metadata
base_model: klue/roberta-base
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: roberta-interview-intent-f
results: []
roberta-interview-intent-f
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: 1.9555
- Accuracy: 0.6763
- Macro F1: 0.4521
- Weighted F1: 0.6773
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: 5e-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: 8
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Macro F1 | Weighted F1 |
|---|---|---|---|---|---|---|
| 1.4857 | 1.0 | 859 | 1.4013 | 0.6564 | 0.3414 | 0.6440 |
| 0.6763 | 2.0 | 1718 | 1.3329 | 0.6673 | 0.4038 | 0.6551 |
| 0.4559 | 3.0 | 2577 | 1.4175 | 0.6654 | 0.4042 | 0.6653 |
| 0.2971 | 4.0 | 3436 | 1.5689 | 0.6622 | 0.4170 | 0.6637 |
| 0.1885 | 5.0 | 4295 | 1.6916 | 0.6656 | 0.4249 | 0.6694 |
| 0.1181 | 6.0 | 5154 | 1.8043 | 0.6763 | 0.4374 | 0.6713 |
| 0.0677 | 7.0 | 6013 | 1.9043 | 0.6736 | 0.4415 | 0.6756 |
| 0.0404 | 8.0 | 6872 | 1.9555 | 0.6763 | 0.4521 | 0.6773 |
Framework versions
- Transformers 4.40.2
- Pytorch 2.8.0+cu128
- Datasets 2.19.0
- Tokenizers 0.19.1