metadata

base_model: MBZUAI/swiftformer-xs
tags:
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - accuracy
model-index:
  - name: swiftformer-xs-DMAE
    results:
      - task:
          name: Image Classification
          type: image-classification
        dataset:
          name: imagefolder
          type: imagefolder
          config: default
          split: validation
          args: default
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.717391304347826

swiftformer-xs-DMAE

This model is a fine-tuned version of MBZUAI/swiftformer-xs on the imagefolder dataset. It achieves the following results on the evaluation set:

Loss: 0.8398
Accuracy: 0.7174

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: 0.005
train_batch_size: 16
eval_batch_size: 16
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 64
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.1
num_epochs: 40

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	0.86	3	1.3706	0.5217
No log	2.0	7	1.1520	0.6304
1.2948	2.86	10	1.2934	0.6087
1.2948	4.0	14	1.2139	0.6304
1.2948	4.86	17	2.5946	0.5217
1.1888	6.0	21	1.1217	0.4783
1.1888	6.86	24	1.1050	0.5870
1.1888	8.0	28	1.6684	0.3913
1.1236	8.86	31	0.8968	0.6739
1.1236	10.0	35	1.2404	0.5652
1.1236	10.86	38	0.9957	0.6087
1.0477	12.0	42	1.1694	0.5
1.0477	12.86	45	0.9247	0.6957
1.0477	14.0	49	0.9464	0.6304
1.0264	14.86	52	0.8716	0.6087
1.0264	16.0	56	0.8909	0.6739
1.0264	16.86	59	0.8654	0.6739
0.909	18.0	63	0.9091	0.6087
0.909	18.86	66	0.8398	0.7174
0.8914	20.0	70	0.9393	0.6522
0.8914	20.86	73	0.9567	0.6739
0.8914	22.0	77	0.9479	0.6087
0.8573	22.86	80	0.9308	0.6739
0.8573	24.0	84	0.8986	0.6739
0.8573	24.86	87	0.9345	0.6739
0.8249	26.0	91	0.9843	0.6087
0.8249	26.86	94	0.9945	0.6087
0.8249	28.0	98	0.9493	0.5870
0.8307	28.86	101	0.9074	0.6739
0.8307	30.0	105	0.9497	0.6304
0.8307	30.86	108	0.9572	0.6087
0.7781	32.0	112	0.9732	0.6087
0.7781	32.86	115	0.9418	0.6304
0.7781	34.0	119	0.9533	0.6087
0.8104	34.29	120	0.9481	0.6087

Framework versions

Transformers 4.36.2
Pytorch 2.1.2+cu118
Datasets 2.16.1
Tokenizers 0.15.0