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_sgd_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: 0.1111111111111111

hushem_1x_beit_base_sgd_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: 1.6388
• Accuracy: 0.1111

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	1.6742	0.1111
1.4975	2.0	12	1.6721	0.1111
1.4975	3.0	18	1.6701	0.1111
1.4871	4.0	24	1.6683	0.1111
1.4949	5.0	30	1.6664	0.1111
1.4949	6.0	36	1.6646	0.1111
1.4943	7.0	42	1.6628	0.1111
1.4943	8.0	48	1.6613	0.1111
1.5225	9.0	54	1.6596	0.1111
1.4389	10.0	60	1.6582	0.1111
1.4389	11.0	66	1.6569	0.1111
1.4732	12.0	72	1.6557	0.1111
1.4732	13.0	78	1.6545	0.1111
1.4384	14.0	84	1.6534	0.1111
1.4676	15.0	90	1.6523	0.1111
1.4676	16.0	96	1.6513	0.1111
1.4696	17.0	102	1.6502	0.1111
1.4696	18.0	108	1.6492	0.1111
1.4688	19.0	114	1.6483	0.1111
1.4525	20.0	120	1.6474	0.1111
1.4525	21.0	126	1.6467	0.1111
1.4642	22.0	132	1.6459	0.1111
1.4642	23.0	138	1.6451	0.1111
1.4184	24.0	144	1.6445	0.1111
1.4687	25.0	150	1.6439	0.1111
1.4687	26.0	156	1.6433	0.1111
1.4512	27.0	162	1.6428	0.1111
1.4512	28.0	168	1.6422	0.1111
1.4747	29.0	174	1.6417	0.1111
1.4313	30.0	180	1.6412	0.1111
1.4313	31.0	186	1.6408	0.1111
1.4333	32.0	192	1.6405	0.1111
1.4333	33.0	198	1.6401	0.1111
1.4855	34.0	204	1.6398	0.1111
1.4466	35.0	210	1.6396	0.1111
1.4466	36.0	216	1.6394	0.1111
1.4336	37.0	222	1.6392	0.1111
1.4336	38.0	228	1.6390	0.1111
1.4754	39.0	234	1.6389	0.1111
1.4452	40.0	240	1.6388	0.1111
1.4452	41.0	246	1.6388	0.1111
1.4335	42.0	252	1.6388	0.1111
1.4335	43.0	258	1.6388	0.1111
1.4391	44.0	264	1.6388	0.1111
1.4625	45.0	270	1.6388	0.1111
1.4625	46.0	276	1.6388	0.1111
1.4619	47.0	282	1.6388	0.1111
1.4619	48.0	288	1.6388	0.1111
1.4316	49.0	294	1.6388	0.1111
1.4278	50.0	300	1.6388	0.1111

Framework versions

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