|
--- |
|
license: apache-2.0 |
|
base_model: google-bert/bert-base-multilingual-cased |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
- f1 |
|
model-index: |
|
- name: SingPurcBERT-Katch-0329 |
|
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. --> |
|
|
|
# SingPurcBERT-Katch-0329 |
|
|
|
This model is a fine-tuned version of [google-bert/bert-base-multilingual-cased](https://huggingface.co/google-bert/bert-base-multilingual-cased) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.0660 |
|
- Accuracy: 0.8436 |
|
- F1: 0.8436 |
|
|
|
## 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: 8 |
|
- eval_batch_size: 8 |
|
- 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 | |
|
|:-------------:|:-----:|:-----:|:---------------:|:--------:|:------:| |
|
| 0.384 | 1.0 | 3372 | 0.3757 | 0.8450 | 0.8445 | |
|
| 0.3444 | 2.0 | 6744 | 0.3650 | 0.8583 | 0.8583 | |
|
| 0.3386 | 3.0 | 10116 | 0.4296 | 0.8593 | 0.8593 | |
|
| 0.3166 | 4.0 | 13488 | 0.5125 | 0.8460 | 0.8457 | |
|
| 0.2781 | 5.0 | 16860 | 0.7211 | 0.8504 | 0.8502 | |
|
| 0.2236 | 6.0 | 20232 | 0.7112 | 0.8504 | 0.8503 | |
|
| 0.2008 | 7.0 | 23604 | 0.8183 | 0.8509 | 0.8509 | |
|
| 0.1591 | 8.0 | 26976 | 0.9926 | 0.8464 | 0.8462 | |
|
| 0.1103 | 9.0 | 30348 | 1.0597 | 0.8411 | 0.8409 | |
|
| 0.0802 | 10.0 | 33720 | 1.0660 | 0.8436 | 0.8436 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.36.0.dev0 |
|
- Pytorch 2.0.0 |
|
- Datasets 2.14.5 |
|
- Tokenizers 0.14.1 |
|
|
