|
--- |
|
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: 0.4996 |
|
- Precisions: 0.8590 |
|
- Recall: 0.8170 |
|
- F-measure: 0.8353 |
|
- Accuracy: 0.9359 |
|
|
|
## 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: 33 |
|
- 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 | |
|
|:-------------:|:-----:|:----:|:---------------:|:----------:|:------:|:---------:|:--------:| |
|
| 0.4674 | 1.0 | 236 | 0.2914 | 0.8891 | 0.6852 | 0.7119 | 0.9125 | |
|
| 0.2266 | 2.0 | 472 | 0.2489 | 0.8410 | 0.7811 | 0.8044 | 0.9294 | |
|
| 0.1394 | 3.0 | 708 | 0.2650 | 0.8611 | 0.7777 | 0.7929 | 0.9296 | |
|
| 0.0878 | 4.0 | 944 | 0.2721 | 0.8608 | 0.8165 | 0.8324 | 0.9373 | |
|
| 0.06 | 5.0 | 1180 | 0.3164 | 0.8457 | 0.7877 | 0.8105 | 0.9342 | |
|
| 0.0378 | 6.0 | 1416 | 0.3793 | 0.8788 | 0.7972 | 0.8309 | 0.9335 | |
|
| 0.0285 | 7.0 | 1652 | 0.3807 | 0.8665 | 0.7905 | 0.8233 | 0.9299 | |
|
| 0.0153 | 8.0 | 1888 | 0.4636 | 0.8555 | 0.7855 | 0.8152 | 0.9303 | |
|
| 0.0115 | 9.0 | 2124 | 0.4649 | 0.8336 | 0.8135 | 0.8190 | 0.9337 | |
|
| 0.0064 | 10.0 | 2360 | 0.5120 | 0.8522 | 0.8010 | 0.8219 | 0.9325 | |
|
| 0.0052 | 11.0 | 2596 | 0.5008 | 0.8616 | 0.8034 | 0.8288 | 0.9337 | |
|
| 0.0038 | 12.0 | 2832 | 0.4807 | 0.8616 | 0.8133 | 0.8346 | 0.9354 | |
|
| 0.0016 | 13.0 | 3068 | 0.4995 | 0.8514 | 0.8186 | 0.8322 | 0.9359 | |
|
| 0.0012 | 14.0 | 3304 | 0.4996 | 0.8590 | 0.8170 | 0.8353 | 0.9359 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.35.0 |
|
- Pytorch 2.1.0+cu118 |
|
- Datasets 2.14.6 |
|
- Tokenizers 0.14.1 |
|
|
