metadata

base_model: microsoft/dit-base-finetuned-rvlcdip
tags:
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - accuracy
model-index:
  - name: dit-base-rvlcdip-finetuned-grp-actual
    results:
      - task:
          name: Image Classification
          type: image-classification
        dataset:
          name: imagefolder
          type: imagefolder
          config: default
          split: train
          args: default
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.7575757575757576

dit-base-rvlcdip-finetuned-grp-actual

This model is a fine-tuned version of microsoft/dit-base-finetuned-rvlcdip on the imagefolder dataset. It achieves the following results on the evaluation set:

Loss: 1.3033
Accuracy: 0.7576

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: 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: 7

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
2.3577	0.96	18	2.0863	0.5114
2.0601	1.97	37	1.8154	0.6477
1.8068	2.99	56	1.5881	0.6705
1.5953	4.0	75	1.4112	0.7159
1.4304	4.96	93	1.3033	0.7576
1.3458	5.97	112	1.2401	0.75
1.3523	6.72	126	1.2240	0.7576

Framework versions

Transformers 4.32.0
Pytorch 2.0.1+cu118
Datasets 2.14.4
Tokenizers 0.13.3