Shadowgraph
TrendingAbout
Sign in

gyr66/RoBERTa-ext-large-lora-chinese-finetuned-ner

Model

should probably proofread and complete it, then remove this comment. -->

0

3 commits

1 linked in READMEs

updated Jan 3, 2024

See the code

README

RoBERTa-ext-large-lora-chinese-finetuned-ner

This model is a fine-tuned version of hfl/chinese-roberta-wwm-ext-large on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 0.3762
  • Precision: 0.6284
  • Recall: 0.7311
  • F1: 0.6759
  • Accuracy: 0.9107

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: 0.001
  • 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 LossEpochStepValidation LossPrecisionRecallF1Accuracy
0.51121.02520.34400.50050.61050.55010.8940
0.2832.05040.31980.53630.67150.59630.9017
0.23733.07560.31040.55060.72160.62460.9054
0.19954.010080.32100.58040.72360.64410.9092
0.16785.012600.33000.58280.71400.64180.9077
0.14356.015120.32740.59120.71730.64820.9104
0.12067.017640.35660.59640.73510.65850.9079
0.1058.020160.35790.60650.72810.66180.9112
0.09259.022680.36450.61480.73820.67090.9103
0.083510.025200.37620.62840.73110.67590.9107

Framework versions

  • Transformers 4.35.2
  • Pytorch 2.1.0+cu121
  • Datasets 2.16.1
  • Tokenizers 0.15.0
generated_from_trainer
safetensors

Contributors

gyr66

3 commits

Similar repos

gyr66/RoBERTa-ext-large-crf-chinese-finetuned-ner-v2

Model

should probably proofread and complete it, then remove this comment. -->

1

gyr66/RoBERTa-ext-large-crf-chinese-finetuned-ner

Model

RoBERTa-ext-large-crf-chinese-finetuned-ner

0

gyr66/RoBERTa-ext-large-chinese-finetuned-ner

Model

RoBERTa-ext-large-chinese-finetuned-ner

0

gyr66/Ernie-3.0-large-chinese-finetuned-ner

Model

Ernie-3.0-large-chinese-finetuned-ner

0

gyr66/bert-base-chinese-finetuned-ner

Model

should probably proofread and complete it, then remove this comment. -->

8

joelito/legal-finnish-roberta-base

Model

should probably proofread and complete it, then remove this comment. -->

1

Pra-tham/results

Model

should probably proofread and complete it, then remove this comment. -->

0

joelito/legal-hungarian-roberta-base

Model

should probably proofread and complete it, then remove this comment. -->

0

Linked in READMEs

gyr66/privacy_detection

非结构化商业文本信息中隐私信息识别比赛代码仓库

22

README badge

gyr66/RoBERTa-ext-large-lora-chinese-finetuned-ner

Model

should probably proofread and complete it, then remove this comment. -->

0

3 commits

1 linked in READMEs

updated Jan 3, 2024

See the code

README

RoBERTa-ext-large-lora-chinese-finetuned-ner

This model is a fine-tuned version of hfl/chinese-roberta-wwm-ext-large on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 0.3762
  • Precision: 0.6284
  • Recall: 0.7311
  • F1: 0.6759
  • Accuracy: 0.9107

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: 0.001
  • 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 LossEpochStepValidation LossPrecisionRecallF1Accuracy
0.51121.02520.34400.50050.61050.55010.8940
0.2832.05040.31980.53630.67150.59630.9017
0.23733.07560.31040.55060.72160.62460.9054
0.19954.010080.32100.58040.72360.64410.9092
0.16785.012600.33000.58280.71400.64180.9077
0.14356.015120.32740.59120.71730.64820.9104
0.12067.017640.35660.59640.73510.65850.9079
0.1058.020160.35790.60650.72810.66180.9112
0.09259.022680.36450.61480.73820.67090.9103
0.083510.025200.37620.62840.73110.67590.9107

Framework versions

  • Transformers 4.35.2
  • Pytorch 2.1.0+cu121
  • Datasets 2.16.1
  • Tokenizers 0.15.0
generated_from_trainer
safetensors

Similar repos

gyr66/RoBERTa-ext-large-crf-chinese-finetuned-ner-v2

Model

should probably proofread and complete it, then remove this comment. -->

1

gyr66/RoBERTa-ext-large-crf-chinese-finetuned-ner

Model

RoBERTa-ext-large-crf-chinese-finetuned-ner

0

gyr66/RoBERTa-ext-large-chinese-finetuned-ner

Model

RoBERTa-ext-large-chinese-finetuned-ner

0

gyr66/Ernie-3.0-large-chinese-finetuned-ner

Model

Ernie-3.0-large-chinese-finetuned-ner

0

gyr66/bert-base-chinese-finetuned-ner

Model

should probably proofread and complete it, then remove this comment. -->

8

joelito/legal-finnish-roberta-base

Model

should probably proofread and complete it, then remove this comment. -->

1

Pra-tham/results

Model

should probably proofread and complete it, then remove this comment. -->

0

joelito/legal-hungarian-roberta-base

Model

should probably proofread and complete it, then remove this comment. -->

0

Linked in READMEs

gyr66/privacy_detection

非结构化商业文本信息中隐私信息识别比赛代码仓库

22

README badge

Contributors

gyr66

3 commits