|
--- |
|
license: apache-2.0 |
|
base_model: bert-base-multilingual-uncased |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- recall |
|
- accuracy |
|
model-index: |
|
- name: multibert1110_lrate7.5b8 |
|
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. --> |
|
|
|
# multibert1110_lrate7.5b8 |
|
|
|
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: 0.6124 |
|
- Precisions: 0.8795 |
|
- Recall: 0.7898 |
|
- F-measure: 0.8228 |
|
- Accuracy: 0.9026 |
|
|
|
## 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: 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: 14 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Precisions | Recall | F-measure | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:----------:|:------:|:---------:|:--------:| |
|
| 0.6395 | 1.0 | 471 | 0.4532 | 0.8345 | 0.6789 | 0.6899 | 0.8619 | |
|
| 0.3636 | 2.0 | 942 | 0.3956 | 0.8284 | 0.7491 | 0.7766 | 0.8853 | |
|
| 0.2471 | 3.0 | 1413 | 0.5037 | 0.8053 | 0.6950 | 0.7258 | 0.8821 | |
|
| 0.1785 | 4.0 | 1884 | 0.5098 | 0.8444 | 0.7522 | 0.7755 | 0.8936 | |
|
| 0.1279 | 5.0 | 2355 | 0.5574 | 0.8751 | 0.7735 | 0.8077 | 0.8973 | |
|
| 0.097 | 6.0 | 2826 | 0.6124 | 0.8795 | 0.7898 | 0.8228 | 0.9026 | |
|
| 0.071 | 7.0 | 3297 | 0.5377 | 0.8621 | 0.7836 | 0.8157 | 0.9044 | |
|
| 0.0494 | 8.0 | 3768 | 0.5842 | 0.8705 | 0.7725 | 0.8109 | 0.9029 | |
|
| 0.0344 | 9.0 | 4239 | 0.6835 | 0.8705 | 0.7506 | 0.7912 | 0.9010 | |
|
| 0.0276 | 10.0 | 4710 | 0.6916 | 0.8226 | 0.7864 | 0.7999 | 0.9048 | |
|
| 0.0174 | 11.0 | 5181 | 0.7412 | 0.8646 | 0.7491 | 0.7905 | 0.8994 | |
|
| 0.0112 | 12.0 | 5652 | 0.7701 | 0.8258 | 0.7647 | 0.7866 | 0.9018 | |
|
| 0.0084 | 13.0 | 6123 | 0.7811 | 0.8331 | 0.7593 | 0.7899 | 0.9058 | |
|
| 0.0063 | 14.0 | 6594 | 0.7682 | 0.8636 | 0.7763 | 0.8112 | 0.9064 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.34.0 |
|
- Pytorch 2.0.1+cu118 |
|
- Datasets 2.14.5 |
|
- Tokenizers 0.14.1 |
|
|
