metadata

tags:
  - generated_from_trainer
metrics:
  - accuracy
model-index:
  - name: sentiment-polish-gpt2-small
    results: []
license: mit
language:
  - pl
datasets:
  - clarin-pl/polemo2-official

sentiment-polish-gpt2-small

This model was trained from scratch on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.4659
Accuracy: 0.9627

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

https://huggingface.co./datasets/clarin-pl/polemo2-official

@inproceedings{kocon-etal-2019-multi,
    title = "Multi-Level Sentiment Analysis of {P}ol{E}mo 2.0: Extended Corpus of Multi-Domain Consumer Reviews",
    author = "Koco{\'n}, Jan  and
      Mi{\l}kowski, Piotr  and
      Za{\'s}ko-Zieli{\'n}ska, Monika",
    booktitle = "Proceedings of the 23rd Conference on Computational Natural Language Learning (CoNLL)",
    month = nov,
    year = "2019",
    address = "Hong Kong, China",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/K19-1092",
    doi = "10.18653/v1/K19-1092",
    pages = "980--991",
    abstract = "In this article we present an extended version of PolEmo {--} a corpus of consumer reviews from 4 domains: medicine, hotels, products and school. Current version (PolEmo 2.0) contains 8,216 reviews having 57,466 sentences. Each text and sentence was manually annotated with sentiment in 2+1 scheme, which gives a total of 197,046 annotations. We obtained a high value of Positive Specific Agreement, which is 0.91 for texts and 0.88 for sentences. PolEmo 2.0 is publicly available under a Creative Commons copyright license. We explored recent deep learning approaches for the recognition of sentiment, such as Bi-directional Long Short-Term Memory (BiLSTM) and Bidirectional Encoder Representations from Transformers (BERT).",
}

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 2e-05
train_batch_size: 4
eval_batch_size: 4
seed: 42
gradient_accumulation_steps: 8
total_train_batch_size: 32
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	Accuracy
0.4049	1.0	3284	0.3351	0.8792
0.1885	2.0	6568	0.2625	0.9218
0.1182	3.0	9852	0.2583	0.9419
0.0825	4.0	13136	0.2886	0.9482
0.0586	5.0	16420	0.3343	0.9538
0.034	6.0	19704	0.3734	0.9595
0.0288	7.0	22988	0.4125	0.9599
0.0185	8.0	26273	0.4262	0.9626
0.0069	9.0	29557	0.4529	0.9622
0.0059	10.0	32840	0.4659	0.9627

Framework versions

Transformers 4.36.2
Pytorch 2.1.2+cu121
Datasets 2.16.1
Tokenizers 0.15.0