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_100
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: 0.9386094674556213
- name: Recall
type: recall
value: 0.9498502994011976
- name: F1
type: f1
value: 0.9441964285714285
- name: Accuracy
type: accuracy
value: 0.9562818336162988
layoutlmv3-finetuned-cord_100
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: 0.2039
- Precision: 0.9386
- Recall: 0.9499
- F1: 0.9442
- Accuracy: 0.9563
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 | 1.56 | 250 | 1.0093 | 0.7425 | 0.7964 | 0.7685 | 0.7984 |
1.3757 | 3.12 | 500 | 0.5393 | 0.8493 | 0.8735 | 0.8613 | 0.8816 |
1.3757 | 4.69 | 750 | 0.3774 | 0.8857 | 0.9049 | 0.8952 | 0.9160 |
0.3755 | 6.25 | 1000 | 0.2909 | 0.9153 | 0.9304 | 0.9228 | 0.9338 |
0.3755 | 7.81 | 1250 | 0.2511 | 0.9174 | 0.9311 | 0.9242 | 0.9393 |
0.1939 | 9.38 | 1500 | 0.2213 | 0.9385 | 0.9484 | 0.9434 | 0.9529 |
0.1939 | 10.94 | 1750 | 0.2176 | 0.9383 | 0.9454 | 0.9418 | 0.9525 |
0.1358 | 12.5 | 2000 | 0.2180 | 0.9314 | 0.9454 | 0.9383 | 0.9503 |
0.1358 | 14.06 | 2250 | 0.2057 | 0.9357 | 0.9484 | 0.9420 | 0.9546 |
0.1035 | 15.62 | 2500 | 0.2039 | 0.9386 | 0.9499 | 0.9442 | 0.9563 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.0
- Datasets 2.10.1
- Tokenizers 0.13.2