metadata

license: cc-by-nc-sa-4.0
tags:
  - generated_from_trainer
metrics:
  - precision
  - recall
  - f1
  - accuracy
model-index:
  - name: layoutlmv2-er-ner
    results: []

layoutlmv2-er-ner

This model is a fine-tuned version of renjithks/layoutlmv2-cord-ner on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.1780
Precision: 0.7176
Recall: 0.6953
F1: 0.7063
Accuracy: 0.9598

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: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
No log	1.0	22	0.5501	0.0	0.0	0.0	0.8801
No log	2.0	44	0.5444	0.0	0.0	0.0	0.8801
No log	3.0	66	0.5355	0.0	0.0	0.0	0.8801
No log	4.0	88	0.4321	0.1621	0.1171	0.1360	0.8671
No log	5.0	110	0.2968	0.5475	0.3738	0.4443	0.9329
No log	6.0	132	0.2926	0.5430	0.3117	0.3961	0.9256
No log	7.0	154	0.2200	0.5812	0.5402	0.5599	0.9452
No log	8.0	176	0.2156	0.6235	0.5021	0.5563	0.9480
No log	9.0	198	0.2202	0.5691	0.5924	0.5805	0.9464
No log	10.0	220	0.1934	0.6299	0.6361	0.6330	0.9537
No log	11.0	242	0.1860	0.6737	0.6756	0.6746	0.9549
No log	12.0	264	0.1840	0.7007	0.6770	0.6887	0.9596
No log	13.0	286	0.1925	0.6709	0.6756	0.6732	0.9579
No log	14.0	308	0.1763	0.7267	0.6939	0.7100	0.9604
No log	15.0	330	0.1850	0.7134	0.6671	0.6895	0.9577
No log	16.0	352	0.1771	0.6936	0.6897	0.6917	0.9587
No log	17.0	374	0.1767	0.7044	0.7024	0.7034	0.9592
No log	18.0	396	0.1739	0.7348	0.6996	0.7168	0.9610
No log	19.0	418	0.1778	0.7224	0.7010	0.7115	0.9600
No log	20.0	440	0.1780	0.7176	0.6953	0.7063	0.9598

Framework versions

Transformers 4.16.2
Pytorch 1.9.0+cu111
Datasets 1.18.4
Tokenizers 0.11.6