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: 0.8732394366197183

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: 0.5558
Accuracy: 0.8732

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: 0.15
num_epochs: 50
label_smoothing_factor: 0.1

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	0.5714	1	0.5123	0.8873
No log	1.7143	3	0.5495	0.8662
No log	2.8571	5	0.6080	0.8592
No log	4.0	7	0.5591	0.8732
No log	4.5714	8	0.5464	0.8732
0.4241	5.7143	10	0.5982	0.8451
0.4241	6.8571	12	0.6497	0.8169
0.4241	8.0	14	0.5928	0.8521
0.4241	8.5714	15	0.5711	0.8521
0.4241	9.7143	17	0.5468	0.8732
0.4241	10.8571	19	0.5483	0.8521
0.4152	12.0	21	0.5783	0.8451
0.4152	12.5714	22	0.5835	0.8451
0.4152	13.7143	24	0.5668	0.8451
0.4152	14.8571	26	0.5556	0.8451
0.4152	16.0	28	0.5564	0.8451
0.4152	16.5714	29	0.5591	0.8451
0.4367	17.7143	31	0.5619	0.8592
0.4367	18.8571	33	0.5809	0.8592
0.4367	20.0	35	0.5810	0.8662
0.4367	20.5714	36	0.5768	0.8662
0.4367	21.7143	38	0.5591	0.8732
0.4241	22.8571	40	0.5452	0.8732
0.4241	24.0	42	0.5387	0.8732
0.4241	24.5714	43	0.5398	0.8732
0.4241	25.7143	45	0.5458	0.8732
0.4241	26.8571	47	0.5509	0.8732
0.4241	28.0	49	0.5550	0.8732
0.4171	28.5714	50	0.5558	0.8732

Framework versions

Transformers 4.44.2
Pytorch 2.4.1+cu121
Datasets 3.2.0
Tokenizers 0.19.1