---
license: mit
tags:
- generated_from_trainer
datasets:
- amazon_reviews_multi
metrics:
- accuracy
- f1
- precision
- recall
model-index:
- name: multi-minilm-finetuned-amazon-review
  results:
  - task:
      name: Text Classification
      type: text-classification
    dataset:
      name: amazon_reviews_multi
      type: amazon_reviews_multi
      args: es
    metrics:
    - name: Accuracy
      type: accuracy
      value: 0.527
    - name: F1
      type: f1
      value: 0.5262492788715516
    - name: Precision
      type: precision
      value: 0.5266767693980432
    - name: Recall
      type: recall
      value: 0.527
---

<!-- 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. -->

# multi-minilm-finetuned-amazon-review

This model is a fine-tuned version of [microsoft/Multilingual-MiniLM-L12-H384](https://huggingface.co/microsoft/Multilingual-MiniLM-L12-H384) on the amazon_reviews_multi dataset.
It achieves the following results on the evaluation set:
- Loss: 1.1588
- Accuracy: 0.527
- F1: 0.5262
- Precision: 0.5267
- Recall: 0.527

## 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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     | Precision | Recall |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
| 1.3182        | 0.4   | 500  | 1.1930          | 0.4684   | 0.4325 | 0.4439    | 0.4684 |
| 1.1715        | 0.8   | 1000 | 1.1570          | 0.4782   | 0.4639 | 0.4629    | 0.4782 |
| 1.0959        | 1.2   | 1500 | 1.1253          | 0.4976   | 0.4962 | 0.5008    | 0.4976 |
| 1.0682        | 1.6   | 2000 | 1.0928          | 0.5128   | 0.5080 | 0.5094    | 0.5128 |
| 1.0272        | 2.0   | 2500 | 1.0936          | 0.5144   | 0.5120 | 0.5138    | 0.5144 |
| 0.956         | 2.4   | 3000 | 1.1047          | 0.5228   | 0.5179 | 0.5159    | 0.5228 |
| 0.9539        | 2.8   | 3500 | 1.0970          | 0.5236   | 0.5211 | 0.5194    | 0.5236 |
| 0.9064        | 3.2   | 4000 | 1.1232          | 0.5278   | 0.5238 | 0.5259    | 0.5278 |
| 0.8595        | 3.6   | 4500 | 1.1256          | 0.5296   | 0.5286 | 0.5313    | 0.5296 |
| 0.8731        | 4.0   | 5000 | 1.1400          | 0.5296   | 0.5238 | 0.5228    | 0.5296 |
| 0.7876        | 4.4   | 5500 | 1.1518          | 0.5244   | 0.5271 | 0.5314    | 0.5244 |
| 0.7959        | 4.8   | 6000 | 1.1588          | 0.527    | 0.5262 | 0.5267    | 0.527  |


### Framework versions

- Transformers 4.15.0
- Pytorch 1.10.0+cu111
- Datasets 1.17.0
- Tokenizers 0.10.3