metadata

license: apache-2.0
base_model: microsoft/resnet-18
tags:
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - accuracy
model-index:
  - name: font-identifier
    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: 0.9040816326530612

font-identifier

This model is a fine-tuned version of microsoft/resnet-18 on the imagefolder dataset. It achieves the following results on the evaluation set:

Loss: 0.3626
Accuracy: 0.9041

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-05
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: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
3.929	0.98	30	3.8215	0.0429
3.2162	1.98	61	2.9144	0.2816
2.4387	2.99	92	2.1019	0.4776
1.9404	4.0	123	1.5607	0.6041
1.5756	4.98	153	1.3012	0.6449
1.3374	5.98	184	1.0699	0.7102
1.1912	6.99	215	0.9145	0.7633
1.0716	8.0	246	0.7864	0.7898
0.9751	8.98	276	0.6894	0.8204
0.8211	9.98	307	0.6256	0.8510
0.8254	10.99	338	0.5563	0.8633
0.742	12.0	369	0.5149	0.8694
0.6949	12.98	399	0.4625	0.8878
0.6401	13.98	430	0.4799	0.8857
0.6304	14.99	461	0.3970	0.8980
0.6239	16.0	492	0.4016	0.9
0.5911	16.98	522	0.4271	0.8755
0.5764	17.98	553	0.3922	0.9
0.5461	18.99	584	0.3750	0.9
0.6236	19.51	600	0.3626	0.9041

Framework versions

Transformers 4.36.0.dev0
Pytorch 2.0.0
Datasets 2.12.0
Tokenizers 0.14.1