metadata

tags:
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - accuracy
  - f1
  - precision
  - recall
model-index:
  - name: msi-resnet18
    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: 0.7618322547900013
          - name: F1
            type: f1
            value: 0.7033583563808773
          - name: Precision
            type: precision
            value: 0.7032472149798531
          - name: Recall
            type: recall
            value: 0.7034695329170948

msi-resnet18

This model was trained from scratch on the imagefolder dataset. It achieves the following results on the evaluation set:

Loss: 0.4869
Accuracy: 0.7618
F1: 0.7034
Precision: 0.7032
Recall: 0.7035

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-06
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: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Precision	Recall
0.6225	1.0	1970	0.6131	0.6718	0.5197	0.6298	0.4424
0.5749	2.0	3941	0.5577	0.7138	0.6061	0.6771	0.5486
0.5506	3.0	5911	0.5347	0.7355	0.6367	0.7096	0.5773
0.5304	4.0	7882	0.5114	0.7501	0.6615	0.7250	0.6082
0.5196	5.0	9852	0.5057	0.7503	0.6932	0.6838	0.7028
0.5125	6.0	11823	0.4920	0.7610	0.6983	0.7078	0.6890
0.5016	7.0	13793	0.4929	0.7578	0.7055	0.6890	0.7228
0.4871	8.0	15764	0.4796	0.7683	0.7042	0.7222	0.6870
0.5069	9.0	17734	0.4766	0.7743	0.6996	0.7512	0.6545
0.5059	10.0	19700	0.4869	0.7618	0.7034	0.7032	0.7035

Framework versions

Transformers 4.35.2
Pytorch 2.0.1+cu118
Datasets 2.15.0
Tokenizers 0.15.0