metadata
library_name: peft
license: mit
base_model: roberta-base
tags:
- base_model:adapter:roberta-base
- lora
- transformers
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: roberta-base-category-classifier
results: []
roberta-base-category-classifier
This model is a fine-tuned version of roberta-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1074
- Accuracy: 0.9717
- Precision: 0.9715
- Recall: 0.9717
- F1: 0.9715
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 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 | Precision | Recall | F1 |
|---|---|---|---|---|---|---|---|
| 0.2522 | 1.0 | 1342 | 0.1409 | 0.9594 | 0.9592 | 0.9594 | 0.9589 |
| 0.1339 | 2.0 | 2684 | 0.1094 | 0.9709 | 0.9707 | 0.9709 | 0.9707 |
| 0.1098 | 3.0 | 4026 | 0.1074 | 0.9717 | 0.9715 | 0.9717 | 0.9715 |
Framework versions
- PEFT 0.17.1
- Transformers 4.55.4
- Pytorch 2.8.0+cu126
- Datasets 4.0.0
- Tokenizers 0.21.4