metadata
base_model: klue/roberta-base
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: roberta-intent-class-weighted
results: []
roberta-intent-class-weighted
This model is a fine-tuned version of klue/roberta-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.5616
- Accuracy: 0.6871
- Macro F1: 0.4540
- Weighted F1: 0.6864
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: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.06
- num_epochs: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Macro F1 | Weighted F1 |
|---|---|---|---|---|---|---|
| 1.8729 | 1.0 | 859 | 1.5736 | 0.6703 | 0.3479 | 0.6513 |
| 0.9142 | 2.0 | 1718 | 1.4981 | 0.6742 | 0.3999 | 0.6641 |
| 0.639 | 3.0 | 2577 | 1.4641 | 0.6863 | 0.4465 | 0.6852 |
| 0.4608 | 4.0 | 3436 | 1.5182 | 0.6853 | 0.4604 | 0.6834 |
| 0.3498 | 5.0 | 4295 | 1.5616 | 0.6871 | 0.4540 | 0.6864 |
Framework versions
- Transformers 4.40.2
- Pytorch 2.8.0+cu128
- Datasets 2.19.0
- Tokenizers 0.19.1