hilco's picture
Finished training.
4ede1ec verified
metadata
library_name: peft
tags:
  - parquet
  - text-classification
datasets:
  - tweet_eval
metrics:
  - accuracy
base_model: matthewburke/korean_sentiment
model-index:
  - name: matthewburke_korean_sentiment-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: 0.5905759162303665
            name: accuracy

matthewburke_korean_sentiment-finetuned-lora-tweet_eval_irony

This model is a fine-tuned version of matthewburke/korean_sentiment on the tweet_eval dataset. It achieves the following results on the evaluation set:

  • accuracy: 0.5906

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
0.4817 None 0
0.5832 0.6875 0
0.5623 0.6665 1
0.5675 0.6484 2
0.5623 0.6406 3
0.5665 0.6353 4
0.5592 0.6288 5
0.5686 0.6241 6
0.5906 0.6219 7

Framework versions

  • PEFT 0.8.2
  • Transformers 4.37.2
  • Pytorch 2.2.0
  • Datasets 2.16.1
  • Tokenizers 0.15.2