metadata
library_name: peft
tags:
- parquet
- text-classification
datasets:
- tweet_eval
metrics:
- accuracy
base_model: 18811449050/bert_finetuning_test
model-index:
- name: 18811449050_bert_finetuning_test-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: 0.6366492146596858
name: accuracy
18811449050_bert_finetuning_test-finetuned-lora-tweet_eval_irony
This model is a fine-tuned version of 18811449050/bert_finetuning_test on the tweet_eval dataset. It achieves the following results on the evaluation set:
- accuracy: 0.6366
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 |
|---|---|---|
| 0.5173 | None | 0 |
| 0.5717 | 0.6954 | 0 |
| 0.6 | 0.6572 | 1 |
| 0.6042 | 0.6240 | 2 |
| 0.6178 | 0.6022 | 3 |
| 0.6178 | 0.5898 | 4 |
| 0.6115 | 0.5757 | 5 |
| 0.6293 | 0.5588 | 6 |
| 0.6366 | 0.5573 | 7 |
Framework versions
- PEFT 0.8.2
- Transformers 4.37.2
- Pytorch 2.2.0
- Datasets 2.16.1
- Tokenizers 0.15.2