metadata

license: mit
base_model: Gladiator/microsoft-deberta-v3-large_ner_conll2003
tags:
  - generated_from_trainer
metrics:
  - precision
  - recall
  - f1
  - accuracy
model-index:
  - name: ner_tag_model
    results:
      - task:
          name: Token Classification
          type: token-classification
        metrics:
          - name: Precision
            type: precision
            value: 0.8568714588197879
          - name: Recall
            type: recall
            value: 0.8550538245045557
          - name: F1
            type: f1
            value: 0.8559616767268047
          - name: Accuracy
            type: accuracy
            value: 0.9150941588185013
language:
  - en
widget:
  - text: >-
      apparatus for models demonstrational for co ltd education and NON-WOVEN
      other BAG 902300000000 or unsuitable example intex for designed
      instruments SS011 uses industries in china 2020 intex purposes exhibitions
  - text: 62044200_IN Apparels india 620442000000 zimmermann zimmermann cotton of
  - text: >-
      nuts or or screws not other Adjusting diesel with and their china screw
      bolts washers dt 2.24061 whether 731815000000 technic
  - text: >-
      secret SHOP s canada victoria other 392690_CA ACCESSORIES victoria
      392690999999 secret FITTING s
  - text: >-
      HAC-30 68/550 germany in 730890200003 A.-Channel stores hilti F hilti
      431892

ner_tag_model

This model is a fine-tuned version of Gladiator/microsoft-deberta-v3-large_ner_conll2003 on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.1712
Precision: 0.8569
Recall: 0.8551
F1: 0.8560
Accuracy: 0.9151

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: 16
eval_batch_size: 16
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
0.2322	1.0	2495	0.1925	0.7990	0.7924	0.7957	0.8969
0.1674	2.0	4990	0.1488	0.8218	0.8316	0.8267	0.9116
0.1381	3.0	7485	0.1438	0.8204	0.8350	0.8276	0.9130
0.1284	4.0	9980	0.1381	0.8419	0.8405	0.8412	0.9148
0.1198	5.0	12475	0.1400	0.8280	0.8410	0.8345	0.9148
0.1155	6.0	14970	0.1395	0.8379	0.8467	0.8423	0.9154
0.1125	7.0	17465	0.1496	0.8438	0.8487	0.8462	0.9151
0.1068	8.0	19960	0.1510	0.8518	0.8529	0.8523	0.9156
0.1002	9.0	22455	0.1616	0.8536	0.8539	0.8537	0.9150
0.0964	10.0	24950	0.1712	0.8569	0.8551	0.8560	0.9151

Framework versions

Transformers 4.33.1
Pytorch 1.13.1+cu116
Datasets 2.14.5
Tokenizers 0.13.3