---
base_model: imvladikon/alephbertgimmel-base-512
tags:
- generated_from_trainer
datasets:
- nemo_corpus
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: aleph_bert_gimmel-finetuned-ner
  results:
  - task:
      name: Token Classification
      type: token-classification
    dataset:
      name: nemo_corpus
      type: nemo_corpus
      config: flat_token
      split: validation
      args: flat_token
    metrics:
    - name: Precision
      type: precision
      value: 0.8048128342245989
    - name: Recall
      type: recall
      value: 0.8058902275769746
    - name: F1
      type: f1
      value: 0.8053511705685619
    - name: Accuracy
      type: accuracy
      value: 0.9723507148864592
---

<!-- 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. -->

# aleph_bert_gimmel-finetuned-ner

This model is a fine-tuned version of [imvladikon/alephbertgimmel-base-512](https://huggingface.co/imvladikon/alephbertgimmel-base-512) on the nemo_corpus dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1231
- Precision: 0.8048
- Recall: 0.8059
- F1: 0.8054
- Accuracy: 0.9724

## 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: 3

### Training results

| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
| 0.375         | 1.0   | 618  | 0.1505          | 0.7767    | 0.7590 | 0.7678 | 0.9660   |
| 0.1377        | 2.0   | 1236 | 0.1240          | 0.8188    | 0.8046 | 0.8116 | 0.9720   |
| 0.0967        | 3.0   | 1854 | 0.1231          | 0.8048    | 0.8059 | 0.8054 | 0.9724   |


### Framework versions

- Transformers 4.35.2
- Pytorch 2.0.1+cpu
- Datasets 2.15.0
- Tokenizers 0.15.0