README.md

metadata

tags:
  - generated_from_trainer
metrics:
  - precision
  - recall
  - f1
  - accuracy
model-index:
  - name: layoutlmv3-er-ner
    results: []

layoutlmv3-er-ner

This model is a fine-tuned version of renjithks/layoutlmv3-cord-ner on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.1788
• Precision: 0.6612
• Recall: 0.6789
• F1: 0.6699
• Accuracy: 0.9549

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
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
No log	1.0	22	0.3892	0.0	0.0	0.0	0.8793
No log	2.0	44	0.2854	0.3343	0.3352	0.3347	0.8956
No log	3.0	66	0.2085	0.5692	0.5233	0.5453	0.9388
No log	4.0	88	0.1785	0.5556	0.6153	0.5839	0.9426
No log	5.0	110	0.1853	0.5769	0.6365	0.6052	0.9455
No log	6.0	132	0.1593	0.6592	0.6676	0.6634	0.9539
No log	7.0	154	0.1684	0.6676	0.6506	0.6590	0.9529
No log	8.0	176	0.1759	0.6443	0.6506	0.6474	0.9537
No log	9.0	198	0.1740	0.6607	0.6832	0.6718	0.9555
No log	10.0	220	0.1788	0.6612	0.6789	0.6699	0.9549

Framework versions

• Transformers 4.20.0.dev0
• Pytorch 1.11.0
• Datasets 2.1.0
• Tokenizers 0.12.1