<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
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}
}
