metadata
tags:
- generated_from_trainer
datasets:
- rvl_cdip
metrics:
- accuracy
base_model: microsoft/dit-base-finetuned-rvlcdip
model-index:
- name: invoicevsadvertisement
results:
- task:
type: image-classification
name: Image Classification
dataset:
name: rvl_cdip
type: rvl_cdip
config: default
split: train
args: default
metrics:
- type: accuracy
value: 0.9892257579553997
name: Accuracy
invoicevsadvertisement
This model is a fine-tuned version of microsoft/dit-base-finetuned-rvlcdip on the rvl_cdip dataset. It achieves the following results on the evaluation set:
- Loss: 0.0292
- Accuracy: 0.9892
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: 192
- eval_batch_size: 192
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 768
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.4353 | 0.98 | 41 | 0.0758 | 0.9837 |
| 0.0542 | 1.98 | 82 | 0.0359 | 0.9860 |
| 0.0349 | 2.98 | 123 | 0.0336 | 0.9867 |
| 0.0323 | 3.98 | 164 | 0.0304 | 0.9876 |
| 0.0288 | 4.98 | 205 | 0.0292 | 0.9892 |
Framework versions
- Transformers 4.21.3
- Pytorch 1.12.1
- Datasets 2.3.2
- Tokenizers 0.12.1