<!-- 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 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
