Aureliano_distilbert-base-uncased-if-finetuned-lora-ag_news
This model is a fine-tuned version of Aureliano/distilbert-base-uncased-if on the ag_news dataset. It achieves the following results on the evaluation set:
- accuracy: 0.9407
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: 0.0004
- train_batch_size: 24
- eval_batch_size: 24
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4
Training results
| accuracy | train_loss | epoch |
|---|---|---|
| 0.2030 | None | 0 |
| 0.9254 | 0.2712 | 0 |
| 0.9308 | 0.2018 | 1 |
| 0.9371 | 0.1779 | 2 |
| 0.9407 | 0.1622 | 3 |
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
- 1
Inference API (serverless) does not yet support peft models for this pipeline type.
Model tree for TransferGraph/Aureliano_distilbert-base-uncased-if-finetuned-lora-ag_news
Base model
Aureliano/distilbert-base-uncased-if