|
--- |
|
license: apache-2.0 |
|
base_model: distilbert-base-multilingual-cased |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- precision |
|
- recall |
|
- f1 |
|
- accuracy |
|
model-index: |
|
- name: BERT_B08 |
|
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. --> |
|
|
|
# BERT_B08 |
|
|
|
This model is a fine-tuned version of [distilbert-base-multilingual-cased](https://huggingface.co/distilbert-base-multilingual-cased) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.3054 |
|
- Precision: 0.6335 |
|
- Recall: 0.6849 |
|
- F1: 0.6582 |
|
- Accuracy: 0.9094 |
|
|
|
## 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: 4e-05 |
|
- train_batch_size: 16 |
|
- eval_batch_size: 16 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 5 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:| |
|
| 0.3792 | 1.0 | 92 | 0.3446 | 0.6004 | 0.5913 | 0.5958 | 0.8982 | |
|
| 0.2782 | 2.0 | 184 | 0.2911 | 0.6485 | 0.6664 | 0.6573 | 0.9110 | |
|
| 0.1736 | 3.0 | 276 | 0.2886 | 0.6570 | 0.6730 | 0.6649 | 0.9123 | |
|
| 0.1434 | 4.0 | 368 | 0.2974 | 0.6481 | 0.6763 | 0.6619 | 0.9109 | |
|
| 0.1422 | 5.0 | 460 | 0.3054 | 0.6335 | 0.6849 | 0.6582 | 0.9094 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.33.3 |
|
- Pytorch 2.0.1+cu117 |
|
- Datasets 2.14.4 |
|
- Tokenizers 0.13.3 |
|
|
