Edit model card

msi-vit-small-1218-2

This model is a fine-tuned version of WinKawaks/vit-small-patch16-224 on the imagefolder dataset. It achieves the following results on the evaluation set:

  • Loss: 1.3372
  • Accuracy: 0.6164
  • F1: 0.3276
  • Precision: 0.6841
  • Recall: 0.2154

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-06
  • 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: 10

Training results

Training Loss Epoch Step Validation Loss Accuracy F1 Precision Recall
0.4367 1.0 1008 0.6603 0.6572 0.5313 0.6530 0.4478
0.2161 2.0 2016 0.8021 0.6329 0.4989 0.6118 0.4211
0.169 3.0 3024 1.4062 0.6010 0.2653 0.6592 0.1661
0.1543 4.0 4032 1.1498 0.6259 0.3670 0.6903 0.2499
0.1534 5.0 5040 1.5067 0.6208 0.3519 0.6808 0.2373
0.1596 6.0 6048 0.8837 0.6504 0.6505 0.5744 0.7498
0.1504 7.0 7056 1.0030 0.6302 0.4192 0.6580 0.3075
0.1795 8.0 8064 1.3908 0.5953 0.2950 0.6041 0.1952
0.1636 9.0 9072 1.1040 0.6290 0.4619 0.6230 0.3671
0.1629 10.0 10080 1.3372 0.6164 0.3276 0.6841 0.2154

Framework versions

  • Transformers 4.36.0
  • Pytorch 2.0.1+cu117
  • Datasets 2.15.0
  • Tokenizers 0.15.0
Downloads last month
5
Safetensors
Model size
21.7M params
Tensor type
F32
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for aaa12963337/msi-vit-small-1218-2

Finetuned
(13)
this model

Evaluation results