|
--- |
|
license: apache-2.0 |
|
base_model: google-bert/bert-base-multilingual-cased |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
- f1 |
|
model-index: |
|
- name: ConcPurcBERT-Katch-0329-v2 |
|
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. --> |
|
|
|
# ConcPurcBERT-Katch-0329-v2 |
|
|
|
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: 0.4808 |
|
- Accuracy: 0.7855 |
|
- F1: 0.7854 |
|
|
|
## 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 | |
|
|:-------------:|:-----:|:-----:|:---------------:|:--------:|:------:| |
|
| 0.4707 | 1.0 | 2522 | 0.5220 | 0.7553 | 0.7517 | |
|
| 0.4152 | 2.0 | 5044 | 0.4808 | 0.7855 | 0.7854 | |
|
| 0.385 | 3.0 | 7566 | 0.5768 | 0.7846 | 0.7834 | |
|
| 0.3495 | 4.0 | 10088 | 0.7314 | 0.7945 | 0.7945 | |
|
| 0.3282 | 5.0 | 12610 | 0.8054 | 0.7893 | 0.7890 | |
|
| 0.3214 | 6.0 | 15132 | 0.9016 | 0.7898 | 0.7895 | |
|
| 0.3038 | 7.0 | 17654 | 1.0931 | 0.7890 | 0.7890 | |
|
| 0.235 | 8.0 | 20176 | 1.1521 | 0.7749 | 0.7741 | |
|
| 0.1705 | 9.0 | 22698 | 1.3791 | 0.7758 | 0.7756 | |
|
| 0.1252 | 10.0 | 25220 | 1.4324 | 0.7742 | 0.7739 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.36.0.dev0 |
|
- Pytorch 2.0.0 |
|
- Datasets 2.14.5 |
|
- Tokenizers 0.14.1 |
|
|
