sandromck's picture
End of training
8376ac2
metadata
license: cc-by-sa-4.0
base_model: classla/xlm-roberta-base-multilingual-text-genre-classifier
tags:
  - generated_from_trainer
metrics:
  - accuracy
model-index:
  - name: movie-genre-predictions
    results: []

movie-genre-predictions

This model is a fine-tuned version of classla/xlm-roberta-base-multilingual-text-genre-classifier on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 1.8254
  • Accuracy: 0.4039

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: 1e-05
  • train_batch_size: 64
  • eval_batch_size: 64
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 15

Training results

Training Loss Epoch Step Validation Loss Accuracy
2.0066 1.0 580 1.7868 0.3721
1.776 2.0 1160 1.7651 0.3909
1.686 3.0 1740 1.6970 0.4086
1.6282 4.0 2320 1.6960 0.4098
1.5714 5.0 2900 1.6749 0.4137
1.516 6.0 3480 1.6763 0.4142
1.4244 7.0 4060 1.7029 0.4159
1.3822 8.0 4640 1.7114 0.4143
1.3422 9.0 5220 1.7400 0.4131
1.3099 10.0 5800 1.7681 0.4084
1.2757 11.0 6380 1.7830 0.4049
1.2489 12.0 6960 1.7978 0.4050
1.2039 13.0 7540 1.8142 0.4058
1.1839 14.0 8120 1.8243 0.4044
1.1641 15.0 8700 1.8254 0.4039

Framework versions

  • Transformers 4.34.0
  • Pytorch 2.0.1+cu118
  • Datasets 2.14.5
  • Tokenizers 0.14.1