hilco's picture
Finished training.
f38a31d verified
---
library_name: peft
tags:
- parquet
- text-classification
datasets:
- tweet_eval
metrics:
- accuracy
base_model: connectivity/cola_6ep_ft-33
model-index:
- name: connectivity_cola_6ep_ft-33-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: 0.6418848167539267
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. -->
# connectivity_cola_6ep_ft-33-finetuned-lora-tweet_eval_irony
This model is a fine-tuned version of [connectivity/cola_6ep_ft-33](https://huggingface.co/connectivity/cola_6ep_ft-33) on the tweet_eval dataset.
It achieves the following results on the evaluation set:
- accuracy: 0.6419
## 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 |
|:--------:|:----------:|:-----:|
| 0.4942 | None | 0 |
| 0.5508 | 0.7507 | 0 |
| 0.5728 | 0.6699 | 1 |
| 0.5979 | 0.6398 | 2 |
| 0.6199 | 0.6192 | 3 |
| 0.6178 | 0.5931 | 4 |
| 0.6293 | 0.5765 | 5 |
| 0.6398 | 0.5584 | 6 |
| 0.6419 | 0.5531 | 7 |
### Framework versions
- PEFT 0.8.2
- Transformers 4.37.2
- Pytorch 2.2.0
- Datasets 2.16.1
- Tokenizers 0.15.2