|
--- |
|
base_model: klue/roberta-large |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
- f1 |
|
model-index: |
|
- name: mango-32-0.00002-10-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-32-0.00002-10-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: 2.5883 |
|
- Accuracy: 0.6357 |
|
- F1: 0.6324 |
|
|
|
## 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: 64 |
|
- eval_batch_size: 64 |
|
- 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 | 233 | 1.7759 | 0.6095 | 0.6127 | |
|
| No log | 2.0 | 466 | 1.8463 | 0.6030 | 0.5997 | |
|
| 0.1567 | 3.0 | 699 | 1.8531 | 0.6297 | 0.6194 | |
|
| 0.1567 | 4.0 | 932 | 2.0262 | 0.6183 | 0.6180 | |
|
| 0.11 | 5.0 | 1165 | 2.1822 | 0.6167 | 0.6193 | |
|
| 0.11 | 6.0 | 1398 | 2.3360 | 0.6380 | 0.6294 | |
|
| 0.0622 | 7.0 | 1631 | 2.3473 | 0.6312 | 0.6286 | |
|
| 0.0622 | 8.0 | 1864 | 2.5031 | 0.6319 | 0.6283 | |
|
| 0.0294 | 9.0 | 2097 | 2.5552 | 0.6359 | 0.6315 | |
|
| 0.0294 | 10.0 | 2330 | 2.5883 | 0.6357 | 0.6324 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.34.1 |
|
- Pytorch 2.1.0a0+b5021ba |
|
- Datasets 2.6.2 |
|
- Tokenizers 0.14.1 |
|
|
