|
--- |
|
license: apache-2.0 |
|
base_model: bert-base-multilingual-cased |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: Improved-bert-multilingual-nodropout |
|
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. --> |
|
|
|
# Improved-bert-multilingual-nodropout |
|
|
|
This model is a fine-tuned version of [bert-base-multilingual-cased](https://huggingface.co/bert-base-multilingual-cased) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.0144 |
|
- Accuracy: 0.76 |
|
|
|
## 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: 1e-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: 15 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:| |
|
| 0.6855 | 0.55 | 50 | 0.6606 | 0.61 | |
|
| 0.5737 | 1.1 | 100 | 0.5402 | 0.74 | |
|
| 0.4677 | 1.65 | 150 | 0.5966 | 0.67 | |
|
| 0.3866 | 2.2 | 200 | 0.5778 | 0.69 | |
|
| 0.3414 | 2.75 | 250 | 0.4483 | 0.8 | |
|
| 0.3047 | 3.3 | 300 | 0.7158 | 0.68 | |
|
| 0.2366 | 3.85 | 350 | 0.6137 | 0.77 | |
|
| 0.2188 | 4.4 | 400 | 0.5294 | 0.77 | |
|
| 0.2191 | 4.95 | 450 | 0.6734 | 0.73 | |
|
| 0.1935 | 5.49 | 500 | 0.6588 | 0.8 | |
|
| 0.1707 | 6.04 | 550 | 1.0354 | 0.65 | |
|
| 0.1216 | 6.59 | 600 | 0.9658 | 0.69 | |
|
| 0.1093 | 7.14 | 650 | 1.0317 | 0.69 | |
|
| 0.1099 | 7.69 | 700 | 0.9484 | 0.71 | |
|
| 0.1128 | 8.24 | 750 | 1.0144 | 0.76 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.34.1 |
|
- Pytorch 2.1.0+cu118 |
|
- Datasets 2.14.7 |
|
- Tokenizers 0.14.1 |
|
|