metadata

license: apache-2.0
tags:
  - generated_from_trainer
metrics:
  - rouge
model-index:
  - name: t5-base-DreamBank-Generation-Emot-EmotNn
    results: []
language:
  - en
widget:
  - text: >-
      I had a dream that Ben was in Costa Rica. I was really nervous about
      something, and he tried to make me feel better. Then Delia was in the
      library and had turned all the lights off. I was scared to lose my books
      since I had a paper due the next day.

t5-base-DreamBank-Generation-Emot-EmotNn

This model is a fine-tuned version of t5-base on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.3559
Rouge1: 0.8119
Rouge2: 0.2070
Rougel: 0.8102
Rougelsum: 0.8115

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: 0.0002
train_batch_size: 32
eval_batch_size: 32
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	24	0.5128	0.5154	0.0562	0.5072	0.5086
No log	2.0	48	0.3782	0.7132	0.0145	0.7127	0.7159
No log	3.0	72	0.3387	0.7872	0.1712	0.7745	0.7756
No log	4.0	96	0.3221	0.7804	0.1598	0.7754	0.7777
No log	5.0	120	0.3669	0.7453	0.1330	0.7403	0.7414
No log	6.0	144	0.3559	0.8119	0.2070	0.8102	0.8115
No log	7.0	168	0.3559	0.8047	0.1895	0.8036	0.8047
No log	8.0	192	0.3808	0.7967	0.1925	0.7934	0.7949
No log	9.0	216	0.3899	0.8047	0.2127	0.8030	0.8040
No log	10.0	240	0.3991	0.8096	0.2247	0.8068	0.8074

Framework versions

Transformers 4.25.1
Pytorch 1.12.1
Datasets 2.5.1
Tokenizers 0.12.1

Cite

If you use the model, please cite the pre-print.

@misc{https://doi.org/10.48550/arxiv.2302.14828,
  doi = {10.48550/ARXIV.2302.14828},
  url = {https://arxiv.org/abs/2302.14828},
  author = {Bertolini, Lorenzo and Elce, Valentina and Michalak, Adriana and Bernardi, Giulio and Weeds, Julie},
  keywords = {Computation and Language (cs.CL), FOS: Computer and information sciences, FOS: Computer and information sciences},
  title = {Automatic Scoring of Dream Reports' Emotional Content with Large Language Models},
  publisher = {arXiv},
  year = {2023},
  copyright = {Creative Commons Attribution 4.0 International}
}