metadata

license: mit
library_name: peft
tags:
  - parquet
  - text-classification
datasets:
  - tweet_eval
metrics:
  - accuracy
base_model: Guscode/DKbert-hatespeech-detection
model-index:
  - name: Guscode_DKbert-hatespeech-detection-finetuned-lora-tweet_eval_irony
    results:
      - task:
          type: text-classification
          name: Text Classification
        dataset:
          name: tweet_eval
          type: tweet_eval
          config: irony
          split: validation
          args: irony
        metrics:
          - type: accuracy
            value: 0.5853403141361256
            name: accuracy

Guscode_DKbert-hatespeech-detection-finetuned-lora-tweet_eval_irony

This model is a fine-tuned version of Guscode/DKbert-hatespeech-detection on the tweet_eval dataset. It achieves the following results on the evaluation set:

accuracy: 0.5853

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: 0.0005
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: 8

Training results

accuracy	train_loss	epoch
0.5204	None	0
0.5141	0.9783	0
0.5298	0.7023	1
0.5497	0.6822	2
0.5696	0.6676	3
0.5822	0.6534	4
0.5696	0.6453	5
0.5780	0.6443	6
0.5853	0.6387	7

Framework versions

PEFT 0.8.2
Transformers 4.37.2
Pytorch 2.2.0
Datasets 2.16.1
Tokenizers 0.15.2