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_rms_00001_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_rms_00001_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: 0.8277
• 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: 1e-05
• 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	1.5522	0.2444
1.5007	2.0	12	0.9869	0.5778
1.5007	3.0	18	0.6157	0.7778
0.5182	4.0	24	0.5627	0.7333
0.1483	5.0	30	0.4776	0.8222
0.1483	6.0	36	0.6682	0.7556
0.0311	7.0	42	0.5819	0.7778
0.0311	8.0	48	0.4872	0.7778
0.0331	9.0	54	0.4912	0.8
0.0033	10.0	60	0.5641	0.8
0.0033	11.0	66	0.6170	0.7778
0.0022	12.0	72	0.5442	0.7778
0.0022	13.0	78	0.5868	0.7778
0.0015	14.0	84	0.6003	0.7778
0.0016	15.0	90	0.6638	0.7778
0.0016	16.0	96	0.5970	0.7778
0.0018	17.0	102	0.5993	0.7556
0.0018	18.0	108	0.6366	0.7778
0.0011	19.0	114	0.6378	0.7778
0.0017	20.0	120	0.8113	0.7111
0.0017	21.0	126	0.8083	0.7111
0.0008	22.0	132	0.7911	0.7111
0.0008	23.0	138	0.7952	0.7111
0.0008	24.0	144	0.7752	0.7333
0.0017	25.0	150	0.9377	0.7333
0.0017	26.0	156	0.8972	0.7333
0.0006	27.0	162	0.8372	0.7556
0.0006	28.0	168	0.8095	0.7556
0.0006	29.0	174	0.8118	0.7556
0.0005	30.0	180	0.7760	0.7556
0.0005	31.0	186	0.7900	0.7556
0.0006	32.0	192	0.7968	0.7556
0.0006	33.0	198	0.7445	0.7556
0.0042	34.0	204	0.7262	0.7556
0.001	35.0	210	0.8101	0.7333
0.001	36.0	216	0.8028	0.7333
0.0005	37.0	222	0.8107	0.7333
0.0005	38.0	228	0.8133	0.7333
0.0025	39.0	234	0.8108	0.7333
0.0005	40.0	240	0.8097	0.7333
0.0005	41.0	246	0.8283	0.7333
0.0006	42.0	252	0.8277	0.7333
0.0006	43.0	258	0.8277	0.7333
0.0012	44.0	264	0.8277	0.7333
0.0004	45.0	270	0.8277	0.7333
0.0004	46.0	276	0.8277	0.7333
0.0008	47.0	282	0.8277	0.7333
0.0008	48.0	288	0.8277	0.7333
0.0011	49.0	294	0.8277	0.7333
0.0003	50.0	300	0.8277	0.7333

Framework versions

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