---
license: mit
base_model: roberta-base
tags:
- generated_from_trainer
datasets:
- fursov/gec_ner_val3
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: ner-gec-roberta-v3
  results:
  - task:
      name: Token Classification
      type: token-classification
    dataset:
      name: fursov/gec_ner_val3
      type: fursov/gec_ner_val3
    metrics:
    - name: Precision
      type: precision
      value: 0.5705440070765149
    - name: Recall
      type: recall
      value: 0.43481191856545776
    - name: F1
      type: f1
      value: 0.493515436703776
    - name: Accuracy
      type: accuracy
      value: 0.9566099116988466
---

<!-- 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. -->

# ner-gec-roberta-v3

This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on the fursov/gec_ner_val3 dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1759
- Precision: 0.5705
- Recall: 0.4348
- F1: 0.4935
- Accuracy: 0.9566

## 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: 128
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10.0

### Training results

| Training Loss | Epoch | Step | Accuracy | F1     | Validation Loss | Precision | Recall |
|:-------------:|:-----:|:----:|:--------:|:------:|:---------------:|:---------:|:------:|
| 0.2421        | 1.15  | 500  | 0.9349   | 0.0868 | 0.2389          | 0.1631    | 0.0591 |
| 0.2065        | 2.3   | 1000 | 0.9381   | 0.2139 | 0.2182          | 0.3006    | 0.1660 |
| 0.1729        | 3.46  | 1500 | 0.9446   | 0.3066 | 0.1986          | 0.4014    | 0.2480 |
| 0.1558        | 4.61  | 2000 | 0.9485   | 0.3556 | 0.1899          | 0.4544    | 0.2921 |
| 0.1546        | 5.76  | 2500 | 0.1857   | 0.4823 | 0.3191          | 0.3841    | 0.9504 |
| 0.1343        | 6.91  | 3000 | 0.1784   | 0.5302 | 0.3794          | 0.4423    | 0.9535 |
| 0.1163        | 8.06  | 3500 | 0.1767   | 0.5563 | 0.4094          | 0.4717    | 0.9556 |
| 0.1045        | 9.22  | 4000 | 0.1783   | 0.5595 | 0.4328          | 0.4880    | 0.9554 |


### Framework versions

- Transformers 4.36.2
- Pytorch 2.1.0+cu118
- Datasets 2.16.1
- Tokenizers 0.15.0