metadata

license: mit
tags:
  - generated_from_trainer
metrics:
  - f1
  - accuracy
model-index:
  - name: xlm-roberta-large-DreamBank
    results: []
widget:
  - text: >-
      I dreamed that Hannah and Sue and I travelled back in time to meet her
      parents. Weird.
pipeline_tag: text-classification

xlm-roberta-large-DreamBank

This model is a fine-tuned version of xlm-roberta-large on the None dataset. It achieves the following results on the evaluation set: Best result (loaded model)

F1: 0.8621

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: 4
eval_batch_size: 4
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	F1	Roc Auc	Accuracy
No log	1.0	185	0.5949	0.0	0.5	0.0
No log	2.0	370	0.3825	0.6052	0.7481	0.4595
0.476	3.0	555	0.2891	0.7403	0.8010	0.5730
0.476	4.0	740	0.2604	0.8425	0.8852	0.7081
0.476	5.0	925	0.2484	0.8504	0.8932	0.6649
0.1457	6.0	1110	0.3092	0.8352	0.8909	0.6703
0.1457	7.0	1295	0.2882	0.8546	0.8950	0.6919
0.1457	8.0	1480	0.3099	0.8549	0.9014	0.6865
0.0691	9.0	1665	0.3080	0.8548	0.9019	0.6811
0.0691	10.0	1850	0.2942	0.8621	0.9069	0.6973

Framework versions

Transformers 4.25.1
Pytorch 1.12.1
Datasets 2.5.1
Tokenizers 0.12.1

Cite

Should use our models in your work, please consider citing us as:

@article{BERTOLINI2024406,
title = {DReAMy: a library for the automatic analysis and annotation of dream reports with multilingual large language models},
journal = {Sleep Medicine},
volume = {115},
pages = {406-407},
year = {2024},
note = {Abstracts from the 17th World Sleep Congress},
issn = {1389-9457},
doi = {https://doi.org/10.1016/j.sleep.2023.11.1092},
url = {https://www.sciencedirect.com/science/article/pii/S1389945723015186},
author = {L. Bertolini and A. Michalak and J. Weeds}
}