|
--- |
|
license: mit |
|
base_model: xlm-roberta-base |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- precision |
|
- recall |
|
- f1 |
|
model-index: |
|
- name: xlm-roberta-base-Multilingual-Sentence-Segmentation-v4 |
|
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. --> |
|
|
|
# xlm-roberta-base-Multilingual-Sentence-Segmentation-v4 |
|
|
|
This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.0074 |
|
- Precision: 0.9664 |
|
- Recall: 0.9677 |
|
- F1: 0.9670 |
|
|
|
## 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: 2e-05 |
|
- train_batch_size: 64 |
|
- eval_batch_size: 64 |
|
- 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 | |
|
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:| |
|
| No log | 0.2 | 100 | 0.0125 | 0.9320 | 0.9487 | 0.9403 | |
|
| No log | 0.4 | 200 | 0.0099 | 0.9547 | 0.9513 | 0.9530 | |
|
| No log | 0.6 | 300 | 0.0092 | 0.9616 | 0.9506 | 0.9561 | |
|
| No log | 0.81 | 400 | 0.0083 | 0.9584 | 0.9618 | 0.9601 | |
|
| 0.0212 | 1.01 | 500 | 0.0082 | 0.9551 | 0.9642 | 0.9596 | |
|
| 0.0212 | 1.21 | 600 | 0.0084 | 0.9630 | 0.9614 | 0.9622 | |
|
| 0.0212 | 1.41 | 700 | 0.0079 | 0.9606 | 0.9648 | 0.9627 | |
|
| 0.0212 | 1.61 | 800 | 0.0077 | 0.9609 | 0.9661 | 0.9635 | |
|
| 0.0212 | 1.81 | 900 | 0.0076 | 0.9623 | 0.9649 | 0.9636 | |
|
| 0.0067 | 2.02 | 1000 | 0.0077 | 0.9598 | 0.9689 | 0.9643 | |
|
| 0.0067 | 2.22 | 1100 | 0.0075 | 0.9614 | 0.9680 | 0.9647 | |
|
| 0.0067 | 2.42 | 1200 | 0.0073 | 0.9626 | 0.9682 | 0.9654 | |
|
| 0.0067 | 2.62 | 1300 | 0.0075 | 0.9617 | 0.9692 | 0.9654 | |
|
| 0.0067 | 2.82 | 1400 | 0.0073 | 0.9658 | 0.9648 | 0.9653 | |
|
| 0.0054 | 3.02 | 1500 | 0.0076 | 0.9656 | 0.9663 | 0.9660 | |
|
| 0.0054 | 3.23 | 1600 | 0.0073 | 0.9625 | 0.9703 | 0.9664 | |
|
| 0.0054 | 3.43 | 1700 | 0.0073 | 0.9658 | 0.9659 | 0.9658 | |
|
| 0.0054 | 3.63 | 1800 | 0.0073 | 0.9626 | 0.9707 | 0.9666 | |
|
| 0.0054 | 3.83 | 1900 | 0.0073 | 0.9659 | 0.9677 | 0.9668 | |
|
| 0.0046 | 4.03 | 2000 | 0.0075 | 0.9671 | 0.9659 | 0.9665 | |
|
| 0.0046 | 4.23 | 2100 | 0.0075 | 0.9654 | 0.9687 | 0.9671 | |
|
| 0.0046 | 4.44 | 2200 | 0.0075 | 0.9662 | 0.9676 | 0.9669 | |
|
| 0.0046 | 4.64 | 2300 | 0.0074 | 0.9657 | 0.9684 | 0.9670 | |
|
| 0.0046 | 4.84 | 2400 | 0.0074 | 0.9664 | 0.9678 | 0.9671 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.39.1 |
|
- Pytorch 2.2.1+cu121 |
|
- Datasets 2.18.0 |
|
- Tokenizers 0.15.2 |
|
|