|
--- |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- rouge |
|
model-index: |
|
- name: bert2bert_law_summarization_tr |
|
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. --> |
|
|
|
# bert2bert_law_summarization_tr |
|
|
|
This model is a fine-tuned version of [mrm8488/bert2bert_shared-turkish-summarization](https://huggingface.co/mrm8488/bert2bert_shared-turkish-summarization) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.9682 |
|
- Rouge1: 0.6221 |
|
- Rouge2: 0.5799 |
|
- Rougel: 0.6007 |
|
- Rougelsum: 0.6009 |
|
- Gen Len: 63.3077 |
|
|
|
## 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: 2 |
|
- eval_batch_size: 2 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 4 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len | |
|
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:| |
|
| 1.6025 | 1.0 | 520 | 1.1210 | 0.611 | 0.5687 | 0.5885 | 0.5883 | 62.6154 | |
|
| 1.0845 | 2.0 | 1040 | 1.0161 | 0.62 | 0.5789 | 0.601 | 0.6005 | 63.4038 | |
|
| 0.9252 | 3.0 | 1560 | 0.9784 | 0.6249 | 0.583 | 0.6043 | 0.6045 | 63.2654 | |
|
| 0.858 | 4.0 | 2080 | 0.9682 | 0.6221 | 0.5799 | 0.6007 | 0.6009 | 63.3077 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.28.0 |
|
- Pytorch 2.0.1+cu118 |
|
- Datasets 2.13.0 |
|
- Tokenizers 0.13.3 |
|
|