connectivity_bert_ft_qqp-94-finetuned-lora-tweet_eval_irony
This model is a fine-tuned version of connectivity/bert_ft_qqp-94 on the tweet_eval dataset.
It achieves the following results on the evaluation set:
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 |
0.5194 |
None |
0 |
0.5225 |
0.9509 |
0 |
0.5267 |
0.7006 |
1 |
0.5539 |
0.6894 |
2 |
0.5686 |
0.6797 |
3 |
0.5958 |
0.6546 |
4 |
0.6021 |
0.6307 |
5 |
0.6157 |
0.6177 |
6 |
0.6304 |
0.6106 |
7 |
Framework versions
- PEFT 0.8.2
- Transformers 4.37.2
- Pytorch 2.2.0
- Datasets 2.16.1
- Tokenizers 0.15.2