ishan_bert-base-uncased-mnli-finetuned-lora-tweet_eval_irony
This model is a fine-tuned version of ishan/bert-base-uncased-mnli on the tweet_eval dataset. It achieves the following results on the evaluation set:
- accuracy: 0.6921
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 |
---|---|---|
0.4607 | None | 0 |
0.5927 | 0.6880 | 0 |
0.6168 | 0.6484 | 1 |
0.6524 | 0.6051 | 2 |
0.6628 | 0.5782 | 3 |
0.6723 | 0.5502 | 4 |
0.6859 | 0.5350 | 5 |
0.6806 | 0.5306 | 6 |
0.6921 | 0.5219 | 7 |
Framework versions
- PEFT 0.8.2
- Transformers 4.37.2
- Pytorch 2.2.0
- Datasets 2.16.1
- Tokenizers 0.15.2
- Downloads last month
- 2
Inference API (serverless) does not yet support peft models for this pipeline type.
Model tree for TransferGraph/ishan_bert-base-uncased-mnli-finetuned-lora-tweet_eval_irony
Base model
ishan/bert-base-uncased-mnli
Adapter
this model
Dataset used to train TransferGraph/ishan_bert-base-uncased-mnli-finetuned-lora-tweet_eval_irony
Evaluation results
- accuracy on tweet_evalvalidation set self-reported0.692