|
--- |
|
library_name: peft |
|
tags: |
|
- parquet |
|
- text-classification |
|
datasets: |
|
- tweet_eval |
|
metrics: |
|
- accuracy |
|
base_model: Jeevesh8/init_bert_ft_qqp-24 |
|
model-index: |
|
- name: Jeevesh8_init_bert_ft_qqp-24-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: 0.625130890052356 |
|
name: accuracy |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# Jeevesh8_init_bert_ft_qqp-24-finetuned-lora-tweet_eval_irony |
|
|
|
This model is a fine-tuned version of [Jeevesh8/init_bert_ft_qqp-24](https://huggingface.co/Jeevesh8/init_bert_ft_qqp-24) on the tweet_eval dataset. |
|
It achieves the following results on the evaluation set: |
|
- accuracy: 0.6251 |
|
|
|
## 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 | |
|
|:--------:|:----------:|:-----:| |
|
| 0.5183 | None | 0 | |
|
| 0.4942 | 0.7904 | 0 | |
|
| 0.5414 | 0.6875 | 1 | |
|
| 0.5812 | 0.6643 | 2 | |
|
| 0.5874 | 0.6493 | 3 | |
|
| 0.6042 | 0.6377 | 4 | |
|
| 0.6168 | 0.6315 | 5 | |
|
| 0.6188 | 0.6216 | 6 | |
|
| 0.6251 | 0.6119 | 7 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.8.2 |
|
- Transformers 4.37.2 |
|
- Pytorch 2.2.0 |
|
- Datasets 2.16.1 |
|
- Tokenizers 0.15.2 |
