metadata

license: apache-2.0
base_model: distilbert-base-cased
tags:
  - generated_from_trainer
metrics:
  - accuracy
  - f1
model-index:
  - name: persuasive_essays_distilbert_cased
    results: []
language:
  - en

persuasive_essays_distilbert_cased

Model description

This model is a fine-tuned version of distilbert-base-cased on the emnlp2017-claim-identification/persuasive_essays dataset. It achieves the following results on the evaluation set:

Loss: 0.4249
Accuracy: 0.8101
Macro F1: 0.7662
Claim F1: 0.665

Intended uses & limitations

Text classification for claims on full sentences. The model perfoms better at in-domain classification. Cross-domain classification is severely limited.

Training and evaluation data

Based on Stab and Gurevych (2017) persuasive essays corpus, preprocessed by Daxenberger et al. (2017).

Original dataset

docs: 402
tokens: 147,271
total instances: 7,116 (65 duplicates)
- #claims: 2,108 (29.62%)

Trimmed datast used for training

total instances: 7051 (65 duplicates removed)
- #claims: 2093 (29.68%)
train/test split: 80/20, stratified

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 2e-05
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: 2
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Macro F1	Claim F1
No log	1.0	353	0.4369	0.7931	0.7574	0.6644
0.4492	2.0	706	0.4249	0.8101	0.7662	0.665

Framework versions

Transformers 4.37.2
Pytorch 2.2.0
Datasets 2.17.0
Tokenizers 0.15.2