Token Classification
Transformers
TensorBoard
Safetensors
layoutlmv3
Generated from Trainer
Eval Results (legacy)
Instructions to use mykh-med/test with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use mykh-med/test with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("token-classification", model="mykh-med/test")# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForTokenClassification processor = AutoProcessor.from_pretrained("mykh-med/test") model = AutoModelForTokenClassification.from_pretrained("mykh-med/test", device_map="auto") - Notebooks
- Google Colab
- Kaggle
|
Download README.md from mykh-med/test: direct link, hf CLI and curl.
- Browser
- Download file 3 kB
-
https://huggingface.co/mykh-med/test/resolve/main/README.md
- Command line
-
hf download hf://mykh-med/test/README.md
-
curl -L -o README.md https://huggingface.co/mykh-med/test/resolve/main/README.md
3 kB
metadata
library_name: transformers
license: cc-by-nc-sa-4.0
base_model: microsoft/layoutlmv3-base
tags:
- generated_from_trainer
datasets:
- layoutlmv3
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: test
results:
- task:
name: Token Classification
type: token-classification
dataset:
name: layoutlmv3
type: layoutlmv3
config: InvoiceExtraction
split: test
args: InvoiceExtraction
metrics:
- name: Precision
type: precision
value: 0.9735537190082645
- name: Recall
type: recall
value: 0.9751655629139073
- name: F1
type: f1
value: 0.9743589743589743
- name: Accuracy
type: accuracy
value: 0.9924257137308216
test
This model is a fine-tuned version of microsoft/layoutlmv3-base on the layoutlmv3 dataset. It achieves the following results on the evaluation set:
- Loss: 0.0899
- Precision: 0.9736
- Recall: 0.9752
- F1: 0.9744
- Accuracy: 0.9924
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: 2
- eval_batch_size: 2
- seed: 42
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- training_steps: 1000
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| No log | 0.5291 | 100 | 0.4956 | 0.7821 | 0.7724 | 0.7772 | 0.9413 |
| No log | 1.0582 | 200 | 0.1802 | 0.9285 | 0.9247 | 0.9266 | 0.9761 |
| No log | 1.5873 | 300 | 0.1465 | 0.9334 | 0.9512 | 0.9422 | 0.9841 |
| No log | 2.1164 | 400 | 0.1309 | 0.9447 | 0.9611 | 0.9528 | 0.9876 |
| 0.3392 | 2.6455 | 500 | 0.1095 | 0.9516 | 0.9594 | 0.9555 | 0.9891 |
| 0.3392 | 3.1746 | 600 | 0.1022 | 0.9573 | 0.9652 | 0.9613 | 0.9915 |
| 0.3392 | 3.7037 | 700 | 0.1081 | 0.9573 | 0.9661 | 0.9617 | 0.9918 |
| 0.3392 | 4.2328 | 800 | 0.0922 | 0.9726 | 0.9694 | 0.9710 | 0.9920 |
| 0.3392 | 4.7619 | 900 | 0.0930 | 0.9702 | 0.9702 | 0.9702 | 0.9916 |
| 0.0282 | 5.2910 | 1000 | 0.0899 | 0.9736 | 0.9752 | 0.9744 | 0.9924 |
Framework versions
- Transformers 4.47.0.dev0
- Pytorch 2.5.1+cu121
- Datasets 3.1.0
- Tokenizers 0.20.3