metadata
license: cc-by-nc-sa-4.0
tags:
- generated_from_trainer
datasets:
- cord-layoutlmv3
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: layoutlmv3-finetuned-cord_vimal
results:
- task:
name: Token Classification
type: token-classification
dataset:
name: cord-layoutlmv3
type: cord-layoutlmv3
config: cord
split: test
args: cord
metrics:
- name: Precision
type: precision
value: 0.725
- name: Recall
type: recall
value: 0.7631578947368421
- name: F1
type: f1
value: 0.7435897435897436
- name: Accuracy
type: accuracy
value: 0.7407407407407407
layoutlmv3-finetuned-cord_vimal
This model is a fine-tuned version of microsoft/layoutlmv3-base on the cord-layoutlmv3 dataset. It achieves the following results on the evaluation set:
- Loss: 1.9129
- Precision: 0.725
- Recall: 0.7632
- F1: 0.7436
- Accuracy: 0.7407
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-05
- train_batch_size: 5
- eval_batch_size: 5
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- training_steps: 2500
Training results
Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
No log | 125.0 | 250 | 1.2365 | 0.7195 | 0.7763 | 0.7468 | 0.7556 |
0.8612 | 250.0 | 500 | 1.4859 | 0.7375 | 0.7763 | 0.7564 | 0.7481 |
0.8612 | 375.0 | 750 | 1.6108 | 0.725 | 0.7632 | 0.7436 | 0.7407 |
0.0297 | 500.0 | 1000 | 1.7046 | 0.725 | 0.7632 | 0.7436 | 0.7407 |
0.0297 | 625.0 | 1250 | 1.7805 | 0.725 | 0.7632 | 0.7436 | 0.7407 |
0.0134 | 750.0 | 1500 | 1.8187 | 0.725 | 0.7632 | 0.7436 | 0.7407 |
0.0134 | 875.0 | 1750 | 1.8624 | 0.725 | 0.7632 | 0.7436 | 0.7407 |
0.0089 | 1000.0 | 2000 | 1.8866 | 0.725 | 0.7632 | 0.7436 | 0.7407 |
0.0089 | 1125.0 | 2250 | 1.9056 | 0.725 | 0.7632 | 0.7436 | 0.7407 |
0.0073 | 1250.0 | 2500 | 1.9129 | 0.725 | 0.7632 | 0.7436 | 0.7407 |
Framework versions
- Transformers 4.26.0
- Pytorch 1.13.1+cu116
- Datasets 2.9.0
- Tokenizers 0.13.2