|
--- |
|
license: apache-2.0 |
|
base_model: google-bert/bert-base-multilingual-cased |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- f1 |
|
- precision |
|
- recall |
|
model-index: |
|
- name: fine_tuned_bert |
|
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. --> |
|
|
|
# fine_tuned_bert |
|
|
|
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: 0.1446 |
|
- F1: 0.6190 |
|
- F5: 0.6548 |
|
- Precision: 0.5417 |
|
- Recall: 0.7222 |
|
|
|
## 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: 5e-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: 10 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | F1 | F5 | Precision | Recall | |
|
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:---------:|:------:| |
|
| No log | 1.0 | 65 | 0.3086 | 0.0 | 0.0 | 0.0 | 0.0 | |
|
| No log | 2.0 | 130 | 0.2538 | 0.5352 | 0.6034 | 0.4130 | 0.76 | |
|
| No log | 3.0 | 195 | 0.3520 | 0.3333 | 0.3107 | 0.4118 | 0.28 | |
|
| No log | 4.0 | 260 | 0.1806 | 0.6531 | 0.6480 | 0.6667 | 0.64 | |
|
| No log | 5.0 | 325 | 0.3014 | 0.5263 | 0.4697 | 0.7692 | 0.4 | |
|
| No log | 6.0 | 390 | 0.2432 | 0.6667 | 0.6562 | 0.6957 | 0.64 | |
|
| No log | 7.0 | 455 | 0.2808 | 0.7059 | 0.7112 | 0.6923 | 0.72 | |
|
| 0.1489 | 8.0 | 520 | 0.2133 | 0.76 | 0.76 | 0.76 | 0.76 | |
|
| 0.1489 | 9.0 | 585 | 0.2639 | 0.7692 | 0.7807 | 0.7407 | 0.8 | |
|
| 0.1489 | 10.0 | 650 | 0.3313 | 0.6809 | 0.6646 | 0.7273 | 0.64 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.38.1 |
|
- Pytorch 2.2.1+cu121 |
|
- Datasets 2.17.0 |
|
- Tokenizers 0.15.2 |
|
|