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_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: 0.5

hushem_1x_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: 3.2977
• Accuracy: 0.5

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	1.3978	0.2619
1.9888	2.0	12	1.3961	0.2381
1.9888	3.0	18	1.3839	0.2619
1.4109	4.0	24	1.3035	0.3095
1.3832	5.0	30	1.2707	0.5714
1.3832	6.0	36	1.2845	0.3571
1.4922	7.0	42	1.4385	0.2857
1.4922	8.0	48	1.2908	0.2619
1.2776	9.0	54	1.3088	0.5238
1.269	10.0	60	1.2412	0.3333
1.269	11.0	66	1.1676	0.5238
1.2132	12.0	72	1.1566	0.4286
1.2132	13.0	78	1.0746	0.5714
1.115	14.0	84	1.2329	0.4286
1.1413	15.0	90	1.1499	0.4048
1.1413	16.0	96	1.0494	0.5476
0.9563	17.0	102	0.9577	0.5238
0.9563	18.0	108	1.2486	0.4048
0.9343	19.0	114	1.2396	0.5238
0.8964	20.0	120	1.5448	0.3810
0.8964	21.0	126	1.6028	0.4762
0.826	22.0	132	1.0756	0.5714
0.826	23.0	138	1.4576	0.4048
0.6612	24.0	144	1.5635	0.4286
0.7361	25.0	150	1.2476	0.5952
0.7361	26.0	156	1.6591	0.4048
0.5674	27.0	162	1.5837	0.5238
0.5674	28.0	168	2.8490	0.4286
0.5637	29.0	174	1.9394	0.5714
0.4528	30.0	180	2.5319	0.4762
0.4528	31.0	186	1.8994	0.5714
0.455	32.0	192	2.3813	0.5476
0.455	33.0	198	2.3989	0.5
0.4317	34.0	204	2.5912	0.5
0.3921	35.0	210	2.8985	0.4762
0.3921	36.0	216	2.9682	0.5
0.3189	37.0	222	3.2291	0.5
0.3189	38.0	228	3.0818	0.5476
0.3067	39.0	234	3.1819	0.5238
0.2523	40.0	240	3.2200	0.4524
0.2523	41.0	246	3.2572	0.5
0.2633	42.0	252	3.2977	0.5
0.2633	43.0	258	3.2977	0.5
0.2304	44.0	264	3.2977	0.5
0.2585	45.0	270	3.2977	0.5
0.2585	46.0	276	3.2977	0.5
0.2417	47.0	282	3.2977	0.5
0.2417	48.0	288	3.2977	0.5
0.2307	49.0	294	3.2977	0.5
0.2495	50.0	300	3.2977	0.5

Framework versions

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