Instructions to use TransferGraph/mrm8488_codebert-base-finetuned-detect-insecure-code-finetuned-lora-tweet_eval_irony with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use TransferGraph/mrm8488_codebert-base-finetuned-detect-insecure-code-finetuned-lora-tweet_eval_irony with PEFT:
from peft import PeftModel from transformers import AutoModelForSequenceClassification base_model = AutoModelForSequenceClassification.from_pretrained("mrm8488/codebert-base-finetuned-detect-insecure-code") model = PeftModel.from_pretrained(base_model, "TransferGraph/mrm8488_codebert-base-finetuned-detect-insecure-code-finetuned-lora-tweet_eval_irony") - Notebooks
- Google Colab
- Kaggle
|
Download README.md from TransferGraph/mrm8488_codebert-base-finetuned-detect-insecure-code-finetuned-lora-tweet_eval_irony: direct link, hf CLI and curl.
- Browser
- Download file 2.09 kB
-
https://huggingface.co/TransferGraph/mrm8488_codebert-base-finetuned-detect-insecure-code-finetuned-lora-tweet_eval_irony/resolve/main/README.md
- Command line
-
hf download hf://TransferGraph/mrm8488_codebert-base-finetuned-detect-insecure-code-finetuned-lora-tweet_eval_irony/README.md
-
curl -L -o README.md https://huggingface.co/TransferGraph/mrm8488_codebert-base-finetuned-detect-insecure-code-finetuned-lora-tweet_eval_irony/resolve/main/README.md
2.09 kB
metadata
library_name: peft
tags:
- parquet
- text-classification
datasets:
- tweet_eval
metrics:
- accuracy
base_model: mrm8488/codebert-base-finetuned-detect-insecure-code
model-index:
- name: >-
mrm8488_codebert-base-finetuned-detect-insecure-code-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: 0.6774869109947644
name: accuracy
mrm8488_codebert-base-finetuned-detect-insecure-code-finetuned-lora-tweet_eval_irony
This model is a fine-tuned version of mrm8488/codebert-base-finetuned-detect-insecure-code on the tweet_eval dataset. It achieves the following results on the evaluation set:
- accuracy: 0.6775
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 |
|---|---|---|
| 0.4513 | None | 0 |
| 0.5958 | 0.7121 | 0 |
| 0.5853 | 0.6449 | 1 |
| 0.6513 | 0.6233 | 2 |
| 0.6639 | 0.5983 | 3 |
| 0.6670 | 0.5817 | 4 |
| 0.6073 | 0.5755 | 5 |
| 0.6723 | 0.5722 | 6 |
| 0.6775 | 0.5690 | 7 |
Framework versions
- PEFT 0.8.2
- Transformers 4.37.2
- Pytorch 2.2.0
- Datasets 2.16.1
- Tokenizers 0.15.2