|
--- |
|
base_model: klue/roberta-large |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
- f1 |
|
- precision |
|
- recall |
|
model-index: |
|
- name: model_y3_research_1 |
|
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. --> |
|
|
|
# model_y3_research_1 |
|
|
|
This model is a fine-tuned version of [klue/roberta-large](https://huggingface.co/klue/roberta-large) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.9169 |
|
- Accuracy: 0.5979 |
|
- F1: 0.5435 |
|
- Precision: 0.5801 |
|
- Recall: 0.5487 |
|
|
|
## 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: 8 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_steps: 500 |
|
- num_epochs: 10 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:| |
|
| 0.9798 | 1.0 | 97 | 0.9334 | 0.5833 | 0.4128 | 0.4359 | 0.4577 | |
|
| 0.9489 | 2.0 | 194 | 0.9621 | 0.4792 | 0.2160 | 0.1597 | 0.3333 | |
|
| 0.9564 | 3.0 | 291 | 0.9505 | 0.5104 | 0.3456 | 0.3323 | 0.3764 | |
|
| 0.8319 | 4.0 | 388 | 0.8693 | 0.6458 | 0.5980 | 0.5970 | 0.6167 | |
|
| 0.7045 | 5.0 | 485 | 1.1875 | 0.5729 | 0.4888 | 0.5051 | 0.4891 | |
|
| 0.6337 | 6.0 | 582 | 1.7888 | 0.6042 | 0.4288 | 0.4648 | 0.4752 | |
|
| 0.3682 | 7.0 | 679 | 2.0383 | 0.5521 | 0.4904 | 0.4889 | 0.4967 | |
|
| 0.2195 | 8.0 | 776 | 2.3023 | 0.5625 | 0.4993 | 0.4986 | 0.5055 | |
|
| 0.0244 | 9.0 | 873 | 2.8742 | 0.5417 | 0.4650 | 0.4650 | 0.4674 | |
|
| 0.1459 | 10.0 | 970 | 2.9738 | 0.5521 | 0.4999 | 0.5001 | 0.5157 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.38.1 |
|
- Pytorch 2.2.1+cu121 |
|
- Datasets 2.17.1 |
|
- Tokenizers 0.15.2 |
|
|