metadata
base_model: klue/roberta-small
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: mainCut-label9
results: []
mainCut-label9
This model is a fine-tuned version of klue/roberta-small on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.1075
- Accuracy: 0.6309
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
- num_epochs: 4
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.2286 | 0.4 | 500 | 1.2054 | 0.5685 |
| 1.2387 | 0.8 | 1000 | 1.1320 | 0.6062 |
| 0.9892 | 1.2 | 1500 | 1.1341 | 0.6169 |
| 1.1259 | 1.6 | 2000 | 1.1117 | 0.6202 |
| 0.9904 | 2.0 | 2500 | 1.0929 | 0.6262 |
| 1.0053 | 2.4 | 3000 | 1.1021 | 0.6243 |
| 0.9492 | 2.8 | 3500 | 1.0982 | 0.6251 |
| 0.9811 | 3.2 | 4000 | 1.1167 | 0.6238 |
| 0.9258 | 3.6 | 4500 | 1.1068 | 0.6341 |
| 0.8481 | 4.0 | 5000 | 1.1075 | 0.6309 |
Framework versions
- Transformers 4.32.1
- Pytorch 2.0.1
- Datasets 2.14.4
- Tokenizers 0.13.3