metadata

license: mit
tags:
  - generated_from_trainer
metrics:
  - precision
  - recall
  - f1
  - accuracy
model-index:
  - name: deberta-v3-large-finetuned-ner-10epochs-V2
    results: []

deberta-v3-large-finetuned-ner-10epochs-V2

This model is a fine-tuned version of microsoft/deberta-v3-large on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.1180
Precision: 0.9033
Recall: 0.9347
F1: 0.9187
Accuracy: 0.9813

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: 2e-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
0.0663	1.0	2261	0.0715	0.8709	0.9194	0.8945	0.9787
0.0583	2.0	4522	0.0629	0.8845	0.9267	0.9051	0.9800
0.0442	3.0	6783	0.0635	0.8841	0.9404	0.9114	0.9802
0.0402	4.0	9044	0.0588	0.9011	0.9283	0.9145	0.9821
0.0327	5.0	11305	0.0676	0.8919	0.9385	0.9146	0.9818
0.0245	6.0	13566	0.0713	0.9037	0.9331	0.9182	0.9821
0.0183	7.0	15827	0.0848	0.9049	0.9181	0.9114	0.9812
0.0157	8.0	18088	0.0898	0.8957	0.9411	0.9178	0.9818
0.009	9.0	20349	0.1027	0.8965	0.9385	0.9170	0.9817
0.0068	10.0	22610	0.1180	0.9033	0.9347	0.9187	0.9813

Framework versions

Transformers 4.30.1
Pytorch 2.0.1+cu117
Datasets 2.12.0
Tokenizers 0.13.3