Edit model card

clasificador-muchocine

This model is a fine-tuned version of mrm8488/electricidad-base-discriminator on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 1.3974
  • Accuracy: 0.4310

Model description

This model enables the classification of user movie reviews written in Spanish into 5 categories corresponding to the number of stars provided in the review (label_0 corresponds to 1 star and label_4 to 5 stars)

Intended uses & limitations

Please, note that this model has been trained with a Spanish dataset and may therefore not be suitable for classifying texts written in other languages. Also, note that the achieved accuracy in the evaluation tests is around 43%.

Training and evaluation data

The dataset employed was randomly divided for the following purposes: 80% training data - 20% test data.

Training procedure

The model has been trained following a 3-epoch cycle.

Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 5e-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: 3.0

Training results

Training Loss Epoch Step Validation Loss Accuracy
No log 1.0 388 1.3304 0.3948
1.4184 2.0 776 1.3010 0.4297
0.9847 3.0 1164 1.3974 0.4310

Framework versions

  • Transformers 4.35.2
  • Pytorch 2.1.0+cu121
  • Datasets 2.16.1
  • Tokenizers 0.15.1
Downloads last month
3
Safetensors
Model size
110M params
Tensor type
F32
·

Finetuned from