usami_distilbert-base-uncased-finetuned-cola-finetuned-lora-ag_news
This model is a fine-tuned version of usami/distilbert-base-uncased-finetuned-cola on the ag_news dataset. It achieves the following results on the evaluation set:
- accuracy: 0.9392
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 |
---|---|---|
0.2808 | None | 0 |
0.925 | 0.2544 | 0 |
0.9313 | 0.1957 | 1 |
0.9363 | 0.1737 | 2 |
0.9392 | 0.1581 | 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
- 0
Inference API (serverless) does not yet support peft models for this pipeline type.
Model tree for TransferGraph/usami_distilbert-base-uncased-finetuned-cola-finetuned-lora-ag_news
Base model
usami/distilbert-base-uncased-finetuned-cola