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: 0.10869565217391304

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: 113.8184
Accuracy: 0.1087

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: 0.0003
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	113.8184	0.1087
No log	2.0	7	113.8094	0.1087
114.0867	2.86	10	113.7944	0.1087
114.0867	4.0	14	113.7881	0.1087
114.0867	4.86	17	113.7100	0.1087
113.3425	6.0	21	113.5884	0.1087
113.3425	6.86	24	113.4998	0.1087
113.3425	8.0	28	113.0578	0.1087
111.228	8.86	31	112.8053	0.1087
111.228	10.0	35	112.5202	0.1087
111.228	10.86	38	112.5811	0.1087
114.9647	12.0	42	112.6090	0.1087
114.9647	12.86	45	112.4973	0.1087
114.9647	14.0	49	111.9761	0.1087
110.7738	14.86	52	111.8117	0.1087
110.7738	16.0	56	111.6589	0.1087
110.7738	16.86	59	111.5367	0.1087
111.0505	18.0	63	111.7016	0.1087
111.0505	18.86	66	111.9068	0.1087
111.4545	20.0	70	111.6203	0.1087
111.4545	20.86	73	111.1266	0.1087
111.4545	22.0	77	110.2879	0.1087
111.2779	22.86	80	109.8523	0.1087
111.2779	24.0	84	109.5283	0.1087
111.2779	24.86	87	109.9590	0.1087
110.5166	26.0	91	109.9752	0.1087
110.5166	26.86	94	109.5435	0.1087
110.5166	28.0	98	109.5712	0.1087
108.66	28.86	101	108.8924	0.1087
108.66	30.0	105	108.3990	0.1087
108.66	30.86	108	108.7050	0.1087
109.688	32.0	112	108.7237	0.1087
109.688	32.86	115	109.0679	0.1087
109.688	34.0	119	108.5750	0.1087
109.4549	34.29	120	108.5167	0.1087

Framework versions

Transformers 4.36.2
Pytorch 2.1.2+cu118
Datasets 2.16.1
Tokenizers 0.15.0