0.7333
0.0002	28.0	168	1.1869	0.7333
0.0002	29.0	174	1.1546	0.7333
0.0002	30.0	180	1.1302	0.7556
0.0002	31.0	186	1.1214	0.7556
0.0003	32.0	192	1.1205	0.7556
0.0003	33.0	198	1.1222	0.7556
0.0018	34.0	204	1.1316	0.7556
0.0004	35.0	210	1.1630	0.7556
0.0004	36.0	216	1.1838	0.7333
0.0002	37.0	222	1.1946	0.7333
0.0002	38.0	228	1.1949	0.7333
0.0004	39.0	234	1.1930	0.7333
0.0002	40.0	240	1.1932	0.7333
0.0002	41.0	246	1.1940	0.7333
0.0002	42.0	252	1.1942	0.7333
0.0002	43.0	258	1.1942	0.7333
0.0002	44.0	264	1.1942	0.7333
0.0002	45.0	270	1.1942	0.7333
0.0002	46.0	276	1.1942	0.7333
0.0002	47.0	282	1.1942	0.7333
0.0002	48.0	288	1.1942	0.7333
0.0003	49.0	294	1.1942	0.7333
0.0001	50.0	300	1.1942	0.7333

Framework versions

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