Downloads · 30 days
13
2% of all-time downloads
fias_NER
Ventalik/fias_NER
fias_NER is a token classification model from Ventalik. Use it when you need labels on individual words, such as names. It is set up for transformers. The card lists the license as mit.
should probably proofread and complete it, then remove this comment. --
All-time downloads
604
Public
Parameters
29.1M
3 GB on disk
Likes
1
Public
Repo makeup
Click a slice to open those files.
.bin116 MB · 49%
Parameter types
How the weights are stored.
F3229.1M · 100%
Try a prompt
Model card
From the Hugging Face model README
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
fias_NER
This model is a fine-tuned version of cointegrated/rubert-tiny2 on an unknown dataset. It achieves the following results on the evaluation set:
- eval_loss: 0.0011
- eval_precision: 0.9993
- eval_recall: 0.9994
- eval_f1: 0.9994
- eval_accuracy: 0.9996
- eval_runtime: 783.8012
- eval_samples_per_second: 2551.667
- eval_steps_per_second: 19.935
- epoch: 1.12
- step: 1200000
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: 128
- eval_batch_size: 128
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- training_steps: 2000000
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu117
- Datasets 2.13.0
- Tokenizers 0.13.3
- Task
- Token Classification
- Library
- transformers
- Type
- bert
- License
- mit
- Created
- Jun 18, 2023
- Updated
- Jun 28, 2023