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: beit-base-patch16-224-hasta-55-fold2
    results:
      - task:
          name: Image Classification
          type: image-classification
        dataset:
          name: imagefolder
          type: imagefolder
          config: default
          split: train
          args: default
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.6944444444444444

beit-base-patch16-224-hasta-55-fold2

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: 1.0368
• Accuracy: 0.6944

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: 5e-05
• train_batch_size: 32
• eval_batch_size: 32
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 128
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 100

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	0.5714	1	1.1041	0.3611
No log	1.7143	3	1.1063	0.4167
No log	2.8571	5	1.1169	0.4722
No log	4.0	7	1.0613	0.4444
No log	4.5714	8	1.0637	0.4167
1.0693	5.7143	10	1.0546	0.5
1.0693	6.8571	12	1.1360	0.3611
1.0693	8.0	14	1.0112	0.5
1.0693	8.5714	15	0.9729	0.5833
1.0693	9.7143	17	1.0749	0.4722
1.0693	10.8571	19	0.9543	0.5
0.8719	12.0	21	1.1289	0.3889
0.8719	12.5714	22	1.0727	0.5556
0.8719	13.7143	24	0.9727	0.6389
0.8719	14.8571	26	0.9647	0.6389
0.8719	16.0	28	0.9078	0.6111
0.8719	16.5714	29	0.9656	0.5833
0.7623	17.7143	31	0.9226	0.6111
0.7623	18.8571	33	0.9612	0.6667
0.7623	20.0	35	1.0379	0.5
0.7623	20.5714	36	0.9974	0.6111
0.7623	21.7143	38	0.9710	0.6667
0.6453	22.8571	40	1.0150	0.6667
0.6453	24.0	42	0.9738	0.6111
0.6453	24.5714	43	1.0280	0.6389
0.6453	25.7143	45	1.0642	0.6111
0.6453	26.8571	47	1.0238	0.5278
0.6453	28.0	49	1.0699	0.5556
0.5475	28.5714	50	1.1394	0.5278
0.5475	29.7143	52	0.9907	0.6111
0.5475	30.8571	54	1.0205	0.6111
0.5475	32.0	56	0.9423	0.6389
0.5475	32.5714	57	0.9201	0.6389
0.5475	33.7143	59	0.9101	0.6667
0.546	34.8571	61	0.9030	0.6111
0.546	36.0	63	0.9390	0.6111
0.546	36.5714	64	0.9516	0.6111
0.546	37.7143	66	0.9317	0.6667
0.546	38.8571	68	1.0006	0.6389
0.4129	40.0	70	1.0144	0.5556
0.4129	40.5714	71	1.0585	0.5833
0.4129	41.7143	73	1.0727	0.6111
0.4129	42.8571	75	1.0666	0.6389
0.4129	44.0	77	1.0368	0.6944
0.4129	44.5714	78	1.0238	0.6389
0.3913	45.7143	80	1.0247	0.6389
0.3913	46.8571	82	1.0485	0.6111
0.3913	48.0	84	1.0710	0.6389
0.3913	48.5714	85	1.0899	0.6111
0.3913	49.7143	87	1.0756	0.6389
0.3913	50.8571	89	1.0665	0.6389
0.3324	52.0	91	1.0853	0.6111
0.3324	52.5714	92	1.0898	0.6111
0.3324	53.7143	94	1.0802	0.6111
0.3324	54.8571	96	1.0720	0.6389
0.3324	56.0	98	1.0649	0.6389
0.3324	56.5714	99	1.0634	0.6389
0.3117	57.1429	100	1.0629	0.6389

Framework versions

• Transformers 4.41.0
• Pytorch 2.3.0+cu121
• Datasets 2.19.1
• Tokenizers 0.19.1