metadata
library_name: peft
license: apache-2.0
base_model: bert-base-uncased
tags:
- base_model:adapter:bert-base-uncased
- lora
- transformers
metrics:
- accuracy
- f1
model-index:
- name: imdb-lora-1.0
results: []
imdb-lora-1.0
This model is a fine-tuned version of bert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.2844
- Accuracy: 0.8846
- F1: 0.8845
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: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| 0.4492 | 1.0 | 391 | 0.3559 | 0.8495 | 0.8495 |
| 0.3118 | 2.0 | 782 | 0.2912 | 0.8807 | 0.8807 |
| 0.2929 | 3.0 | 1173 | 0.2844 | 0.8846 | 0.8845 |
Framework versions
- PEFT 0.18.0
- Transformers 4.57.3
- Pytorch 2.9.1+cu128
- Datasets 4.4.1
- Tokenizers 0.22.1