metadata

tags:
  - generated_from_trainer
datasets:
  - amazon_reviews_multi
widget:
  - text: >-
      me parece muy mal , se salía el producto por la caja y venían vacios , lo
      devolvere
  - text: >-
      Correa de buena calidad, con un interior oscuro. Cumple perfectamente su
      función y se intercambia fácilmente. Una buena opción para cambiar el
      aspecto del reloj
  - text: cumple su cometido sin nada que merezca la pena destacar
metrics:
  - accuracy
model-index:
  - name: electricidad-small-finetuned-amazon-review-classification
    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: 0.5832

electricidad-small-finetuned-amazon-review-classification

This model is a fine-tuned version of mrm8488/electricidad-small-discriminator on the amazon_reviews_multi dataset. It achieves the following results on the evaluation set:

Loss: 0.9506
Accuracy: 0.5832

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: 32
eval_batch_size: 32
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
1.0258	1.0	6250	1.0209	0.5502
0.9668	2.0	12500	0.9960	0.565
0.953	3.0	18750	0.9802	0.5704
0.9201	4.0	25000	0.9831	0.567
0.902	5.0	31250	0.9814	0.5672

Framework versions

Transformers 4.17.0
Pytorch 1.10.0+cu111
Datasets 1.18.4
Tokenizers 0.11.6