|
--- |
|
base_model: microsoft/dit-base-finetuned-rvlcdip |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- imagefolder |
|
metrics: |
|
- accuracy |
|
- recall |
|
- f1 |
|
- precision |
|
model-index: |
|
- name: dit-base-finetuned-rvlcdip-finetuned-ind-17-imbalanced-aadhaarmask |
|
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: 0.8458918688803746 |
|
- name: Recall |
|
type: recall |
|
value: 0.8458918688803746 |
|
- name: F1 |
|
type: f1 |
|
value: 0.8445087759723635 |
|
- name: Precision |
|
type: precision |
|
value: 0.8462519380607423 |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# dit-base-finetuned-rvlcdip-finetuned-ind-17-imbalanced-aadhaarmask |
|
|
|
This model is a fine-tuned version of [microsoft/dit-base-finetuned-rvlcdip](https://huggingface.co/microsoft/dit-base-finetuned-rvlcdip) on the imagefolder dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.3727 |
|
- Accuracy: 0.8459 |
|
- Recall: 0.8459 |
|
- F1: 0.8445 |
|
- Precision: 0.8463 |
|
|
|
## 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: 8 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 4 |
|
- total_train_batch_size: 32 |
|
- 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 | Recall | F1 | Precision | |
|
|:-------------:|:------:|:----:|:---------------:|:--------:|:------:|:------:|:---------:| |
|
| 0.9625 | 0.9974 | 293 | 0.8121 | 0.7812 | 0.7812 | 0.7600 | 0.7620 | |
|
| 0.7711 | 1.9983 | 587 | 0.5780 | 0.8135 | 0.8135 | 0.7960 | 0.7843 | |
|
| 0.555 | 2.9991 | 881 | 0.4868 | 0.8255 | 0.8255 | 0.8133 | 0.8133 | |
|
| 0.6008 | 4.0 | 1175 | 0.4475 | 0.8357 | 0.8357 | 0.8281 | 0.8253 | |
|
| 0.5318 | 4.9974 | 1468 | 0.4478 | 0.8267 | 0.8267 | 0.8221 | 0.8254 | |
|
| 0.3382 | 5.9983 | 1762 | 0.3946 | 0.8463 | 0.8463 | 0.8412 | 0.8427 | |
|
| 0.4307 | 6.9991 | 2056 | 0.4083 | 0.8344 | 0.8344 | 0.8317 | 0.8362 | |
|
| 0.4613 | 8.0 | 2350 | 0.3915 | 0.8442 | 0.8442 | 0.8429 | 0.8481 | |
|
| 0.3247 | 8.9974 | 2643 | 0.3758 | 0.8421 | 0.8421 | 0.8402 | 0.8395 | |
|
| 0.3965 | 9.9745 | 2930 | 0.3637 | 0.8484 | 0.8484 | 0.8466 | 0.8470 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.40.1 |
|
- Pytorch 2.2.0a0+81ea7a4 |
|
- Datasets 2.19.0 |
|
- Tokenizers 0.19.1 |
|
|
