lora_training
This model is a fine-tuned version of ykacer/bert-base-cased-imdb-sequence-classification on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.0969
- Accuracy: 0.5975
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: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.6038 | 1.0 | 800 | 1.5082 | 0.4547 |
| 1.305 | 2.0 | 1600 | 1.2096 | 0.5466 |
| 1.1727 | 3.0 | 2400 | 1.1352 | 0.5775 |
| 1.1199 | 4.0 | 3200 | 1.1062 | 0.5947 |
| 1.0959 | 5.0 | 4000 | 1.0969 | 0.5975 |
Framework versions
- PEFT 0.13.2
- Transformers 4.46.2
- Pytorch 2.5.0+cu121
- Datasets 3.1.0
- Tokenizers 0.20.3
- Downloads last month
- 58
Inference API (serverless) does not yet support peft models for this pipeline type.