Gustave Cortal, Alain Finkel, Patrick Paroubek, Lina Ye. May 2023. Emotion Recognition based on Psychological Components in Guided Narratives for Emotion Regulation. In Proceedings of the 7th Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature, pages 72–81, Dubrovnik, Croatia. Association for Computational Linguistics.
distilcamembert-cae-all
This model is a fine-tuned version of cmarkea/distilcamembert-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.6016
- Precision: 0.8510
- Recall: 0.8481
- F1: 0.8471
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: 5e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 5.0
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 |
|---|---|---|---|---|---|---|
| 1.18 | 1.0 | 40 | 0.9901 | 0.6418 | 0.4557 | 0.2991 |
| 0.8718 | 2.0 | 80 | 0.6938 | 0.7667 | 0.7468 | 0.7196 |
| 0.4656 | 3.0 | 120 | 0.6928 | 0.8364 | 0.8354 | 0.8353 |
| 0.2418 | 4.0 | 160 | 0.6008 | 0.8276 | 0.8228 | 0.8228 |
| 0.1285 | 5.0 | 200 | 0.6016 | 0.8510 | 0.8481 | 0.8471 |
Framework versions
- Transformers 4.24.0
- Pytorch 1.12.1+cu113
- Datasets 2.7.1
- Tokenizers 0.13.2
- Downloads last month
- 4