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