---
language:
- mn
license: bigscience-bloom-rail-1.0
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: bloom-NER-fr
  results: []
---

<!-- 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. -->

# bloom-NER-fr

This model is a fine-tuned version of [bigscience/bloom-560m](https://huggingface.co/bigscience/bloom-560m) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.3194
- Precision: 0.3970
- Recall: 0.5804
- F1: 0.4715
- Accuracy: 0.9283

## 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: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 6

### Training results

| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
| 1.0627        | 1.0   | 235  | 0.3106          | 0.2650    | 0.4111 | 0.3223 | 0.8957   |
| 0.3001        | 2.0   | 470  | 0.2626          | 0.3603    | 0.5418 | 0.4328 | 0.9145   |
| 0.2208        | 3.0   | 705  | 0.2848          | 0.3911    | 0.5569 | 0.4595 | 0.9178   |
| 0.1573        | 4.0   | 940  | 0.2904          | 0.3479    | 0.5336 | 0.4212 | 0.9149   |
| 0.1004        | 5.0   | 1175 | 0.2746          | 0.3884    | 0.5704 | 0.4621 | 0.9268   |
| 0.0594        | 6.0   | 1410 | 0.3194          | 0.3970    | 0.5804 | 0.4715 | 0.9283   |


### Framework versions

- Transformers 4.28.1
- Pytorch 2.0.0+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3