metadata
base_model: klue/roberta-base
tags:
- generated_from_trainer
metrics:
- f1
- accuracy
model-index:
- name: aha_class_v1
results: []
aha_class_v1
This model is a fine-tuned version of klue/roberta-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0464
- F1: 0.99
- Roc Auc: 0.99
- Accuracy: 0.99
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
- num_epochs: 8
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 | Roc Auc | Accuracy |
|---|---|---|---|---|---|---|
| No log | 1.0 | 36 | 0.1850 | 0.9500 | 0.95 | 0.95 |
| No log | 2.0 | 72 | 0.1223 | 0.96 | 0.96 | 0.96 |
| No log | 3.0 | 108 | 0.0464 | 0.99 | 0.99 | 0.99 |
| No log | 4.0 | 144 | 0.0509 | 0.99 | 0.99 | 0.99 |
| No log | 5.0 | 180 | 0.0855 | 0.98 | 0.98 | 0.98 |
| No log | 6.0 | 216 | 0.0898 | 0.98 | 0.98 | 0.98 |
Framework versions
- Transformers 4.42.3
- Pytorch 2.3.0+cu121
- Datasets 2.18.0
- Tokenizers 0.19.1