|
--- |
|
license: apache-2.0 |
|
base_model: bert-base-multilingual-uncased |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- recall |
|
- accuracy |
|
model-index: |
|
- name: multibert_seed33_1311 |
|
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. --> |
|
|
|
# multibert_seed33_1311 |
|
|
|
This model is a fine-tuned version of [bert-base-multilingual-uncased](https://huggingface.co/bert-base-multilingual-uncased) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.4745 |
|
- Precisions: 0.8770 |
|
- Recall: 0.8049 |
|
- F-measure: 0.8343 |
|
- Accuracy: 0.9364 |
|
|
|
## 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: 7.5e-05 |
|
- train_batch_size: 16 |
|
- eval_batch_size: 16 |
|
- seed: 34 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 14 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Precisions | Recall | F-measure | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:----------:|:------:|:---------:|:--------:| |
|
| 0.4458 | 1.0 | 236 | 0.2719 | 0.8870 | 0.7002 | 0.7379 | 0.9144 | |
|
| 0.2302 | 2.0 | 472 | 0.2497 | 0.8728 | 0.7439 | 0.7647 | 0.9209 | |
|
| 0.139 | 3.0 | 708 | 0.2849 | 0.8797 | 0.7900 | 0.8231 | 0.9340 | |
|
| 0.0881 | 4.0 | 944 | 0.3292 | 0.8694 | 0.7757 | 0.8140 | 0.9296 | |
|
| 0.0539 | 5.0 | 1180 | 0.3674 | 0.8488 | 0.7775 | 0.8061 | 0.9272 | |
|
| 0.0382 | 6.0 | 1416 | 0.3497 | 0.8482 | 0.8083 | 0.8263 | 0.9356 | |
|
| 0.0266 | 7.0 | 1652 | 0.3809 | 0.8435 | 0.8162 | 0.8281 | 0.9366 | |
|
| 0.0187 | 8.0 | 1888 | 0.4222 | 0.8522 | 0.7840 | 0.8096 | 0.9303 | |
|
| 0.0133 | 9.0 | 2124 | 0.4423 | 0.8646 | 0.7878 | 0.8176 | 0.9356 | |
|
| 0.0085 | 10.0 | 2360 | 0.4632 | 0.8538 | 0.8005 | 0.8221 | 0.9342 | |
|
| 0.007 | 11.0 | 2596 | 0.4638 | 0.8632 | 0.8026 | 0.8281 | 0.9342 | |
|
| 0.0031 | 12.0 | 2832 | 0.4679 | 0.8720 | 0.8037 | 0.8303 | 0.9361 | |
|
| 0.0023 | 13.0 | 3068 | 0.4712 | 0.8644 | 0.8098 | 0.8327 | 0.9366 | |
|
| 0.0018 | 14.0 | 3304 | 0.4745 | 0.8770 | 0.8049 | 0.8343 | 0.9364 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.35.0 |
|
- Pytorch 2.1.0+cu118 |
|
- Datasets 2.14.6 |
|
- Tokenizers 0.14.1 |
|
|
