|
--- |
|
base_model: klue/roberta-large |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
- f1 |
|
model-index: |
|
- name: mango-16-0.00002-10-fin |
|
results: [] |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# mango-16-0.00002-10-fin |
|
|
|
This model is a fine-tuned version of [klue/roberta-large](https://huggingface.co/klue/roberta-large) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 3.0500 |
|
- Accuracy: 0.6357 |
|
- F1: 0.6333 |
|
|
|
## 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: 10 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:| |
|
| No log | 1.0 | 466 | 2.1468 | 0.6171 | 0.6168 | |
|
| 0.13 | 2.0 | 932 | 2.2649 | 0.6268 | 0.6204 | |
|
| 0.137 | 3.0 | 1398 | 2.1698 | 0.6254 | 0.6221 | |
|
| 0.1215 | 4.0 | 1864 | 2.1453 | 0.6265 | 0.6262 | |
|
| 0.1048 | 5.0 | 2330 | 2.4639 | 0.6205 | 0.6214 | |
|
| 0.0745 | 6.0 | 2796 | 2.7197 | 0.6341 | 0.6267 | |
|
| 0.0524 | 7.0 | 3262 | 2.8052 | 0.6317 | 0.6283 | |
|
| 0.0271 | 8.0 | 3728 | 2.9613 | 0.6297 | 0.6260 | |
|
| 0.0146 | 9.0 | 4194 | 3.0469 | 0.6292 | 0.6282 | |
|
| 0.0099 | 10.0 | 4660 | 3.0500 | 0.6357 | 0.6333 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.34.1 |
|
- Pytorch 2.1.0a0+b5021ba |
|
- Datasets 2.6.2 |
|
- Tokenizers 0.14.1 |
|
|
