metadata

library_name: transformers
base_model: Melo1512/vit-msn-small-beta-fia-manually-enhanced-HSV_test_2
tags:
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - accuracy
model-index:
  - name: vit-msn-small-beta-fia-manually-enhanced-HSV_test_3
    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: 0.8661971830985915

vit-msn-small-beta-fia-manually-enhanced-HSV_test_3

This model is a fine-tuned version of Melo1512/vit-msn-small-beta-fia-manually-enhanced-HSV_test_2 on the imagefolder dataset. It achieves the following results on the evaluation set:

Loss: 0.5321
Accuracy: 0.8662

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: 1e-05
train_batch_size: 64
eval_batch_size: 64
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 256
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.33
num_epochs: 50
label_smoothing_factor: 0.1

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	0.5714	1	0.5167	0.8803
No log	1.7143	3	0.5197	0.8803
No log	2.8571	5	0.5266	0.8803
No log	4.0	7	0.5391	0.8803
No log	4.5714	8	0.5425	0.8803
0.4435	5.7143	10	0.5403	0.8803
0.4435	6.8571	12	0.5251	0.8803
0.4435	8.0	14	0.5160	0.8732
0.4435	8.5714	15	0.5123	0.8873
0.4435	9.7143	17	0.5292	0.8803
0.4435	10.8571	19	0.5686	0.8732
0.4418	12.0	21	0.5460	0.8732
0.4418	12.5714	22	0.5333	0.8873
0.4418	13.7143	24	0.5152	0.8803
0.4418	14.8571	26	0.5236	0.8732
0.4418	16.0	28	0.5372	0.8592
0.4418	16.5714	29	0.5472	0.8592
0.4363	17.7143	31	0.5422	0.8592
0.4363	18.8571	33	0.5293	0.8803
0.4363	20.0	35	0.5235	0.8803
0.4363	20.5714	36	0.5240	0.8803
0.4363	21.7143	38	0.5302	0.8803
0.4371	22.8571	40	0.5324	0.8803
0.4371	24.0	42	0.5349	0.8803
0.4371	24.5714	43	0.5363	0.8732
0.4371	25.7143	45	0.5342	0.8732
0.4371	26.8571	47	0.5315	0.8732
0.4371	28.0	49	0.5319	0.8732
0.4298	28.5714	50	0.5321	0.8662

Framework versions

Transformers 4.44.2
Pytorch 2.4.1+cu121
Datasets 3.2.0
Tokenizers 0.19.1