metadata

license: apache-2.0
tags:
  - generated_from_trainer
  - relation-extraction
metrics:
  - rouge
model-index:
  - name: t5-base-DreamBank-Generation-Act-Char
    results: []
language:
  - en
inference:
  parameters:
    max_length: 128
widget:
  - text: >-
      I was skating on the outdoor ice pond that used to be across the street
      from my house. I was not alone, but I did not recognize any of the other
      people who were skating around. I went through my whole repertoire of
      jumps, spires, and steps-some of which I can do and some of which I'm not
      yet sure of. They were all executed flawlessly-some I repeated, some I did
      only once. I seemed to know that if I went into competition, I would be
      sure of coming in third because there were only three contestants. Up to
      that time I hadn't considered it because I hadn't thought I was good
      enough, but now since everything was going so well, I decided to enter.
    example_title: Dream 1
  - text: >-
      I was talking on the telephone to the father of an old friend of mine
      (boy, 21 years old). We were discussing the party the Saturday night
      before to which I had invited his son as a guest. I asked him if his son
      had a good time at the party. He told me not to tell his son that he had
      told me, but that he had had a good time, except he was a little surprised
      that I had acted the way I did.
    example_title: Dream 2
  - text: I was walking alone with my dog in a forest.
    example_title: Dream 3

t5-base-DreamBank-Generation-Act-Char

This model is a fine-tuned version of DReAMy-lib/t5-base-DreamBank-Generation-NER-Char on the DreamBank dataset. The uploaded model contains the weights of the best-performing model (see table below), tune to annotate a given dream report according to Hall and Van de Castle the Activity feature

Model description

The model is trained end-to-end using a text2text solution to annotate dream reports following the Activity feature from the Hall and Van de Castle scoring framework. Given a report, the model generates texts of the form (initialiser : activity type : receiver). For those cases where initialiser and receiver are the same entity, the output will follow the (initialiser : alone activity type : none) setting.

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 0.001
train_batch_size: 16
eval_batch_size: 16
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 10
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum
No log	1.0	49	0.3674	0.4008	0.3122	0.3821	0.3812
No log	2.0	98	0.3200	0.4240	0.3433	0.4130	0.4121
No log	3.0	147	0.2845	0.4591	0.3883	0.4459	0.4455
No log	4.0	196	0.2508	0.4614	0.3930	0.4504	0.4497
No log	5.0	245	0.2632	0.4614	0.3929	0.4467	0.4459
No log	6.0	294	0.2688	0.4706	0.4036	0.4537	0.4534
No log	7.0	343	0.2790	0.4682	0.4043	0.4559	0.4556
No log	8.0	392	0.2895	0.4670	0.3972	0.4529	0.4534
No log	9.0	441	0.3058	0.4708	0.4040	0.4576	0.4572
No log	10.0	490	0.3169	0.4690	0.4001	0.4547	0.4544

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}
}