somosnlp-hackathon-2022/class-poems-es

classification-poems

This model is a fine-tuned version of BSC-TeMU/roberta-base-bne on the spanish Poems Dataset dataset. It achieves the following results on the evaluation set:

• Loss: 0.8228
• Accuracy: 0.7241

Model description

The model was trained to classify poems in Spanish, taking into account the content.

Training and evaluation data

The original dataset has the columns author, content, title, year and type of poem.

For each example, the type of poem it belongs to is identified. Then the model will recognize which type of poem the entered content belongs to.

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 2e-05
• train_batch_size: 2
• eval_batch_size: 2
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 2

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.9344	1.0	258	0.7505	0.7586
0.9239	2.0	516	0.8228	0.7241

Framework versions

• Transformers 4.17.0
• Pytorch 1.10.0+cu111
• Datasets 2.0.0
• Tokenizers 0.11.6